Journal articles: 'Slot Filling'

1

Dai, Yinpei, Yichi Zhang, Hong Liu, Zhijian Ou, Yi Huang, and Junlan Feng. "Elastic CRFs for Open-Ontology Slot Filling." Applied Sciences 11, no. 22 (November 12, 2021): 10675. http://dx.doi.org/10.3390/app112210675.

Full text

Abstract:

Slot filling is a crucial component in task-oriented dialog systems that is used to parse (user) utterances into semantic concepts called slots. An ontology is defined by the collection of slots and the values that each slot can take. The most widely used practice of treating slot filling as a sequence labeling task suffers from two main drawbacks. First, the ontology is usually pre-defined and fixed and therefore is not able to detect new labels for unseen slots. Second, the one-hot encoding of slot labels ignores the correlations between slots with similar semantics, which makes it difficult to share knowledge learned across different domains. To address these problems, we propose a new model called elastic conditional random field (eCRF), where each slot is represented by the embedding of its natural language description and modeled by a CRF layer. New slot values can be detected by eCRF whenever a language description is available for the slot. In our experiment, we show that eCRFs outperform existing models in both in-domain and cross-domain tasks, especially in predicting unseen slots and values.

APA, Harvard, Vancouver, ISO, and other styles

2

Khan, Bakhtiar, Faisal Khan, Wasiq Ullah, Muhammad Umair, and Shahid Hussain. "Slot Filling Factor Calculation and Electromagnetic Performance of Single Phase Electrically Excited Flux Switching Motors." Applied Computational Electromagnetics Society 35, no. 8 (October 7, 2020): 922–28. http://dx.doi.org/10.47037/2020.aces.j.350811.

Full text

Abstract:

For variable speed applications, flux controlling capability of electrically excited flux switching motors (EEFSMs) attract researchers’ attention. However, low copper slot filling factor of the EEFSM with standard stator slot vitiates the electromagnetic performance and efficiency. This paper has proposed a new Octane Modular Stator (OMS) EEFSM model that has pentagonal stator slot and high copper slot filling factor. Copper slot filling factor is deliberated analytically for the proposed model and designs with standard stator slots, i.e., trapezoidal and rectangular. Electromagnetic performance of the OMS, Rectangular Stator Slot (RSS) and Trapezoidal Stator Slot (TSS) EEFSM designs are evaluated by finite element analysis (FEA) through JMAG v18.1 FEA solver. The proposed OMS EEFSM model has 9% higher copper slot filling factor in comparison with standard stator slots designs under same geometric parameters. The high copper slot filling factor of the proposed OMS EEFSM model has improved performance in term of low electric and magnetic loading.

APA, Harvard, Vancouver, ISO, and other styles

3

Lee, Sang Yul, and Sang Yong Lee. "Filling and Solidification Characteristics during Thixoforming of Copper Rotor for the Electrical Motors." Solid State Phenomena 116-117 (October 2006): 652–55. http://dx.doi.org/10.4028/www.scientific.net/ssp.116-117.652.

Full text

Abstract:

Filling and solidification phenomena during thixoforming of copper rotor for small sized induction motors have been analyzed and characterized by experiment and computer simulation. Forming defects in slots of thixoformed rotor were examined by microstructural observation. Most filling and solidification failures were mainly related to complexity in slurry flows through slots in rotor core. Computer simulation with single slot model showed the effects of die temperature and ram speed on the filling characteristics clearly. Simulations with flow guide model showed that the control of filling velocity of slurry at slot and the consideration of possible differences in flow velocity in each slot are important.

APA, Harvard, Vancouver, ISO, and other styles

4

Lee, Sang Yul, and Sang Yong Lee. "A Study on the Microstructural Defects in Slots of Thixoformed Copper Rotor." Solid State Phenomena 116-117 (October 2006): 300–303. http://dx.doi.org/10.4028/www.scientific.net/ssp.116-117.300.

Full text

Abstract:

Cu-Ca alloys and the squirrel cage rotors for induction motors of small capacities were used for the development of thixoforming processes. Processing conditions, motor efficiency and forming defects in macro- and microscale for thixoforming of Cu-Ca rotors have been performed to investigate the microstructural features and the filling phenomena in slots of squirrel cage rotor. Inadequate filling due to the complexity of slot structure, separation of solidified metal from the slot, porosities and phase inhomogenitites were typical microstructural defects found in thixoformed Cu-Ca rotors. Exact flow control in terms of billet and die temperatures at slot gate especially, was necessary to prevent significant defects such as incomplete filling of slot.

APA, Harvard, Vancouver, ISO, and other styles

5

Roca, Surya, Sophie Rosset, José García, and Álvaro Alesanco. "A Study on the Impacts of Slot Types and Training Data on Joint Natural Language Understanding in a Spanish Medication Management Assistant Scenario." Sensors 22, no. 6 (March 18, 2022): 2364. http://dx.doi.org/10.3390/s22062364.

Full text

Abstract:

This study evaluates the impacts of slot tagging and training data length on joint natural language understanding (NLU) models for medication management scenarios using chatbots in Spanish. In this study, we define the intents (purposes of the sentences) for medication management scenarios and two types of slot tags. For training the model, we generated four datasets, combining long/short sentences with long/short slots, while for testing, we collect the data from real interactions of users with a chatbot. For the comparative analysis, we chose six joint NLU models (SlotRefine, stack-propagation framework, SF-ID network, capsule-NLU, slot-gated modeling, and a joint SLU-LM model) from the literature. The results show that the best performance (with a sentence-level semantic accuracy of 68.6%, an F1-score of 76.4% for slot filling, and an accuracy of 79.3% for intent detection) is achieved using short sentences and short slots. Our results suggest that joint NLU models trained with short slots yield better results than those trained with long slots for the slot filling task. The results also indicate that short slots could be a better choice for the dialog system because of their simplicity. Importantly, the work demonstrates that the performance of the joint NLU models can be improved by selecting the correct slot configuration according to the usage scenario.

APA, Harvard, Vancouver, ISO, and other styles

6

Lim, Jungwoo, Suhyune Son, Songeun Lee, Changwoo Chun, Sungsoo Park, Yuna Hur, and Heuiseok Lim. "Intent Classification and Slot Filling Model for In-Vehicle Services in Korean." Applied Sciences 12, no. 23 (December 5, 2022): 12438. http://dx.doi.org/10.3390/app122312438.

