Smart assistants are tasked to answer various questions regarding world knowledge. These questions range from retrieval of simple facts to retrieval of complex, multi-hops question followed by various operators (i.e., filter, argmax). Semantic parsing has emerged as the state-of-the-art for answering these kinds of questions by forming queries to extract information from knowledge bases (KBs). Specially, neural semantic parsers (NSPs) effectively translate natural questions to logical forms, which execute on KB and give desirable answers. Yet, NSPs suffer from non-executable logical forms for some instances in the generated logical forms might be missing due to the incompleteness of KBs. Intuitively, knowing the KB structure informs NSP with changes of the global logical forms structures with respect to changes in KB instances. In this work, we propose a novel knowledge-informed decoder variant of NSP. We consider the conversational question answering settings, where a natural language query, its context and its final answers are available at training. Experimental results show that our method outperformed strong baselines by 1.8 F1 points overall across 10 types of questions of the CSQA dataset. Especially for the “Logical Reasoning” category, our model improves by 7 F1 points. Furthermore, our results are achieved with 90.3% fewer parameters, allowing faster training for large-scale datasets.
Raghuveer Thirukovalluru, Mukund Sridhar, Dung Thai, Shruti Chanumolu, Nicholas Monath, Sankaranarayanan Ananthakrishnan, and Andrew McCallum. 2021.Knowledge Informed Semantic Parsing for Conversational Question Answering. InProceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 231–240, Online. Association for Computational Linguistics.
@inproceedings{thirukovalluru-etal-2021-knowledge, title = "Knowledge Informed Semantic Parsing for Conversational Question Answering", author = "Thirukovalluru, Raghuveer and Sridhar, Mukund and Thai, Dung and Chanumolu, Shruti and Monath, Nicholas and Ananthakrishnan, Sankaranarayanan and McCallum, Andrew", editor = "Rogers, Anna and Calixto, Iacer and Vuli{\'c}, Ivan and Saphra, Naomi and Kassner, Nora and Camburu, Oana-Maria and Bansal, Trapit and Shwartz, Vered", booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.repl4nlp-1.24/", doi = "10.18653/v1/2021.repl4nlp-1.24", pages = "231--240", abstract = "Smart assistants are tasked to answer various questions regarding world knowledge. These questions range from retrieval of simple facts to retrieval of complex, multi-hops question followed by various operators (i.e., filter, argmax). Semantic parsing has emerged as the state-of-the-art for answering these kinds of questions by forming queries to extract information from knowledge bases (KBs). Specially, neural semantic parsers (NSPs) effectively translate natural questions to logical forms, which execute on KB and give desirable answers. Yet, NSPs suffer from non-executable logical forms for some instances in the generated logical forms might be missing due to the incompleteness of KBs. Intuitively, knowing the KB structure informs NSP with changes of the global logical forms structures with respect to changes in KB instances. In this work, we propose a novel knowledge-informed decoder variant of NSP. We consider the conversational question answering settings, where a natural language query, its context and its final answers are available at training. Experimental results show that our method outperformed strong baselines by 1.8 F1 points overall across 10 types of questions of the CSQA dataset. Especially for the {\textquotedblleft}Logical Reasoning{\textquotedblright} category, our model improves by 7 F1 points. Furthermore, our results are achieved with 90.3{\%} fewer parameters, allowing faster training for large-scale datasets."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="thirukovalluru-etal-2021-knowledge"> <titleInfo> <title>Knowledge Informed Semantic Parsing for Conversational Question Answering</title> </titleInfo> <name type="personal"> <namePart type="given">Raghuveer</namePart> <namePart type="family">Thirukovalluru</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Mukund</namePart> <namePart type="family">Sridhar</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Dung</namePart> <namePart type="family">Thai</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Shruti</namePart> <namePart type="family">Chanumolu</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Nicholas</namePart> <namePart type="family">Monath</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Sankaranarayanan</namePart> <namePart type="family">Ananthakrishnan</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Andrew</namePart> <namePart type="family">McCallum</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2021-08</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title> </titleInfo> <name type="personal"> <namePart type="given">Anna</namePart> <namePart