Answer Consolidation: Formulation and Benchmarking
Not on the map. Why?
Abstract (arXiv)
Current question answering (QA) systems primarily consider the single-answer scenario, where each question is assumed to be paired with one correct answer. However, in many real-world QA applications, multiple answer scenarios arise where consolidating answers into a comprehensive and non-redundant set of answers is a more efficient user interface. In this paper, we formulate the problem of answer consolidation, where answers are partitioned into multiple groups, each representing different aspects of the answer set. Then, given this partitioning, a comprehensive and non-redundant set of answers can be constructed by picking one answer from each group. To initiate research on answer consolidation, we construct a dataset consisting of 4,699 questions and 24,006 sentences and evaluate multiple models. Despite a promising performance achieved by the best-performing supervised models, we still believe this task has room for further improvements.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 50 references that are in the map. First posted on arXiv 29 Apr 2022.
Builds on
31 of 50 references.
References · 31
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
- 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
- 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 476
- 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
19 more
- 2018Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Taskscited by 215
- 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
- 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
- 2019End-to-End Open-Domain Question Answering with BERTserinicited by 152
- 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 148
- 2017DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applicationscited by 110
- 2019Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answeringcited by 96
- 2021GooAQ: Open Question Answering with Diverse Answer Typescited by 53
- 2021Joint Passage Ranking for Diverse Multi-Answer Retrievalcited by 43
- 2017Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answeringcited by 24
- 2018TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verificationcited by 17
- 2019RankQA: Neural Question Answering with Answer Re-Rankingcited by 15
- 2021MultiOpEd: A Corpus of Multi-Perspective News Editorialscited by 13
- 2018CQASUMM: Building References for Community Question Answering Summarization Corporacited by 11
- 2020Managing Diversity in Airbnb Searchcited by 11
- 2018Modeling Diverse Relevance Patterns in Ad-hoc Retrievalcited by 10
- 2019Open Information Extraction from Question-Answer Pairscited by 6
- 2021Multi-Perspective Abstractive Answer Summarizationcited by 4
- 2020Diverse and Non-redundant Answer Set Extraction on Community QA based on DPPscited by 1
Built on by
Citing papers per year: 2022: 1.
1 paper.