Full text

Abstract:

Since understanding a user’s request has become a critical task for the artificial intelligence speakers, capturing intents and finding correct slots along with corresponding slot value is significant. Despite various studies concentrating on a real-life situation, dialogue system that is adaptive to in-vehicle services are limited. Moreover, the Korean dialogue system specialized in an vehicle domain rarely exists. We propose a dialogue system that captures proper intent and activated slots for Korean in-vehicle services in a multi-tasking manner. We implement our model with a pre-trained language model, and it includes an intent classifier, slot classifier, slot value predictor, and value-refiner. We conduct the experiments on the Korean in-vehicle services dataset and show 90.74% of joint goal accuracy. Also, we analyze the efficacy of each component of our model and inspect the prediction results with qualitative analysis.

APA, Harvard, Vancouver, ISO, and other styles

7

Adel, Heike, and Hinrich Schuetze. "Type-aware Convolutional Neural Networks for Slot Filling." Journal of Artificial Intelligence Research 66 (September 28, 2019): 297–339. http://dx.doi.org/10.1613/jair.1.11725.

Full text

Abstract:

The slot filling task aims at extracting answers for queries about entities from text, such as "Who founded Apple". In this paper, we focus on the relation classification component of a slot filling system. We propose type-aware convolutional neural networks to benefit from the mutual dependencies between entity and relation classification. In particular, we explore different ways of integrating the named entity types of the relation arguments into a neural network for relation classification, including a joint training and a structured prediction approach. To the best of our knowledge, this is the first study on type-aware neural networks for slot filling. The type-aware models lead to the best results of our slot filling pipeline. Joint training performs comparable to structured prediction. To understand the impact of the different components of the slot filling pipeline, we perform a recall analysis, a manual error analysis and several ablation studies. Such analyses are of particular importance to other slot filling researchers since the official slot filling evaluations only assess pipeline outputs. The analyses show that especially coreference resolution and our convolutional neural networks have a large positive impact on the final performance of the slot filling pipeline. The presented models, the source code of our system as well as our coreference resource is publicly available.

APA, Harvard, Vancouver, ISO, and other styles

8

Dietz, Armin, Antonino Oscar Di Tommaso, Fabrizio Marignetti, Rosario Miceli, and Claudio Nevoloso. "Enhanced Flexible Algorithm for the Optimization of Slot Filling Factors in Electrical Machines." Energies 13, no. 5 (February 26, 2020): 1041. http://dx.doi.org/10.3390/en13051041.

Full text

Abstract:

The continuous development in the field of industrial automation and electric mobility has led to the need for more efficient electrical machines with a high power density. The improvement of electrical machines’ slot filling factors is one of the measures to satisfy these requirements. In recent years, this topic has aroused greater interest in the industrial sector, since the evolution of the winding technological manufacturing processes allows an economically sustainable realization of ordered winding arrangements, rather than random ones. Moreover, the manufacture of electrical machines’ windings must be preceded by an accurate design phase in which it is possible to evaluate the maximum slot filling factor obtainable for a given wire shape and for its dimensions. For this purpose, this paper presents an algorithmic approach for the evaluation of maximum slot filling factors in electrical machines under an ideal geometric premise. In particular, this algorithm has a greater degree of flexibility with respect to the algorithm approaches found in the literature, since the study has been extended to round, rectangular and hexagonal wire sections. Furthermore, the slot filling factor calculation was carried out both for standard and non-standard slots. The algorithmic approach proposed can be considered as an additional useful tool for the fast design of electrical machine windings.

APA, Harvard, Vancouver, ISO, and other styles

9

Sun, Rui, Lu Rao, and Xingfa Zhou. "A Joint Model of Natural Language Understanding for Human-Computer Conversation in IoT." Wireless Communications and Mobile Computing 2022 (August 21, 2022): 1–10. http://dx.doi.org/10.1155/2022/2074035.

Full text

Abstract:

Natural language understanding (NLU) technologies for human-computer conversation is becoming a hot topic in the Internet of Things (IoT). Intent detection and slot filling are two fundamental NLU subtasks. Current approaches to these two subtasks include joint training methods and pipeline methods. Whether treating intent detection and slot filling as two separate tasks or training the two tasks as a joint model utilizing neural networks, most methods fail to build a complete correlation between the intent and slots. Some studies indicate that the intent and slots have a strong relationship because slots often highly depend on intent and also give clues to intent. Thus, recent joint models connect the two subtasks by sharing an intermediate network representation, but we argue that precise label information from one task is more helpful in improving the performance of another task. It is difficult to achieve complete information interaction between intent and slots because the extracted features in existing methods do not contain sufficient label information. Therefore, a novel bidirectional information transfer model is proposed in order to create a sufficient interaction between intent detection and slot filling with type-aware information enhancement. Such a framework collects more explicit label information from the network’s top layer and learns discriminative features from labels. According to the experimental results, our model greatly outperforms previous models and achieves the state-of-the-art performance on the two datasets: ATIS and SNIPS.

APA, Harvard, Vancouver, ISO, and other styles

10

Cheng, Shih Ping, Chang Chou Hwang, and Chia Ming Chang. "Design Techniques for Reducing Cogging Torque in SPM Motors Using Shifted Slot Opening." Applied Mechanics and Materials 284-287 (January 2013): 692–96. http://dx.doi.org/10.4028/www.scientific.net/amm.284-287.692.

Full text

Abstract:

Skewing is one of the most common methods to reduce the cogging torque of permanent magnet synchronous motors. This technique may cause manufacturing troubles such as impossible automatic slot filling due to skewing stator slot. One method to overcome this problem is to use the step twisted stator structure with shifted slot opening. Compared to other methods of skewing, in the presented method, the stator slots are still straight slots and the skewing effect is implemented by shifting slot openings coupled with a step twisted stator design. This paper discusses the use of the step twisted stator structure with shifted slot opening and the associated effects on machine performance. We address the cogging torque, average torque, torque ripple, and back-EMF and its total harmonic distortion (THD). We examine the results using finite element analysis (FEA).

APA, Harvard, Vancouver, ISO, and other styles

11

Youn, Jeong Il, and Young Jig Kim. "Application of Semi-Solid Process for Production of the Induction Motor Squirrel Cage." Solid State Phenomena 116-117 (October 2006): 730–33. http://dx.doi.org/10.4028/www.scientific.net/ssp.116-117.730.

