paper-with-me

Papers

Guiding Extractive Summarization with Question-Answering Rewards

2019-04-04 · NAACL 2019 6 · Kristjan Arumae, Fei Liu

Highlighting while reading is a natural behavior for people to track salient content of a document. It would be desirable to teach an extractive summarizer to do the same. However, a major obstacle to the development of a supervised summarizer is the lack of ground-truth. Manual annotation of extraction units is cost-prohibitive, whereas acquiring labels by automatically aligning human abstracts and source documents can yield inferior results. In this paper we describe a novel framework to guide a supervised, extractive summarization system with question-answering rewards. We argue that quality summaries should serve as a document surrogate to answer important questions, and such question-answer pairs can be conveniently obtained from human abstracts. The system learns to promote summaries that are informative, fluent, and perform competitively on question-answering. Our results compare favorably with those reported by strong summarization baselines as evaluated by automatic metrics and human assessors.

📄 PDF Abstract BibTeX arXiv:1904.02321

Code (1)

ucfnlp/summ_qa_rewards 공식 구현

Tasks

Extractive SummarizationQuestion Answering

Similar Papers 제목 키워드 기반

Reinforced Extractive Summarization with Question-Focused Rewards

2018-05-25 · ACL 2018 7 · Kristjan Arumae, Fei Liu

We investigate a new training paradigm for extractive summarization. Traditionally, human abstracts are used to derive goldstandard labels for extraction units. However, the labels are often inaccurate, because human abs…

Extractive Summarizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering

2023-10-10 · Nianlong Gu, Yingqiang Gao, Richard H. R. Hahnloser

We introduce MemSum-DQA, an efficient system for document question answering (DQA) that leverages MemSum, a long document extractive summarizer. By prefixing each text block in the parsed document with the provided quest…

Extractive SummarizationQuestion Answering

UNCC QA: Biomedical Question Answering system

2018-11-01 · WS 2018 11 · Bh, Abhishek waldar, Wlodek Zadrozny

In this paper, we detail our submission to the BioASQ competition{'}s Biomedical Semantic Question and Answering task. Our system uses extractive summarization techniques to generate answers and has scored highest ROUGE-…

Extractive SummarizationQuestion Answering

Summarizing Lengthy Questions

2017-11-01 · IJCNLP 2017 11 · Tatsuya Ishigaki, Hiroya Takamura, Manabu Okumura

In this research, we propose the task of question summarization. We first analyzed question-summary pairs extracted from a Community Question Answering (CQA) site, and found that a proportion of questions cannot be summa…

Abstractive Text SummarizationCommunity Question AnsweringDecoderQuestion Answering

Hindi History Note Generation with Unsupervised Extractive Summarization

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Aayush Shah, Dhineshkumar Ramasubbu, Dhruv Mathew, Meet Chetan Gadoya

In this work, the task of extractive single document summarization applied to an education setting to generate summaries of chapters from grade 10 Hindi history textbooks is undertaken. Unsupervised approaches to extract…

Document SummarizationExtractive SummarizationUnsupervised Extractive Summarization