paper-with-me

Papers

HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles

2021-10-07 · Odellia Boni, Guy Feigenblat, Guy Lev, Michal Shmueli-Scheuer, Benjamin Sznajder, David Konopnicki

We present HowSumm, a novel large-scale dataset for the task of query-focused multi-document summarization (qMDS), which targets the use-case of generating actionable instructions from a set of sources. This use-case is different from the use-cases covered in existing multi-document summarization (MDS) datasets and is applicable to educational and industrial scenarios. We employed automatic methods, and leveraged statistics from existing human-crafted qMDS datasets, to create HowSumm from wikiHow website articles and the sources they cite. We describe the creation of the dataset and discuss the unique features that distinguish it from other summarization corpora. Automatic and human evaluations of both extractive and abstractive summarization models on the dataset reveal that there is room for improvement.

📄 PDF Abstract BibTeX arXiv:2110.03179

Code (1)

odelliab/HowSumm 공식 구현

Tasks

Abstractive Text SummarizationArticlesDocument SummarizationMulti-Document Summarization

Similar Papers 제목 키워드 기반

MSˆ2: Multi-Document Summarization of Medical Studies

2021-11-01 · EMNLP 2021 11 · Jay DeYoung, Iz Beltagy, Madeleine van Zuylen, Bailey Kuehl 외

To assess the effectiveness of any medical intervention, researchers must conduct a time-intensive and manual literature review. NLP systems can help to automate or assist in parts of this expensive process. In support o…

Document SummarizationMulti-Document Summarization

MS2: Multi-Document Summarization of Medical Studies

2021-04-13 · Jay DeYoung, Iz Beltagy, Madeleine van Zuylen, Bailey Kuehl 외

To assess the effectiveness of any medical intervention, researchers must conduct a time-intensive and highly manual literature review. NLP systems can help to automate or assist in parts of this expensive process. In su…

Document SummarizationMulti-Document Summarization

MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization

2021-09-22 · Findings (EMNLP) 2021 11 · Xinnuo Xu, Ondřej Dušek, Shashi Narayan, Verena Rieser 외

One of the most challenging aspects of current single-document news summarization is that the summary often contains 'extrinsic hallucinations', i.e., facts that are not present in the source document, which are often de…

ArticlesDocument SummarizationMulti-Document SummarizationNews Summarization+1

OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization

2023-12-07 · Shmuel Amar, Liat Schiff, Ori Ernst, Asi Shefer 외

The performance of automatic summarization models has improved dramatically in recent years. Yet, there is still a gap in meeting specific information needs of users in real-world scenarios, particularly when a targeted …

Document SummarizationMulti-Document Summarization

Neural Abstractive Summarization with Structural Attention

2020-04-21 · Tanya Chowdhury, Sachin Kumar, Tanmoy Chakraborty

Attentional, RNN-based encoder-decoder architectures have achieved impressive performance on abstractive summarization of news articles. However, these methods fail to account for long term dependencies within the senten…

Abstractive Text SummarizationArticlesCommunity Question AnsweringDecoder+4