Full text

Abstract:

This paper presents semi-solid processing of Cu-Ag alloy to produce squirrel cage for small and medium induction motors. Complete die filling could be achieved with the slug at 1065 oC, casting pressure of 9 MPa and ram speed of 0.08 m/s. There were no defects in squirrel cage and slug temperature and ram speed affected the slot filling of rotor importantly, however, casting pressure rarely has an effect of the filling in this experiment. As the same thixoforming condition, when the ram speed was 1.5 m/s, slurry could not fill the slot and solidified like a needle shape. The rapid flow like this would be the cause of non-filling defect of slot because the slurry injected and solidified in the slot firstly was became the obstacle not to flow the rest of the slurry.

APA, Harvard, Vancouver, ISO, and other styles

12

Calabrese, Agostina, Björn Ross, and Mirella Lapata. "Explainable Abuse Detection as Intent Classification and Slot Filling." Transactions of the Association for Computational Linguistics 10 (2022): 1440–54. http://dx.doi.org/10.1162/tacl_a_00527.

Full text

Abstract:

Abstract To proactively offer social media users a safe online experience, there is a need for systems that can detect harmful posts and promptly alert platform moderators. In order to guarantee the enforcement of a consistent policy, moderators are provided with detailed guidelines. In contrast, most state-of-the-art models learn what abuse is from labeled examples and as a result base their predictions on spurious cues, such as the presence of group identifiers, which can be unreliable. In this work we introduce the concept of policy-aware abuse detection, abandoning the unrealistic expectation that systems can reliably learn which phenomena constitute abuse from inspecting the data alone. We propose a machine-friendly representation of the policy that moderators wish to enforce, by breaking it down into a collection of intents and slots. We collect and annotate a dataset of 3,535 English posts with such slots, and show how architectures for intent classification and slot filling can be used for abuse detection, while providing a rationale for model decisions.1

APA, Harvard, Vancouver, ISO, and other styles

13

Tran, Thanh, Kai Wei, Weitong Ruan, Ross McGowan, Nathan Susanj, and Grant P. Strimel. "Adaptive Global-Local Context Fusion for Multi-Turn Spoken Language Understanding." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12622–28. http://dx.doi.org/10.1609/aaai.v36i11.21536.

Full text

Abstract:

Recent years have seen significant advances in multi-turn Spoken Language Understanding (SLU), where dialogue contexts are used to guide intent classification and slot filling. However, how to selectively incorporate dialogue contexts, such as previous utterances and dialogue acts, into multi-turn SLU still remains a substantial challenge. In this work, we propose a novel contextual SLU model for multi-turn intent classification and slot filling tasks. We introduce an adaptive global-local context fusion mechanism to selectively integrate dialogue contexts into our model. The local context fusion aligns each dialogue context using multi-head attention, while the global context fusion measures overall context contribution to intent classification and slot filling tasks. Experiments show that on two benchmark datasets, our model achieves absolute F1 score improvements of 2.73% and 2.57% for the slot filling task on Sim-R and Sim M datasets, respectively. Additional experiments on a large-scale, de-identified, in-house dataset further verify the measurable accuracy gains of our proposed model.

APA, Harvard, Vancouver, ISO, and other styles

14

Shi, Xiaoming, Haifeng Hu, Wanxiang Che, Zhongqian Sun, Ting Liu, and Junzhou Huang. "Understanding Medical Conversations with Scattered Keyword Attention and Weak Supervision from Responses." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 8838–45. http://dx.doi.org/10.1609/aaai.v34i05.6412.

Full text

Abstract:

In this work, we consider the medical slot filling problem, i.e., the problem of converting medical queries into structured representations which is a challenging task. We analyze the effectiveness of two points: scattered keywords in user utterances and weak supervision with responses. We approach the medical slot filling as a multi-label classification problem with label-embedding attentive model to pay more attention to scattered medical keywords and learn the classification models by weak-supervision from responses. To evaluate the approaches, we annotate a medical slot filling data and collect a large scale unlabeled data. The experiments demonstrate that these two points are promising to improve the task.

APA, Harvard, Vancouver, ISO, and other styles

15

Bott, Oliver, and Torgrim Solstad. "Discourse expectations: explaining the implicit causality biases of verbs." Linguistics 59, no. 2 (February 17, 2021): 361–416. http://dx.doi.org/10.1515/ling-2021-0007.

Full text

Abstract:

Abstract This article presents a linguistic account explaining particular mechanisms underlying the generation of expectations at the discourse level. We further develop a linguistic theory – the Empty Slot Theory – explaining the phenomenon of implicit verb causality. According to our proposal, implicit causality (IC) verbs introduce lexically determined slots for causal content of specific types. If the required information is not derivable from the current or preceding context, IC verbs generate the expectation that these slots will be filled in the upcoming discourse. The cognitive mechanism underlying the bias is grounded in the general processing strategy of avoiding accommodation. Empirical evidence for the proposed theory is provided in three continuation experiments in German with comprehensive semantic annotation of the continuations provided by the participants. The reported experiments consistently show that IC bias can be manipulated in systematic ways. Experiment 1 demonstrates important ontological constraints on causal content crucial for our theory. Experiments 2 and 3 show how IC biases can be manipulated in predictable ways by filling the hypothesized slots in the prompt. Experiment 2 illustrates that stimulus-experiencer (experiencer-object) verbs in contrast to causative agent-patient verbs can be manipulated with respect to coherence and coreference by employing adverbial modification. Filling the lexically determined slot of psychological verbs resulted in predictable changes in coherence relations and types of explanations, resulting in the predicted effects on coreference. Experiment 3 extends the empirical investigations to so-called “agent-evocator” verbs. Again, filling the semantic slot as part of the prompt resulted in predictable shifts in coherence relations and explanation types with transparent effects on coreference. The reported experiments shed further light on the close correspondence between coherence and coreference as a hallmark of natural language discourse.

APA, Harvard, Vancouver, ISO, and other styles

16

Chen, Sixuan, and Shuai Yu. "WAIS: Word Attention for Joint Intent Detection and Slot Filling." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 9927–28. http://dx.doi.org/10.1609/aaai.v33i01.33019927.

Full text

Abstract:

Attention-based recurrent neural network models for joint intent detection and slot filling have achieved a state-of-the-art performance. Most previous works exploited semantic level information to calculate the attention weights. However, few works have taken the importance of word level information into consideration. In this paper, we propose WAIS, word attention for joint intent detection and slot filling. Considering that intent detection and slot filling have a strong relationship, we further propose a fusion gate that integrates the word level information and semantic level information together for jointly training the two tasks. Extensive experiments show that the proposed model has robust superiority over its competitors and sets the state-of-the-art.

