Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua 2021
DOI: 10.18653/v1/2021.naacl-main.44
|View full text |Cite
|
Sign up to set email alerts
|

Open-Domain Question Answering Goes Conversational via Question Rewriting

Abstract: We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs. The task in QReCC is to find answers to conversational questions within a collection of 10M web pages (split into 54M passages). Answers to questions in the same conversation may be distributed across several web pages. QReCC provides annotations that allow us to train and evaluate individual subtasks of question rewriting, passage retrieval and reading comprehen… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
59
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 52 publications
(59 citation statements)
references
References 24 publications
0
59
0
Order By: Relevance
“…We experiment with two different fixed retrievers, and show CONQRR outperforms baseline supervised models on three conversational retrieval metrics for an average of 13% performance boost on a recent open-domain CQA dataset QReCC (Anantha et al, 2021). We also observe the performance boost on three QReCC subsets from different conversation sources.…”
Section: Introductionmentioning
confidence: 80%
See 4 more Smart Citations
“…We experiment with two different fixed retrievers, and show CONQRR outperforms baseline supervised models on three conversational retrieval metrics for an average of 13% performance boost on a recent open-domain CQA dataset QReCC (Anantha et al, 2021). We also observe the performance boost on three QReCC subsets from different conversation sources.…”
Section: Introductionmentioning
confidence: 80%
“…Different from our work, such datasets do not require the retrieval step. QReCC (Anantha et al, 2021) is a recently released open-domain CQA dataset of dialogues where a conversational agent first retrieves the most relevant passage(s) before generating an answer response to the a question.…”
Section: Related Workmentioning
confidence: 99%
See 3 more Smart Citations