paper-with-me

홈 › Papers

Reference-based Weak Supervision for Answer Sentence Selection using Web Data

2021-04-18 · Findings (EMNLP) 2021 11 · Vivek Krishnamurthy, Thuy Vu, Alessandro Moschitti

Answer sentence selection (AS2) modeling requires annotated data, i.e., hand-labeled question-answer pairs. We present a strategy to collect weakly supervised answers for a question based on its reference to improve AS2 modeling. Specifically, we introduce Reference-based Weak Supervision (RWS), a fully automatic large-scale data pipeline that harvests high-quality weakly-supervised answers from abundant Web data requiring only a question-reference pair as input. We study the efficacy and robustness of RWS in the setting of TANDA, a recent state-of-the-art fine-tuning approach specialized for AS2. Our experiments indicate that the produced data consistently bolsters TANDA. We achieve the state of the art in terms of P@1, 90.1%, and MAP, 92.9%, on WikiQA.

📄 PDF Abstract BibTeX arXiv:2104.08943

Code (0)

등록된 구현이 없습니다.

Tasks

Sentence

Similar Papers 제목 키워드 기반

Weak Supervision Enhanced Generative Network for Question Generation

2019-07-01 · Yutong Wang, Jiyuan Zheng, Qijiong Liu, Zhou Zhao 외

Automatic question generation according to an answer within the given passage is useful for many applications, such as question answering system, dialogue system, etc. Current neural-based methods mostly take two steps w…

DecoderQuestion AnsweringQuestion GenerationQuestion-Generation

Context-based Transformer Models for Answer Sentence Selection

2020-06-01 · Ivano Lauriola, Alessandro Moschitti

An important task for the design of Question Answering systems is the selection of the sentence containing (or constituting) the answer from documents relevant to the asked question. Most previous work has only used the …

Question AnsweringSentence

SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References

2023-09-21 · Matteo Gabburo, Siddhant Garg, Rik Koncel Kedziorski, Alessandro Moschitti

Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions. Recent works (AVA, BEM) have shown that transformer LM encoder …

Answer SelectionQuestion AnsweringSentence

Learning Answer Generation using Supervision from Automatic Question Answering Evaluators

2023-05-24 · Matteo Gabburo, Siddhant Garg, Rik Koncel-Kedziorski, Alessandro Moschitti

Recent studies show that sentence-level extractive QA, i.e., based on Answer Sentence Selection (AS2), is outperformed by Generation-based QA (GenQA) models, which generate answers using the top-k answer sentences ranked…

Answer GenerationQuestion AnsweringRetrievalRetrieval-augmented Generation+1

Evidence Sentence Extraction for Machine Reading Comprehension

2019-02-23 · CONLL 2019 11 · Hai Wang, Dian Yu, Kai Sun, Jianshu Chen 외

Remarkable success has been achieved in the last few years on some limited machine reading comprehension (MRC) tasks. However, it is still difficult to interpret the predictions of existing MRC models. In this paper, we …

Machine Reading ComprehensionMultiple-choiceOpen-Domain Question AnsweringQuestion Answering+2