Natural Language Engineering最新文献

筛选

英文中文

A Semantic Parsing Pipeline for Context-Dependent Question Answering over Temporally Structured Data. 在时态结构数据上进行上下文相关问题解答的语义解析管道。

IF 2.5 3区计算机科学

Natural Language Engineering Pub Date : 2023-05-01 Epub Date: 2021-10-29 DOI: 10.1017/s1351324921000292

Charles Chen, Razvan Bunescu, Cindy Marling

{"title":"A Semantic Parsing Pipeline for Context-Dependent Question Answering over Temporally Structured Data.","authors":"Charles Chen, Razvan Bunescu, Cindy Marling","doi":"10.1017/s1351324921000292","DOIUrl":"10.1017/s1351324921000292","url":null,"abstract":"<p><p>We propose a new setting for question answering in which users can query the system using both natural language and direct interactions within a graphical user interface that displays multiple time series associated with an entity of interest. The user interacts with the interface in order to understand the entity's state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We describe a pipeline implementation where spoken questions are first transcribed into text which is then semantically parsed into logical forms that can be used to automatically extract the answer from the underlying database. The speech recognition module is implemented by adapting a pre-trained LSTM-based architecture to the user's speech, whereas for the semantic parsing component we introduce an LSTM-based encoder-decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When evaluated separately, with and without data augmentation, both models are shown to substantially outperform several strong baselines. Furthermore, the full pipeline evaluation shows only a small degradation in semantic parsing accuracy, demonstrating that the semantic parser is robust to mistakes in the speech recognition output. The new question answering paradigm proposed in this paper has the potential to improve the presentation and navigation of the large amounts of sensor data and life events that are generated in many areas of medicine.</p>","PeriodicalId":49143,"journal":{"name":"Natural Language Engineering","volume":"29 2","pages":"769-793"},"PeriodicalIF":2.5,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10348695/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10184074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0