Coreference resolution such as for anaphora has been an essential challenge that is commonly found in conversational machine reading comprehension (CMRC). This task aims to determine the referential entity to which a pronoun refers on the basis of contextual information. Existing approaches based on pre-trained language models (PLMs) mainly rely on an end-to-end method, which still has limitations in clarifying referential dependency. In this study, a novel graph-based approach is proposed to integrate the coreference of given text into graph structures (called coreference graphs), which can pinpoint a pronoun’s referential entity. We propose two graph-combined methods, evidence-enhanced and the fusion model, for CMRC to integrate coreference graphs from different levels of the PLM architecture. Evidence-enhanced refers to textual level methods that include an evidence generator (for generating new text to elaborate a pronoun) and enhanced question (for rewriting a pronoun in a question) as PLM input. The fusion model is a structural level method that combines the PLM with a graph neural network. We evaluated these approaches on a CoQA pronoun-containing dataset and the whole CoQA dataset. The result showed that our methods can outperform baseline PLM methods with BERT and RoBERTa.
@inproceedings{wang-komatani-2022-graph, title = "Graph-combined Coreference Resolution Methods on Conversational Machine Reading Comprehension with Pre-trained Language Model", author = "Wang, Zhaodong and Komatani, Kazunori", editor = "Feng, Song and Wan, Hui and Yuan, Caixia and Yu, Han", booktitle = "Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering", month = may, year = "2022", address = "Dublin, Ireland", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.dialdoc-1.8/", doi = "10.18653/v1/2022.dialdoc-1.8", pages = "72--82", abstract = "Coreference resolution such as for anaphora has been an essential challenge that is commonly found in conversational machine reading comprehension (CMRC). This task aims to determine the referential entity to which a pronoun refers on the basis of contextual information. Existing approaches based on pre-trained language models (PLMs) mainly rely on an end-to-end method, which still has limitations in clarifying referential dependency. In this study, a novel graph-based approach is proposed to integrate the coreference of given text into graph structures (called coreference graphs), which can pinpoint a pronoun`s referential entity. We propose two graph-combined methods, evidence-enhanced and the fusion model, for CMRC to integrate coreference graphs from different levels of the PLM architecture. Evidence-enhanced refers to textual level methods that include an evidence generator (for generating new text to elaborate a pronoun) and enhanced question (for rewriting a pronoun in a question) as PLM input. The fusion model is a structural level method that combines the PLM with a graph neural network. We evaluated these approaches on a CoQA pronoun-containing dataset and the whole CoQA dataset. The result showed that our methods can outperform baseline PLM methods with BERT and RoBERTa."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="wang-komatani-2022-graph"> <titleInfo> <title>Graph-combined Coreference Resolution Methods on Conversational Machine Reading Comprehension with Pre-trained Language Model</title> </titleInfo> <name type="personal"> <namePart type="given">Zhaodong</namePart> <namePart type="family">Wang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Kazunori</namePart> <namePart type="family">Komatani</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2022-05</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering</title> </titleInfo> <name type="personal"> <namePart type="given">Song</namePart> <namePart type="family">Feng</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Hui</namePart> <namePart type="family">Wan</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Caixia</namePart> <namePart type="family">Yuan</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Han</namePart> <namePart type="family">Yu</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Dublin, Ireland</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Coreference resolution such as for anaphora has been an essential challenge that is commonly found in conversational machine reading comprehension (CMRC). This task aims to determine the referential entity to which a pronoun refers on the basis of contextual information. Existing approaches based on pre-trained language models (PLMs) mainly rely on an end-to-end method, which still has limitations in clarifying referential dependency. In this study, a novel graph-based approach is proposed to integrate the coreference of given text into graph structures (called coreference graphs), which can pinpoint a pronoun‘s referential entity. We propose two graph-combined methods, evidence-enhanced and the fusion model, for CMRC to integrate coreference graphs from different levels of the PLM architecture. Evidence-enhanced refers to textual level methods that include an evidence generator (for generating new text to elaborate a pronoun) and enhanced question (for rewriting a pronoun in a question) as PLM input. The fusion model is a structural level method that combines the PLM with a graph neural network. We evaluated these approaches on a CoQA pronoun-containing dataset and the whole CoQA dataset. The result showed that our methods can outperform baseline PLM methods with BERT and RoBERTa.</abstract> <identifier type="citekey">wang-komatani-2022-graph</identifier> <identifier type="doi">10.18653/v1/2022.dialdoc-1.8</identifier> <location> <url>https://aclanthology.org/2022.dialdoc-1.8/</url> </location> <part> <date>2022-05</date> <extent unit="page"> <start>72</start> <end>82</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Graph-combined Coreference Resolution Methods on Conversational Machine Reading Comprehension with Pre-trained Language Model%A Wang, Zhaodong%A Komatani, Kazunori%Y Feng, Song%Y Wan, Hui%Y Yuan, Caixia%Y Yu, Han%S Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering%D 2022%8 May%I Association for Computational Linguistics%C Dublin, Ireland%F wang-komatani-2022-graph%X Coreference resolution such as for anaphora has been an essential challenge that is commonly found in conversational machine reading comprehension (CMRC). This task aims to determine the referential entity to which a pronoun refers on the basis of contextual information. Existing approaches based on pre-trained language models (PLMs) mainly rely on an end-to-end method, which still has limitations in clarifying referential dependency. In this study, a novel graph-based approach is proposed to integrate the coreference of given text into graph structures (called coreference graphs), which can pinpoint a pronoun‘s referential entity. We propose two graph-combined methods, evidence-enhanced and the fusion model, for CMRC to integrate coreference graphs from different levels of the PLM architecture. Evidence-enhanced refers to textual level methods that include an evidence generator (for generating new text to elaborate a pronoun) and enhanced question (for rewriting a pronoun in a question) as PLM input. The fusion model is a structural level method that combines the PLM with a graph neural network. We evaluated these approaches on a CoQA pronoun-containing dataset and the whole CoQA dataset. The result showed that our methods can outperform baseline PLM methods with BERT and RoBERTa.%R 10.18653/v1/2022.dialdoc-1.8%U https://aclanthology.org/2022.dialdoc-1.8/%U https://doi.org/10.18653/v1/2022.dialdoc-1.8%P 72-82