type="family">Rogers</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Iacer</namePart> <namePart type="family">Calixto</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Ivan</namePart> <namePart type="family">Vulić</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Naomi</namePart> <namePart type="family">Saphra</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Nora</namePart> <namePart type="family">Kassner</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Oana-Maria</namePart> <namePart type="family">Camburu</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Trapit</namePart> <namePart type="family">Bansal</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Vered</namePart> <namePart type="family">Shwartz</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Online</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Smart assistants are tasked to answer various questions regarding world knowledge. These questions range from retrieval of simple facts to retrieval of complex, multi-hops question followed by various operators (i.e., filter, argmax). Semantic parsing has emerged as the state-of-the-art for answering these kinds of questions by forming queries to extract information from knowledge bases (KBs). Specially, neural semantic parsers (NSPs) effectively translate natural questions to logical forms, which execute on KB and give desirable answers. Yet, NSPs suffer from non-executable logical forms for some instances in the generated logical forms might be missing due to the incompleteness of KBs. Intuitively, knowing the KB structure informs NSP with changes of the global logical forms structures with respect to changes in KB instances. In this work, we propose a novel knowledge-informed decoder variant of NSP. We consider the conversational question answering settings, where a natural language query, its context and its final answers are available at training. Experimental results show that our method outperformed strong baselines by 1.8 F1 points overall across 10 types of questions of the CSQA dataset. Especially for the “Logical Reasoning” category, our model improves by 7 F1 points. Furthermore, our results are achieved with 90.3% fewer parameters, allowing faster training for large-scale datasets.</abstract> <identifier type="citekey">thirukovalluru-etal-2021-knowledge</identifier> <identifier type="doi">10.18653/v1/2021.repl4nlp-1.24</identifier> <location> <url>https://aclanthology.org/2021.repl4nlp-1.24/</url> </location> <part> <date>2021-08</date> <extent unit="page"> <start>231</start> <end>240</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Knowledge Informed Semantic Parsing for Conversational Question Answering%A Thirukovalluru, Raghuveer%A Sridhar, Mukund%A Thai, Dung%A Chanumolu, Shruti%A Monath, Nicholas%A Ananthakrishnan, Sankaranarayanan%A McCallum, Andrew%Y Rogers, Anna%Y Calixto, Iacer%Y Vulić, Ivan%Y Saphra, Naomi%Y Kassner, Nora%Y Camburu, Oana-Maria%Y Bansal, Trapit%Y Shwartz, Vered%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)%D 2021%8 August%I Association for Computational Linguistics%C Online%F thirukovalluru-etal-2021-knowledge%X Smart assistants are tasked to answer various questions regarding world knowledge. These questions range from retrieval of simple facts to retrieval of complex, multi-hops question followed by various operators (i.e., filter, argmax). Semantic parsing has emerged as the state-of-the-art for answering these kinds of questions by forming queries to extract information from knowledge bases (KBs). Specially, neural semantic parsers (NSPs) effectively translate natural questions to logical forms, which execute on KB and give desirable answers. Yet, NSPs suffer from non-executable logical forms for some instances in the generated logical forms might be missing due to the incompleteness of KBs. Intuitively, knowing the KB structure informs NSP with changes of the global logical forms structures with respect to changes in KB instances. In this work, we propose a novel knowledge-informed decoder variant of NSP. We consider the conversational question answering settings, where a natural language query, its context and its final answers are available at training. Experimental results show that our method outperformed strong baselines by 1.8 F1 points overall across 10 types of questions of the CSQA dataset. Especially for the “Logical Reasoning” category, our model improves by 7 F1 points. Furthermore, our results are achieved with 90.3% fewer parameters, allowing faster training for large-scale datasets.%R 10.18653/v1/2021.repl4nlp-1.24%U https://aclanthology.org/2021.repl4nlp-1.24/%U https://doi.org/10.18653/v1/2021.repl4nlp-1.24%P 231-240
Raghuveer Thirukovalluru, Mukund Sridhar, Dung Thai, Shruti Chanumolu, Nicholas Monath, Sankaranarayanan Ananthakrishnan, and Andrew McCallum. 2021.Knowledge Informed Semantic Parsing for Conversational Question Answering. InProceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 231–240, Online. Association for Computational Linguistics.