Filters








5,722 Hits in 5.7 sec

End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding

Yun-Nung Chen, Dilek Hakkani-Tür, Gokhan Tur, Jianfeng Gao, Li Deng
2016 Interspeech 2016  
Spoken language understanding (SLU) is a core component of a spoken dialogue system.  ...  This paper addresses the above issues by proposing an architecture using end-to-end memory networks to model knowledge carryover in multi-turn conversations, where utterances encoded with intents and slots  ...  are domain classification, intent determination, and slot filling [1] .  ... 
doi:10.21437/interspeech.2016-312 dblp:conf/interspeech/ChenHTGD16 fatcat:4rzay27mrnhnnoufzxremlzjse

Incorporating Loose-Structured Knowledge into Conversation Modeling via Recall-Gate LSTM [article]

Zhen Xu, Bingquan Liu, Baoxun Wang, Chengjie Sun, Xiaolong Wang
2017 arXiv   pre-print
Through a specially designed Recall gate, domain knowledge can be transformed into the extra global memory of Long Short-Term Memory (LSTM), so as to enhance LSTM by cooperating with its local memory to  ...  In this paper, a deep neural network is proposed to incorporate background knowledge for conversation modeling.  ...  To make domain knowledge perform as a global memory for greater effect, we design a special model component for LSTM. Figure 4 shows the detail of the LSTM cell with Recall gate (r-LSTM cell).  ... 
arXiv:1605.05110v2 fatcat:z4pn5dgdzzfxrcttnhmkf3bnuy

Bootstrapping NLU Models with Multi-task Learning [article]

Shubham Kapoor, Caglar Tirkaz
2019 arXiv   pre-print
We address these issues by introducing a character-level unified neural architecture for joint modeling of the domain, intent, and slot classification.  ...  A common approach that is adapted in digital assistants when responding to a user query is to process the input in a pipeline manner where the first task is to predict the domain, followed by the inference  ...  We implement this gating mechanism using a feedforward layer as defined in Eq. 8, which transforms the input vector x i of the slot classifier to determine their corresponding gating vectors.  ... 
arXiv:1911.06673v1 fatcat:4mbprnql5bexdhwtovrmqe3ynq

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, Pascale Fung
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Our model is composed of an utterance encoder, a slot gate, and a state generator, which are shared across domains.  ...  In this paper, we propose a TRAnsferable Dialogue statE generator (TRADE) that generates dialogue states from utterances using a copy mechanism, facilitating knowledge transfer when predicting (domain,  ...  The hard-gate copy mechanism usually needs additional supervi-sion on the gating function.  ... 
doi:10.18653/v1/p19-1078 dblp:conf/acl/WuMHXSF19 fatcat:oinpen53frbqhnuduo3njbzqru

XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking [article]

Han Zhou, Ignacio Iacobacci, Pasquale Minervini
2022 arXiv   pre-print
We show its competitive transferability by zero-shot domain-adaptation experiments on MultiWOZ 2.1 with an average JGA of 31.6% for five domains.  ...  In this paper, we propose a multi-domain and multi-lingual dialogue state tracker in a neural reading comprehension approach.  ...  Shared Classification Gate Our model contains a shared classification gate θ gate for every domain-slot question.  ... 
arXiv:2204.05895v1 fatcat:g6v6c5cc7bbwzb4hkx2btlxn5y

Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks [article]

Yun-Nung Chen, Dilek Hakkani-Tur, Gokhan Tur, Asli Celikyilmaz, Jianfeng Gao, Li Deng
2016 arXiv   pre-print
Traditionally, the NLU module tags semantic slots for utterances considering their flat structures, as the underlying RNN structure is a linear chain.  ...  This paper introduces a novel model, knowledge-guided structural attention networks (K-SAN), a generalization of RNN to additionally incorporate non-flat network topologies guided by prior knowledge.  ...  RNN-GRU can incorporate the encoded knowledge in the similar way, where M o can be added into gating mechanisms for modeling contextual knowledge similarly.  ... 
arXiv:1609.03286v1 fatcat:ovmddipcgba7xiaujxymzfk6fm

Supervised Domain Enablement Attention for Personalized Domain Classification [article]

Joo-Kyung Kim, Young-Bum Kim
2018 arXiv   pre-print
By evaluating on the actual utterances from a large-scale IPDA, we show that our approach significantly improves domain classification performance.  ...  mechanism has been shown to improve the overall domain classification performance.  ...  For an input utterance, Kim et al. (2018b) use attention mechanism so that a weighted sum of the enabled domain vectors are used as an input signal as well as the utterance vector.  ... 
arXiv:1812.07546v1 fatcat:enxqgwm73ncujkzok4jotpuk3a

