Conversational machine comprehension: a literature review

Conversational machine comprehension: a literature review. Gupta, S., Rawat, B. P. S., & Yu, H. arXiv preprint arXiv:2006.00671, December, 2020.
doi abstract bibtex

Conversational Machine Comprehension (CMC), a research track in conversational AI, expects the machine to understand an open-domain natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. While most of the research in Machine Reading Comprehension (MRC) revolves around single-turn question answering (QA), multi-turn CMC has recently gained prominence, thanks to the advancement in natural language understanding via neural language models such as BERT and the introduction of large-scale conversational datasets such as CoQA and QuAC. The rise in interest has, however, led to a flurry of concurrent publications, each with a different yet structurally similar modeling approach and an inconsistent view of the surrounding literature. With the volume of model submissions to conversational datasets increasing every year, there exists a need to consolidate the scattered knowledge in this domain to streamline future research. This literature review attempts at providing a holistic overview of CMC with an emphasis on the common trends across recently published models, specifically in their approach to tackling conversational history. The review synthesizes a generic framework for CMC models while highlighting the differences in recent approaches and intends to serve as a compendium of CMC for future researchers.

@article{gupta_conversational_2020,
	title = {Conversational machine comprehension: a literature review},
	shorttitle = {Conversational machine comprehension},
	doi = {10.18653/v1/2020.coling-main.247},
	abstract = {Conversational Machine Comprehension (CMC), a research track in conversational AI, expects
the machine to understand an open-domain natural language text and thereafter engage in a
multi-turn conversation to answer questions related to the text. While most of the research in
Machine Reading Comprehension (MRC) revolves around single-turn question answering (QA),
multi-turn CMC has recently gained prominence, thanks to the advancement in natural language
understanding via neural language models such as BERT and the introduction of large-scale conversational datasets such as CoQA and QuAC. The rise in interest has, however, led to a flurry of
concurrent publications, each with a different yet structurally similar modeling approach and an
inconsistent view of the surrounding literature. With the volume of model submissions to conversational datasets increasing every year, there exists a need to consolidate the scattered knowledge
in this domain to streamline future research. This literature review attempts at providing a holistic overview of CMC with an emphasis on the common trends across recently published models,
specifically in their approach to tackling conversational history. The review synthesizes a generic
framework for CMC models while highlighting the differences in recent approaches and intends
to serve as a compendium of CMC for future researchers.},
	journal = {arXiv preprint arXiv:2006.00671},
	author = {Gupta, Somil and Rawat, Bhanu Pratap Singh and Yu, Hong},
	month = dec,
	year = {2020},
	pages = {2739--2753},
}

Downloads: 0

{"_id":"wA4uJsczkNT7gkS7i","bibbaseid":"gupta-rawat-yu-conversationalmachinecomprehensionaliteraturereview-2020","author_short":["Gupta, S.","Rawat, B. P. S.","Yu, H."],"bibdata":{"bibtype":"article","type":"article","title":"Conversational machine comprehension: a literature review","shorttitle":"Conversational machine comprehension","doi":"10.18653/v1/2020.coling-main.247","abstract":"Conversational Machine Comprehension (CMC), a research track in conversational AI, expects the machine to understand an open-domain natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. While most of the research in Machine Reading Comprehension (MRC) revolves around single-turn question answering (QA), multi-turn CMC has recently gained prominence, thanks to the advancement in natural language understanding via neural language models such as BERT and the introduction of large-scale conversational datasets such as CoQA and QuAC. The rise in interest has, however, led to a flurry of concurrent publications, each with a different yet structurally similar modeling approach and an inconsistent view of the surrounding literature. With the volume of model submissions to conversational datasets increasing every year, there exists a need to consolidate the scattered knowledge in this domain to streamline future research. This literature review attempts at providing a holistic overview of CMC with an emphasis on the common trends across recently published models, specifically in their approach to tackling conversational history. The review synthesizes a generic framework for CMC models while highlighting the differences in recent approaches and intends to serve as a compendium of CMC for future researchers.","journal":"arXiv preprint arXiv:2006.00671","author":[{"propositions":[],"lastnames":["Gupta"],"firstnames":["Somil"],"suffixes":[]},{"propositions":[],"lastnames":["Rawat"],"firstnames":["Bhanu","Pratap","Singh"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"month":"December","year":"2020","pages":"2739–2753","bibtex":"@article{gupta_conversational_2020,\n\ttitle = {Conversational machine comprehension: a literature review},\n\tshorttitle = {Conversational machine comprehension},\n\tdoi = {10.18653/v1/2020.coling-main.247},\n\tabstract = {Conversational Machine Comprehension (CMC), a research track in conversational AI, expects\nthe machine to understand an open-domain natural language text and thereafter engage in a\nmulti-turn conversation to answer questions related to the text. While most of the research in\nMachine Reading Comprehension (MRC) revolves around single-turn question answering (QA),\nmulti-turn CMC has recently gained prominence, thanks to the advancement in natural language\nunderstanding via neural language models such as BERT and the introduction of large-scale conversational datasets such as CoQA and QuAC. The rise in interest has, however, led to a flurry of\nconcurrent publications, each with a different yet structurally similar modeling approach and an\ninconsistent view of the surrounding literature. With the volume of model submissions to conversational datasets increasing every year, there exists a need to consolidate the scattered knowledge\nin this domain to streamline future research. This literature review attempts at providing a holistic overview of CMC with an emphasis on the common trends across recently published models,\nspecifically in their approach to tackling conversational history. The review synthesizes a generic\nframework for CMC models while highlighting the differences in recent approaches and intends\nto serve as a compendium of CMC for future researchers.},\n\tjournal = {arXiv preprint arXiv:2006.00671},\n\tauthor = {Gupta, Somil and Rawat, Bhanu Pratap Singh and Yu, Hong},\n\tmonth = dec,\n\tyear = {2020},\n\tpages = {2739--2753},\n}\n\n","author_short":["Gupta, S.","Rawat, B. P. S.","Yu, H."],"key":"gupta_conversational_2020","id":"gupta_conversational_2020","bibbaseid":"gupta-rawat-yu-conversationalmachinecomprehensionaliteraturereview-2020","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"http://fenway.cs.uml.edu/papers/pubs-all.bib","dataSources":["TqaA9miSB65nRfS5H"],"keywords":[],"search_terms":["conversational","machine","comprehension","literature","review","gupta","rawat","yu"],"title":"Conversational machine comprehension: a literature review","year":2020,"downloads":1}