APA, Harvard, Vancouver, ISO, and other styles

17

Wei, Pengfei, Bi Zeng, and Wenxiong Liao. "Joint intent detection and slot filling with wheel-graph attention networks." Journal of Intelligent & Fuzzy Systems 42, no. 3 (February 2, 2022): 2409–20. http://dx.doi.org/10.3233/jifs-211674.

Full text

Abstract:

Intent detection and slot filling are recognized as two very important tasks in a spoken language understanding (SLU) system. In order to model these two tasks at the same time, many joint models based on deep neural networks have been proposed recently and archived excellent results. In addition, graph neural network has made good achievements in the field of vision. Therefore, we combine these two advantages and propose a new joint model with a wheel-graph attention network (Wheel-GAT), which is able to model interrelated connections directly for single intent detection and slot filling. To construct a graph structure for utterances, we create intent nodes, slot nodes, and directed edges. Intent nodes can provide utterance-level semantic information for slot filling, while slot nodes can also provide local keyword information for intent detection. The two tasks promote each other and carry out end-to-end training at the same time. Experiments show that our proposed approach is superior to multiple baselines on ATIS and SNIPS datasets. Besides, we also demonstrate that using bi-directional encoder representation from transformer (BERT) model further boosts the performance of the SLU task.

APA, Harvard, Vancouver, ISO, and other styles

18

Wang, Jue, Ke Chen, Lidan Shou, Sai Wu, and Gang Chen. "Effective Slot Filling via Weakly-Supervised Dual-Model Learning." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 16 (May 18, 2021): 13952–60. http://dx.doi.org/10.1609/aaai.v35i16.17643.

Full text

Abstract:

Slot filling is a challenging task in Spoken Language Understanding (SLU). Supervised methods usually require large amounts of annotation to maintain desirable performance. A solution to relieve the heavy dependency on labeled data is to employ bootstrapping, which leverages unlabeled data. However, bootstrapping is known to suffer from semantic drift. We argue that semantic drift can be tackled by exploiting the correlation between slot values (phrases) and their respective types. By using some particular weakly labeled data, namely the plain phrases included in sentences, we propose a weakly-supervised slot filling approach. Our approach trains two models, namely a classifier and a tagger, which can effectively learn from each other on the weakly labeled data. The experimental results demonstrate that our approach achieves better results than standard baselines on multiple datasets, especially in the low-resource setting.

APA, Harvard, Vancouver, ISO, and other styles

19

Fan, Jun-Feng, Mei-Ling Wang, Chang-Liang Li, Zi-Qiang Zhu, and Lu Mao. "Intent-Slot Correlation Modeling for Joint Intent Prediction and Slot Filling." Journal of Computer Science and Technology 37, no. 2 (March 31, 2022): 309–19. http://dx.doi.org/10.1007/s11390-020-0326-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Fan, Jun-Feng, Mei-Ling Wang, Chang-Liang Li, Zi-Qiang Zhu, and Lu Mao. "Intent-Slot Correlation Modeling for Joint Intent Prediction and Slot Filling." Journal of Computer Science and Technology 37, no. 2 (March 31, 2022): 309–19. http://dx.doi.org/10.1007/s11390-020-0326-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Yanli, Hui. "Research on Spoken Language Understanding Based on Deep Learning." Scientific Programming 2021 (October 27, 2021): 1–9. http://dx.doi.org/10.1155/2021/8900304.

Full text

Abstract:

Aiming at solving the problem that the recognition effect of rare slot values in spoken language is poor, which affects the accuracy of oral understanding task, a spoken language understanding method is designed based on deep learning. The local features of semantic text are extracted and classified to make the classification results match the dialogue task. An intention recognition algorithm is designed for the classification results. Each datum has a corresponding intention label to complete the task of semantic slot filling. The attention mechanism is applied to the recognition of rare slot value information, the weight of hidden state and corresponding slot characteristics are obtained, and the updated slot value is used to represent the tracking state. An auxiliary gate unit is constructed between the upper and lower slots of historical dialogue, and the word vector is trained based on deep learning to complete the task of spoken language understanding. The simulation results show that the proposed method can realize multiple rounds of man-machine spoken language. Compared with the spoken language understanding methods based on cyclic network, context information, and label decomposition, it has higher accuracy and F1 value and has higher practical application value.

APA, Harvard, Vancouver, ISO, and other styles

22

He, Ting, Xiaohong Xu, Yating Wu, Huazhen Wang, and Jian Chen. "Multitask Learning with Knowledge Base for Joint Intent Detection and Slot Filling." Applied Sciences 11, no. 11 (May 26, 2021): 4887. http://dx.doi.org/10.3390/app11114887.

Full text

Abstract:

Intent detection and slot filling are important modules in task-oriented dialog systems. In order to make full use of the relationship between different modules and resource sharing, solving the problem of a lack of semantics, this paper proposes a multitasking learning intent-detection system, based on the knowledge-base and slot-filling joint model. The approach has been used to share information and rich external utility between intent and slot modules in a three-part process. First, this model obtains shared parameters and features between the two modules based on long short-term memory and convolutional neural networks. Second, a knowledge base is introduced into the model to improve its performance. Finally, a weighted-loss function is built to optimize the joint model. Experimental results demonstrate that our model achieves better performance compared with state-of-the-art algorithms on a benchmark Airline Travel Information System (ATIS) dataset and the Snips dataset. Our joint model achieves state-of-the-art results on the benchmark ATIS dataset with a 1.33% intent-detection accuracy improvement, a 0.94% slot filling F value improvement, and with 0.19% and 0.31% improvements respectively on the Snips dataset.

APA, Harvard, Vancouver, ISO, and other styles

23

Wang, Jixuan, Kai Wei, Martin Radfar, Weiwei Zhang, and Clement Chung. "Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Filling." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 16 (May 18, 2021): 13943–51. http://dx.doi.org/10.1609/aaai.v35i16.17642.

Full text

Abstract:

We propose a novel Transformer encoder-based architecture with syntactical knowledge encoded for intent detection and slot filling. Specifically, we encode syntactic knowledge into the Transformer encoder by jointly training it to predict syntactic parse ancestors and part-of-speech of each token via multi-task learning. Our model is based on self-attention and feed-forward layers and does not require external syntactic information to be available at inference time. Experiments show that on two benchmark datasets, our models with only two Transformer encoder layers achieve state-of-the-art results. Compared to the previously best performed model without pre-training, our models achieve absolute F1 score and accuracy improvement of 1.59 % and 0.85 % for slot filling and intent detection on the SNIPS dataset, respectively. Our models also achieve absolute F1 score and accuracy improvement of 0.1 % and 0.34 % for slot filling and intent detection on the ATIS dataset, respectively, over the previously best performed model. Furthermore, the visualization of the self-attention weights illustrates the benefits of incorporating syntactic information during training.

