A New Focus Strategy for Efficient Dialog Management

来源 :第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD | 被引量 : 0次 | 上传用户:hlxcun871
下载到本地 , 更方便阅读
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
  The dialog manager is the most important component for a dialog system,in which the dialog state tracking is crucial to a real-world system.We claim that the intractability of dialog states comes from two aspects: the large slot size in users goal and the large candidate value size for each slot.For the first time,we propose a new focus strategy to deal with the former problem,by reducing the full slots of the users goal into a small subset focus slot.We also implement a partition-based method to deal with the latter problem.Then we combine both strategies to take advantage of their complement property.In our experiment of a real-world application in an image purchase domain,our proposed focus strategy is far faster than both the partition method and the na(i)ve algorithm with comparable quality.
其他文献
Most researches to SRL focus on English.It is still a challenge to improve the SRL performance of other language.In this paper,we introduce a two-pass approach to do Chinese SRL with a Recurrent Neura
In this paper,we propose a neural graph-based dependency parsing model which utilizes hierarchical LSTM networks on character level and word level to learn word representations,allowing our model to a
In order to explore a practical way of improving machine translation(MT)quality,the error types and distribution of MT results have to be analyzed first.This paper analyzed English-Chinese MT errors f
For the difficulty of marking Vietnamese dependency tree,this paper proposed the method which combined MST algorithm and improved Nivre algorithm to build Vietnamese dependency treebank.The method too
Traditional Mongolian Unicode Encoding has serious problems as several pairs of vowels with the same glyphs but different pronunciations are coded differently.We expose the severity of the problem by
Unlike previous Mongolian morphological segmentation methods based on large labeled training data or complicated rules concluded by linguists,we explore a novel semi-supervised method for a practical
As a fundamental step in biomedical information extraction tasks,biomedical named entity recognition remains challenging.In recent years,the neural network has been applied on the entity recognition t
Previous researches on event relation classification primarily rely on lexical and syntactic features.In this paper,we use a Shallow Convolutional Neural Network(SCNN)to extract event-level and cross-
Sentiment analysis on social media represented by Weibo is one of the hotspot research problems in NLP.A comprehensive and systematic fine-grained annotated corpus plays a significance role.In this pa
A great number of clinicians in mainland China are under increasing pressure to publish their research results on international journals,and they urgently need support for writing research articles in