End-to-end Task-Oriented Dialogue System with Distantly Supervised Knowledge Base Retriever

来源 :第十七届全国计算语言学学术会议暨第六届基于自然标注大数据的自然语言处理国际学术研讨会(CCL 2018) | 被引量 : 0次 | 上传用户：svennis

【摘要】

：

Task-oriented dialog systems usually face the challenge of querying knowledge base.However,it usually cannot be explicitly modeled due to the lack of annotation.In this paper,we introduce an explicit

【作者】

：

Libo Qin Yijia Liu Wanxiang Che Haoyang Wen Ting Liu

【机构】

：

Research Center for Social Computing and Information Retrieval Harbin Institute of Technology,China

【出处】

：

第十七届全国计算语言学学术会议暨第六届基于自然标注大数据的自然语言处理国际学术研讨会(CCL 2018)

【发表日期】

：

2018年9期

【关键词】

：

task-oriented dialog systems sequence-to-sequence Knowledge Base

下载到本地 , 更方便阅读

下载此文赞助VIP

声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架

论文部分内容阅读

　　Task-oriented dialog systems usually face the challenge of querying knowledge base.However,it usually cannot be explicitly modeled due to the lack of annotation.In this paper,we introduce an explicit KB retrieval component(KB retriever)into the seq2seq dialogue system.We first use the KB retriever to get the most relevant entry according to the dialogue history and KB,and then apply the copying mechanism to retrieve entities from the retrieved KB in decoding time.Moreover,the KB retriever is trained with distant supervision,which does not need any annotation efforts.Experiments on Stanford Multi-turn Task-oriented Dialogue Dataset shows that our framework significantly outperforms other sequence-to-sequence based baseline models on both automatic and human evaluation.

其他文献

Question-answering Aspect Classification with Hierarchical Attention Network

In e-commerce websites,user-generated question-answering text pairs generally contain rich aspect information of products.In this paper,we address a new task,namely Question-answering(QA)aspect classi

会议

Aspect ClassificationQuestion AnsweringHierarchical Attention

Improving Low-Resource Neural Machine Translation with Weight Sharing

Neural machine translation(NMT)has achieved great suc-cess under a great deal of bilingual corpora in the past few years.Howev-er,it is much less effective for low-resource language.In order to allevi

会议

Low-resourceNeural machine translationWeight sharing

Identifying Word Translations in Scientific Literature based on Labeled Bilingual Topic Model and Co

Aiming at the increasingly rich multi language information resources and multi-label data in scientific literature,in order to mining the relevance and correlation in languages,this paper proposed the

会议

Topic ModelLabelCo-occurrence FeaturesWord Translations

An End-to-End Entity and Relation Extraction Network with Multi-head Attention

Relation extraction is an important semantic processing task in natu-ral language processing.The state-of-the-art systems usually rely on elaborately designed features,which are usually time-consuming

会议

Relation ExtractionEnd-to-End Joint ExtractionNamed Entity Recognition

Learning to Detect Verbose Expressions in Spoken Texts

The analysis and understanding of spoken texts is an impor-tant task in artificial intelligence and natural language processing.How-ever,there are many verbose expressions(such as mantras,nonsense,mod

会议

Trigger Words Detection by Integrating Attention Mechanism into Bi-LSTM Neural Network | A Case stud

A Bi-LSTM based encode/decode mechanism for named entity recognition was studied in this research.In the proposed mechanism,Bi-LSTM was used for encoding,an Attention method was used in the intermedia

会议

natural language processingLSTMencoder/decoder modeltrigger words

Attention-Based Convolutional Neural Networks for Chinese Relation Extraction

Relation extraction is an important part of many information extrac-tion systems that mines structured facts from texts.Recently,deep learning has achieved good results in relation extraction.Attentio

会议

Relation ExtractionConvolutional Neural NetworksAttention Mechanism

A Hierarchical Hybrid Neural Network Architecture for Chinese Text Summarization

Using sequence-to-sequence models for abstractive text sum-marization is generally plagued by three problems: inability to deal with out-of-vocabulary words,repetition in summaries and time-consuming

会议

Abstractive Text SummarizationHierarchical Attention MechanismPointer Mechanis

TSABCNN:Two-Stage Attention-Based Convolutional Neural Network for Frame Identification

As an essential sub-task of frame-semantic parsing,Frame Identifica-tion(FI)is a fundamentally important research topic in shallow semantic pars-ing.However,most existing work is based on sophisticate

会议

Frame IdentificationFrameNetConvolutional Neural Network

Revisiting Correlations between Intrinsic and Extrinsic Evaluations of Word Embeddings

The evaluation of word embeddings has received a considerable amount of attention in recent years,but there have been some debates about whether intrinsic measures can predict the performance of downs

会议

word embeddingintrinsic evaluationextrinsic evaluation

End-to-end Task-Oriented Dialogue System with Distantly Supervised Knowledge Base Retriever

其他学术论文