APA, Harvard, Vancouver, ISO, and other styles

24

Zhang, Linhao, Dehong Ma, Xiaodong Zhang, Xiaohui Yan, and Houfeng Wang. "Graph LSTM with Context-Gated Mechanism for Spoken Language Understanding." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 9539–46. http://dx.doi.org/10.1609/aaai.v34i05.6499.

Full text

Abstract:

Much research in recent years has focused on spoken language understanding (SLU), which usually involves two tasks: intent detection and slot filling. Since Yao et al.(2013), almost all SLU systems are RNN-based, which have been shown to suffer various limitations due to their sequential nature. In this paper, we propose to tackle this task with Graph LSTM, which first converts text into a graph and then utilizes the message passing mechanism to learn the node representation. Not only the Graph LSTM addresses the limitations of sequential models, but it can also help to utilize the semantic correlation between slot and intent. We further propose a context-gated mechanism to make better use of context information for slot filling. Our extensive evaluation shows that the proposed model outperforms the state-of-the-art results by a large margin.

APA, Harvard, Vancouver, ISO, and other styles

25

LI, Sixia, Shogo OKADA, and Jianwu DANG. "Intrinsic Representation Mining for Zero-Shot Slot Filling." IEICE Transactions on Information and Systems E105.D, no. 11 (November 1, 2022): 1947–56. http://dx.doi.org/10.1587/transinf.2022edp7026.

Full text

APA, Harvard, Vancouver, ISO, and other styles

26

Gong, Yu, Xusheng Luo, Yu Zhu, Wenwu Ou, Zhao Li, Muhua Zhu, Kenny Q. Zhu, Lu Duan, and Xi Chen. "Deep Cascade Multi-Task Learning for Slot Filling in Online Shopping Assistant." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 6465–72. http://dx.doi.org/10.1609/aaai.v33i01.33016465.

Full text

Abstract:

Slot filling is a critical task in natural language understanding (NLU) for dialog systems. State-of-the-art approaches treat it as a sequence labeling problem and adopt such models as BiLSTM-CRF. While these models work relatively well on standard benchmark datasets, they face challenges in the context of E-commerce where the slot labels are more informative and carry richer expressions. In this work, inspired by the unique structure of E-commerce knowledge base, we propose a novel multi-task model with cascade and residual connections, which jointly learns segment tagging, named entity tagging and slot filling. Experiments show the effectiveness of the proposed cascade and residual structures. Our model has a 14.6% advantage in F1 score over the strong baseline methods on a new Chinese E-commerce shopping assistant dataset, while achieving competitive accuracies on a standard dataset. Furthermore, online test deployed on such dominant E-commerce platform shows 130% improvement on accuracy of understanding user utterances. Our model has already gone into production in the E-commerce platform.

APA, Harvard, Vancouver, ISO, and other styles

27

Zhang, Zhen, Hao Huang, and Kai Wang. "Using Deep Time Delay Neural Network for Slot Filling in Spoken Language Understanding." Symmetry 12, no. 6 (June 10, 2020): 993. http://dx.doi.org/10.3390/sym12060993.

Full text

Abstract:

Modeling the context of a target word is of fundamental importance in predicting the semantic label for slot filling task in Spoken Language Understanding (SLU). Although Recurrent Neural Network (RNN) has shown to successfully achieve the state-of-the-art results for SLU, and Bidirectional RNN is capable of obtaining further improvement by modeling information not only from the past, but also from the future, they only consider limited contextual information of the target word. In order to make the network deeper and hence obtain longer contextual information, we propose to use a multi-layer Time Delay Neural Network (TDNN), which is prevalent in current large vocabulary continuous speech recognition tasks. In particular, we use a TDNN with symmetric time delay offset. To make the stacked TDNN easily trained, residual structures and skip concatenation are adopted. In addition, we further improve the model by introducing ResTDNN-BiLSTM, which combines the advantages of both the residual TDNN and BiLSTM. Experiments on slot filling tasks on the Air Travel Information System (ATIS) and Snips benchmark datasets show the proposed SC-TDNN-C achieves state-of-the-art results without any additional knowledge and data resources. Finally, we review and compare slot filling results by using a variety of existing models and methods.

APA, Harvard, Vancouver, ISO, and other styles

28

Гончаренко, Игорь Андреевич, Виталий Николаевич Рябцев, Александр Васильевич Ильюшонок, and Олег Дмитриевич Навроцкий. "Sensor of high frequency electric fields intensity on the base of slot waveguides with electro-optic polymer filling." Journal of Civil Protection 4, no. 4 (November 20, 2020): 378–88. http://dx.doi.org/10.33408/2519-237x.2020.4-4.378.

Full text

Abstract:

Purpose. Development of the structure and operation principles of high frequency electric fields intensity optical sensor. Methods. Method of lines was used for calculation of propagation constants and mode electric fields distribution of strip waveguides with vertical and horizontal slots filled with electro-optical polymer SEO125. Findings. The structure and operation principles of high frequency electric fields intensity sensor on the base of slot waveguides with vertical and horizontal slots filled with electro-optical polymer are proposed. Sensor makes it possible measuring the variable electric fields with frequencies up to 10 MHz. The sensor sensitivity order is of 30 V/m. Application field of research. Determination of fire-dangerous and injurious factors of electric field during emergencies elimination.

APA, Harvard, Vancouver, ISO, and other styles

29

Pertiwi, Novalia, Fannush Shofi Akbar, Eko Setijadi, and Gamantyo Hendrantoro. "Linear Array Thinning with Cavity backed U-slot Patch Antenna using Genetic Algorithm." Journal of Science and Applicative Technology 5, no. 1 (March 11, 2021): 9. http://dx.doi.org/10.35472/jsat.v5i1.386.

Full text

Abstract:

In this paper, a thinned linear array with Cavity backed U-slot Patch has been investigated using the Genetic Algorithm to minimize peak sidelobe level and the number of antenna elements. One of the essential steps in the Genetic Algorithm method is a crossover, which uses the Paired Top Ten and Combined Top Five rules applied to the Cavity backed U-slot Patch antenna. The peak sidelobe level value is -18.63 dB with a array filling of 63.33% at the broadside angle using Combined Top Five rules. In Paired Top Ten, the peak sidelobe level value is -19.48 dB with a array filling of 70%. The two methods are still better as compared to a dense array. This study is essential in the development of radar technologies since it needs a low sidelobe level.