Supervised Domain Enablement Attention for Personalized Domain Classification

Joo-Kyung Kim, Young-Bum Kim
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
By evaluating on the actual utterances from a large-scale IPDA, we show that our approach significantly improves domain classification performance.  ...  mechanism has been shown to improve the overall domain classification performance.  ...  For an input utterance, Kim et al. (2018b) use attention mechanism so that a weighted sum of the enabled domain vectors are used as an input signal as well as the utterance vector.  ... 
doi:10.18653/v1/d18-1106 dblp:conf/emnlp/KimK18 fatcat:xeaxoagv7zg2lj2cheyjjrqvia

Dialogue State Tracking with Incremental Reasoning

Lizi Liao, Le Hong Long, Yunshan Ma, Wenqiang Lei, Tat-Seng Chua
2021 Transactions of the Association for Computational Linguistics  
Empirical results demonstrate that our method outperforms the state-of-the-art methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human--human dialogue dataset across multiple domains  ...  Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined slot-value pairs, or generating values for different slots given the dialogue history.  ...  The sequence classification task decides which domain the turn is talking about and whether a specific (domain, slot) pair takes the gate value like yes, no, doncare, none, or generate from token classification  ... 
doi:10.1162/tacl_a_00384 fatcat:6quh2aapgnfvtnh3efhopddpde

Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey [article]

Samuel Louvan, Bernardo Magnini
2020 arXiv   pre-print
In recent years, fostered by deep learning technologies and by the high demand for conversational AI, various approaches have been proposed that address the capacity to elicit and understand user's needs  ...  We focus on two core tasks, slot filling (SF) and intent classification (IC), and survey how neural-based models have rapidly evolved to address natural language understanding in dialogue systems.  ...  First, in addition to the slot-gated mechanism, they add an intent-gated mechanism as well.  ... 
arXiv:2011.00564v1 fatcat:pjpnqp3rmjhfdmrtk3ybwd5tfq

Learning to Memorize in Neural Task-Oriented Dialogue Systems [article]

Chien-Sheng Wu
2019 arXiv   pre-print
We first propose a transferable dialogue state generator (TRADE) that leverages its copy mechanism to get rid of dialogue ontology and share knowledge between domains.  ...  We also evaluate unseen domain dialogue state tracking and show that TRADE enables zero-shot dialogue state tracking and can adapt to new few-shot domains without forgetting the previous domains.  ...  It includes an utterance encoder, a slot gate, and a state generator.  ... 
arXiv:1905.07687v1 fatcat:upvqqczyajdtnf45bcszxs6nai

Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking [article]

Su Zhu, Jieyu Li, Lu Chen, Kai Yu
2020 arXiv   pre-print
For multi-domain DST, the data sparsity problem is a major obstacle due to increased numbers of state candidates and dialogue lengths.  ...  To consider relations among different domain-slots, the schema graph involving prior knowledge is exploited.  ...  Acknowledgments We thank the anonymous reviewers for their thoughtful comments.  ... 
arXiv:2004.03386v4 fatcat:l6enipvnfjdm7po3lbkptav4oy

TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking [article]

Michael Heck, Carel van Niekerk, Nurul Lubis, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, Milica Gašić
2020 arXiv   pre-print
A slot is filled by one of three copy mechanisms: (1) Span prediction may extract values directly from the user input; (2) a value may be copied from a system inform memory that keeps track of the system's  ...  inform operations; (3) a value may be copied over from a different slot that is already contained in the dialog state to resolve coreferences within and across domains.  ...  ) i.e., each slot gate is realized by a trainable linear layer classification head for BERT.  ... 
arXiv:2005.02877v4 fatcat:orsm7vd4j5hpdkcl5sucvu6ms4

LSTM-RASA Based Agri Farm Assistant for Farmers [article]

Narayana Darapaneni, Selvakumar Raj, Raghul V, Venkatesh Sivaraman, Sunil Mohan, Anwesh Reddy Paduri
2022 arXiv   pre-print
This project aims to implement a closed domain ChatBot for the field of Agriculture Farmers Assistant. Farmers can have conversation with the Chatbot and get the expert advice in their field.  ...  The farmers are still largely dependent on their peers knowledge in solving the problems they face in their field.  ...  Knowledge Base We analyzed the data and prepared the knowledge base with the help of Domain 4.  ... 
arXiv:2204.09717v1 fatcat:4jivdhxb4rb3nnic4rjtnyujaa

A Multiple Utterances based Neural Network Model for Joint Intent Detection and Slot Filling

Lingfeng Pan, Yi Zhang, Feiliang Ren, Yining Hou, Yan Li, Xiaobo Liang, Yongkang Liu
2018 China Conference on Knowledge Graph and Semantic Computing  
We also combine the intent information to the slot filling process with a gating mechanism. Using this proposed model, we participated in the task2 of CCKS2018.  ...  In our method, we use an utterance2utterance attention mechanism to combine the information of multiple continuous utterances.  ...  Then we combine the intent information to the slot filling process with a gating mechanism.  ... 
dblp:conf/ccks/PanZRHLLL18 fatcat:ig6wbe3n3naefmteoh3lst3vg4
« Previous Showing results 1 — 15 out of 5,722 results