A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding
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]
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]
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
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]
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]
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]
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
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
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]
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]
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]
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]
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]
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
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