APA, Harvard, Vancouver, ISO, and other styles

30

Lange Di Cesare, Kevin, Amal Zouaq, Michel Gagnon, and Ludovic Jean-Louis. "A Machine Learning Filter for the Slot Filling Task." Information 9, no. 6 (May 30, 2018): 133. http://dx.doi.org/10.3390/info9060133.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

Hermawan, Faried. "Using Intelligent Tutoring Systems Through Cognitive Tutor Authoring Tools to Solve Filling Slot Problems." Jurnal Pendidikan Matematika (Kudus) 5, no. 1 (June 26, 2022): 93. http://dx.doi.org/10.21043/jpmk.v5i1.14484.

Full text

Abstract:

Intelligent Tutoring Systems (ITS) is a computer system that provides instructions and is adapted to students who apply learning by doing theory. Cognitive Tutor Authoring Tools (CTAT) is one of ITS that supports the creation of flexible tutors for simple problems and complex solutions, able to support several strategies so that they can describe what students do when solving problems. In working on the problem of filling the place, students will solve the problem according to the students' logic of thinking. This is because the logic of thinking of each student is different depending on the information he receives. For this reason, in this study, the use of CTAT will be tried in working on filling slot questions using media, namely Intelligent Tutoring Systems (ITS) which uses Cognitive Tutor Authoring Tools (CTAT) tools. In this study, students have obtained the filling slot material first. Only then is the media used which will later be used to work on filling slot questions with different problems. From this research, it was found that the results of the study were increasing students' understanding in working on filling slot questions using Cognitive Tutor Authoring Tools (CTAT) media.So that the Cognitive Tutor Authoring Tools (CTAT) media can be used as an alternative learning media to develop students' understanding of filling slot material. Intelligent Tutoring Systems (ITS) adalah sistem komputer yang memberikan instruksi dan disesuaikan dengan siswa yang menerapkan learning by doing theory. Cognitive Tutor Authoring Tools (CTAT) merupakan salah satu ITS yang mendukung terciptanya tutor yang fleksibel untuk masalah sederhana dan solusi kompleks, mampu mendukung beberapa strategi sehingga dapat menggambarkan apa yang dilakukan siswa saat menyelesaikan masalah. Dalam mengerjakan soal aturan pengisian tempat, siswa akan menyelesaikan soal tersebut sesuai dengan logika berpikir siswa. Hal ini dikarenakan logika berpikir setiap siswa berbeda-beda tergantung dari informasi yang diterimanya. Untuk itu pada penelitian ini akan dicoba penggunaan CTAT dalam mengerjakan soal aturan pengisian tempat menggunakan media yaitu Intelligent Tutoring Systems (ITS) yang menggunakan tools Cognitive Tutor Authoring Tools (CTAT). Pada penelitian ini siswa telah memperoleh materi aturan pengisian tempat terlebih dahulu. Baru kemudian digunakan media yang nantinya akan digunakan untuk mengerjakan soal aturan pengisian tempat dengan soal yang berbeda. Dari penelitian ini diketahui bahwa hasil penelitian adalah peningkatan pemahaman siswa dalam mengerjakan soal aturan pengisian tempat menggunakan media Cognitive Tutor Authoring Tools (CTAT). Sehingga media Cognitive Tutor Authoring Tools (CTAT) dapat digunakan sebagai media pembelajaran alternatif untuk mengembangkan pemahaman siswa terhadap materi aturan pengisian tempat.

APA, Harvard, Vancouver, ISO, and other styles

32

Andreev, A. M., A. I. Tadzhibaev, A. Sh Azizov, A. M. Kostelov, A. A. Stepanov, G. A. Nazarov, and S. A. Ivanov. "Ensuring the reliability of turbogenerators on the basis of the control of discharge processes in the stator winding insulation." Safety and Reliability of Power Industry 15, no. 3 (November 14, 2022): 199–204. http://dx.doi.org/10.24223/1999-5555-2022-15-3-199-204.

Full text

Abstract:

Issues related to the reliability of the electrical insulation system of high-load powerful turbogenerators with indirect gas cooling are considered and analyzed. The mechanisms of aging of the main components (main insulation, slot filling elements) of the insulation system under operating conditions exposed to electrical and thermal fields, and mechanical forces are studied. Modern ideas about the mechanisms of aging of main insulation and slot filling elements under the action of internal and external impacts (slot and spark discharges) are analyzed. The degradation of insulating materials during operation begins, first of all, in a weak local area of the main insulation, characterized by a large number of technological defects (cavities filled with gas), in which internal partial discharges occur. However, thermosetting insulation of high-voltage electrical machines can function normally throughout its lifetime in the presence of rather intense internal discharges. At the same time, no service life deterioration is observed due to the specific properties of modern main insulation, which contains a mica barrier. The greatest danger is posed by slot partial discharges (SPD) and vibration spark discharges (VS) that occur in the slot area of the stator winding. To reduce the intensity of these discharge processes, it is necessary to optimize the design of the anti-corona coating. On the basis of the performed analysis, a scheme was developed of the aging of the electrical insulation system of the stator winding of air-cooled turbogenerators. Based on the results of prototype tests, an estimated assessment of the "lifetime" of the electrical insulation system of the stator winding, developed using promising electrical insulating materials, was carried out.

APA, Harvard, Vancouver, ISO, and other styles

33

Buzheninov, A. E. "Conventional and Innovative Metaphors with Source Sphere “Liquidity” in English Investment Discourse." Nauchnyi dialog 11, no. 2 (March 18, 2022): 9–27. http://dx.doi.org/10.24224/2227-1295-2022-11-2-9-27.

Full text

Abstract:

The results of the metaphorical model study “investment phenomenon is a liquid” in the investment English discourse are presented. The relevance of the study is due, on the one hand, to the most important epistemological role of metaphor as a mechanism that categorizes, interprets and forms knowledge about the world and its phenomena, and on the other hand, the fact that the study of the metaphorical model is carried out on the basis of scientific discourse. The methodological basis of the study is the frame-slot analysis of the metaphorical model, which includes contextual, component and definitional types of analysis of the metaphorically used lexical units. A review of works devoted to various aspects of the study of conventional and innovative metaphors is given. The work develops a frame-slot structure of the metaphorical model under study, which is represented by such frames as “Movement of a liquid” (slots: “Vessels”, “Reservoirs”), “Disasters” and “Procedural properties of a liquid”. Particular attention is paid to the role of conventional and innovative metaphors in the conceptualization of investment phenomena. The derivative nature of innovative metaphors from conventional ones is shown, the first ones represent a further expansion of the conceptual links between the target sphere and the source sphere by occasional lexical filling of the target slots.

APA, Harvard, Vancouver, ISO, and other styles

34

Abood, Israa, Sayed Elshahat, and Zhengbiao Ouyang. "High Figure of Merit Optical Buffering in Coupled-Slot Slab Photonic Crystal Waveguide with Ionic Liquid." Nanomaterials 10, no. 9 (September 3, 2020): 1742. http://dx.doi.org/10.3390/nano10091742.

Full text

Abstract:

Slow light with adequate low group velocity and wide bandwidth with a flat band of the zero-dispersion area were investigated. High buffering capabilities were obtained in a silicon-polymer coupled-slot slab photonic crystal waveguide (SP-CS-SPCW) with infiltrating slots by ionic liquid. A figure of merit (FoM) around 0.663 with the lowest physical bit length Lbit of 4.6748 µm for each stored bit in the optical communication waveband was gained by appropriately modifying the square air slot length. Posteriorly, by filling the slots with ionic liquid, the Lbit was enhanced to be 4.2817 μm with the highest FoM of 0.72402 in wider transmission bandwidth and ultra-high bit rate in terabit range, which may become useful for the future 6G mobile communication network. Ionic liquids have had a noticeable effect in altering the optical properties of photonic crystals. A polymer was used for the future incorporation of an electro-optic effect in buffers to realize the dynamic controlling of optical properties. Ionic liquids enhanced the transmission rate through optical materials. Additionally, the delay time in the ns-range was achieved, providing longer delay and ultra-low group velocity, which is important for light-matter interaction in light amplifiers and nonlinear devices.

APA, Harvard, Vancouver, ISO, and other styles

35

Hou, Yutai, Sanyuan Chen, Wanxiang Che, Cheng Chen, and Ting Liu. "C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 14 (May 18, 2021): 13027–35. http://dx.doi.org/10.1609/aaai.v35i14.17540.

Full text

Abstract:

Slot filling, a fundamental module of spoken language understanding, often suffers from insufficient quantity and diversity of training data. To remedy this, we propose a novel Cluster-to-Cluster generation framework for Data Augmentation (DA), named C2C-GenDA. It enlarges the training set by reconstructing existing utterances into alternative expressions while keeping semantic. Different from previous DA works that reconstruct utterances one by one independently, C2C-GenDA jointly encodes multiple existing utterances of the same semantics and simultaneously decodes multiple unseen expressions. Jointly generating multiple new utterances allows to consider the relations between generated instances and encourages diversity. Besides, encoding multiple existing utterances endows C2C with a wider view of existing expressions, helping to reduce generation that duplicates existing data. Experiments on ATIS and Snips datasets show that instances augmented by C2C-GenDA improve slot filling by 7.99 (11.9%↑) and 5.76 (13.6%↑) F-scores respectively, when there are only hundreds of training utterances. Code: https://github.com/Sanyuan-Chen/C2C-DA.

APA, Harvard, Vancouver, ISO, and other styles

36

Chernobrovkin, R. E., I. V. Ivanchenko, A. M. Korolev, N. A. Popenko, and K. Yu Sirenko. "The Novel Microwave Stop-Band Filter." Active and Passive Electronic Components 2008 (2008): 1–5. http://dx.doi.org/10.1155/2008/745368.

Full text

Abstract:

The stop-band filter with the new band-rejection element is proposed. The element is a coaxial waveguide with the slot in the centre conductor. In the frame of this research, the numerical and experimental investigations of the amplitude-frequency characteristics of the filter are carried out. It is noted that according to the slot parameters the two typical resonances (half-wave and quarter-wave) can be excited. The rejection band of the single element is defined by the width, depth, and dielectric filling of the slot. Fifth-order Chebyshev filter utilizing the aforementioned element is also synthesized, manufactured, and tested. The measured and simulated results are in good agreement. The experimental filter prototype exhibits the rejection band 0.86 GHz at the level −40 dB.

APA, Harvard, Vancouver, ISO, and other styles

37

Zhou, Luwang, Zhimin Huang, and Ying Nie. "Research of Attention-Based Bi-GRU-CRF for Slot Filling." Journal of Physics: Conference Series 1757, no. 1 (January 1, 2021): 012077. http://dx.doi.org/10.1088/1742-6596/1757/1/012077.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Ghali, H. A., and T. A. Moselhy. "Broad-band and circularly polarized space-filling-based slot antennas." IEEE Transactions on Microwave Theory and Techniques 53, no. 6 (June 2005): 1946–50. http://dx.doi.org/10.1109/tmtt.2005.848843.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Loope, David. "Cut, Fill, Repeat: Slot Canyons of Dry Fork, Kane County." Geosites 1 (March 13, 2020): 1–8. http://dx.doi.org/10.31711/geosites.v1i1.61.

Full text

Abstract:

The slot canyons of southern Utah have become popular destinations for hikers, climbers, and photographers. For most of these canyons, the geology is simple: sediment carried by flowing water abrades a thick, homogeneous sandstone. As time passes, the rate of down- cutting is rapid compared to the rate of cliff retreat. End of story. The strange abundance and configuration of the slot canyons along Dry Fork Coyote (a tributary of Coyote Gulch and the Escalante River), however, have a convoluted geologic history that is climate-driven and involves canyon cutting, canyon filling, and more canyon cutting.

APA, Harvard, Vancouver, ISO, and other styles

40

Torreggiani, Ambra, Claudio Bianchini, Matteo Davoli, and Alberto Bellini. "Design for Reliability: The Case of Fractional-Slot Surface Permanent-Magnet Machines." Energies 12, no. 9 (May 5, 2019): 1691. http://dx.doi.org/10.3390/en12091691.

Full text

Abstract:

Surface permanent-magnet machines are widely used in different applications, from industrial automation to home appliance and electrical traction. Among any possible machine topology, the fractional-slot surface permanent-magnet one has gained increasing importance, because of its high torque density, low cogging torque, extended flux weakening capability and high efficiency. In addition, fractional-slot machines are attractive for tooth concentrated windings, which allow some optimized manufacturing solutions such as modular stator tooth and high slot filling factor, which result in copper volume reduction; cost reduction, and lower stator parasitic resistances. The slot–pole combination is one of the most important design parameter and, as shown in this paper, it affects performances and the robustness of the machine with respect to the manufacturing imperfections. In the literature, slot–pole combinations are optimized at design phase by finite-element analysis relying on a healthy machine model. The original contribution of this paper is a design for reliability method that models manufacturing defects and includes them at design phase in the optimization process of slot–pole combinations. A method is presented that allows defining the optimal design parameters for maximum performances and robustness towards unavoidable imperfections caused by tolerances of the manufacturing process.

APA, Harvard, Vancouver, ISO, and other styles

41

Banman, P. P. "Titles of Memoir and Autobiographical Texts about First World War: “War Captivity” Frame." Nauchnyi dialog, no. 5 (May 28, 2021): 9–24. http://dx.doi.org/10.24224/2227-1295-2021-5-9-24.

Full text

Abstract:

The article is devoted to the analysis of the “Kriegsgefangenschaft” / “War Captivity” frame, the identification of its slots and their filling based on the headings of German-language memoir and autobiographical texts written by prisoners of war of the First World War. It is noted that these materials did not become the subject of a wide study of Russian-speaking researchers. The author draws attention to the fact that headings, being a strong position of the text, are aimed at attracting the attention of a potential recipient. It has been established that in the course of the author’s semantization, the concept of “captivity” is subject to rethinking: places of stay in captivity (Russia, Siberia) are described as disastrous: the camps become a prison for prisoners of war who, despite the existence of conventions protecting their rights, turn into convicts. It is shown that the slot “time” implies either an exact indication of the historical period (the years of the First World War), or the duration of being in captivity; in isolated cases, we are talking about the age and period of a person’s life. It has been established that the “agent” slot is filled with anthroponyms, indicating nationality, position, rank, profession. The author comes to the conclusion that the identified slots get their further implementation at the text level.

APA, Harvard, Vancouver, ISO, and other styles

42

Li, Lu, and Fang Wang. "Comparative Study of Comprehensive Performance on Typical Die Structures in Knuckle Hot Forging." Applied Mechanics and Materials 121-126 (October 2011): 3180–84. http://dx.doi.org/10.4028/www.scientific.net/amm.121-126.3180.

Full text

Abstract:

In order to improve the severe service conditions and balance the needs between the better filling capacity and longer die life, a new flash structure named by resistance wall was introduced into knuckle hot extrusion dies. Focusing on filling capacity, the maximum deformation load and the highest die surface-layer temperature, different die structures, such as flash slot structure, traditional closed die structure and resistance wall structure, were comparatively analyzed by FEM simulation. It is shown that the resistance wall structure can be extensively used in many applications thanks to its comprehensive performance.

APA, Harvard, Vancouver, ISO, and other styles

43

Lyakhovsky, A. F., L. P. Yatsuk, V. A. Katrich, A. A. Lyakhovsky, and S. L. Berdnik. "INTERNAL PARTIAL CONDUCTANCES OF A LONGITUDINAL SLOT WITH PARTIAL DIELECTRIC FILLING." Telecommunications and Radio Engineering 78, no. 4 (2019): 281–93. http://dx.doi.org/10.1615/telecomradeng.v78.i4.10.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Wakabayashi, Kei, Johane Takeuchi, and Mikio Nakano. "Robust Slot Filling Modeling for Incomplete Annotations using Segmentation-Based Formulation." Transactions of the Japanese Society for Artificial Intelligence 37, no. 3 (May 1, 2022): IDS—E_1–12. http://dx.doi.org/10.1527/tjsai.37-3_ids-e.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Liu, Jian, Mengshi Yu, Yufeng Chen, and Jinan Xu. "Cross-Domain Slot Filling as Machine Reading Comprehension: A New Perspective." IEEE/ACM Transactions on Audio, Speech, and Language Processing 30 (2022): 673–85. http://dx.doi.org/10.1109/taslp.2022.3140559.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Firdaus, Mauajama, Ankit Kumar, Asif Ekbal, and Pushpak Bhattacharyya. "A Multi-Task Hierarchical Approach for Intent Detection and Slot Filling." Knowledge-Based Systems 183 (November 2019): 104846. http://dx.doi.org/10.1016/j.knosys.2019.07.017.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Mesnil, Gregoire, Yann Dauphin, Kaisheng Yao, Yoshua Bengio, Li Deng, Dilek Hakkani-Tur, Xiaodong He, et al. "Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding." IEEE/ACM Transactions on Audio, Speech, and Language Processing 23, no. 3 (March 2015): 530–39. http://dx.doi.org/10.1109/taslp.2014.2383614.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Säynätjoki, A., T. Alasaarela, A. Khanna, L. Karvonen, P. Stenberg, M. Kuittinen, A. Tervonen, and S. Honkanen. "Angled sidewalls in silicon slot waveguides: conformal filling and mode properties." Optics Express 17, no. 23 (November 4, 2009): 21066. http://dx.doi.org/10.1364/oe.17.021066.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Wang, Xueying, and Meng Jiang. "Precise temporal slot filling via truth finding with data-driven commonsense." Knowledge and Information Systems 62, no. 10 (July 16, 2020): 4113–39. http://dx.doi.org/10.1007/s10115-020-01493-w.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Liu, Xin, RuiHua Qi, and Lin Shao. "Joint Model-Based Attention for Spoken Language Understanding Task." International Journal of Digital Crime and Forensics 12, no. 4 (October 2020): 32–43. http://dx.doi.org/10.4018/ijdcf.2020100103.

Full text

Abstract:

Intent determination (ID) and slot filling (SF) are two critical steps in the spoken language understanding (SLU) task. Conventionally, most previous work has been done for each subtask respectively. To exploit the dependencies between intent label and slot sequence, as well as deal with both tasks simultaneously, this paper proposes a joint model (ABLCJ), which is trained by a united loss function. In order to utilize both past and future input features efficiently, a joint model based Bi-LSTM with contextual information is employed to learn the representation of each step, which are shared by two tasks and the model. This paper also uses sentence-level tag information learned from a CRF layer to predict the tag of each slot. Meanwhile, a submodule-based attention is employed to capture global features of a sentence for intent classification. The experimental results demonstrate that ABLCJ achieves competitive performance in the Shared Task 4 of NLPCC 2018.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Slot Filling'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles