paper-with-me

Papers

NEWTS: A Corpus for News Topic-Focused Summarization

2022-05-31 · Findings (ACL) 2022 5 · Seyed Ali Bahrainian, Sheridan Feucht, Carsten Eickhoff

Text summarization models are approaching human levels of fidelity. Existing benchmarking corpora provide concordant pairs of full and abridged versions of Web, news or, professional content. To date, all summarization datasets operate under a one-size-fits-all paradigm that may not reflect the full range of organic summarization needs. Several recently proposed models (e.g., plug and play language models) have the capacity to condition the generated summaries on a desired range of themes. These capacities remain largely unused and unevaluated as there is no dedicated dataset that would support the task of topic-focused summarization. This paper introduces the first topical summarization corpus NEWTS, based on the well-known CNN/Dailymail dataset, and annotated via online crowd-sourcing. Each source article is paired with two reference summaries, each focusing on a different theme of the source document. We evaluate a representative range of existing techniques and analyze the effectiveness of different prompting methods.

📄 PDF Abstract BibTeX arXiv:2205.15661

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingText Summarization

Similar Papers 제목 키워드 기반

Controllable Topic-Focused Abstractive Summarization

2023-11-12 · Seyed Ali Bahrainian, Martin Jaggi, Carsten Eickhoff

Controlled abstractive summarization focuses on producing condensed versions of a source article to cover specific aspects by shifting the distribution of generated text towards a desired style, e.g., a set of topics. Su…

Abstractive Text Summarization

Topic-Selective Graph Network for Topic-Focused Summarization

2023-02-25 · Shi Zesheng, Zhou Yucheng

Due to the success of the pre-trained language model (PLM), existing PLM-based summarization models show their powerful generative capability. However, these models are trained on general-purpose summarization datasets, …

ARCLanguage ModelingLanguage Modelling

Logit Reweighting for Topic-Focused Summarization

2025-07-07 · Joschka Braun, Bálint Mucsányi, Seyed Ali Bahrainian arxiv

Generating abstractive summaries that adhere to a specific topic remains a significant challenge for language models. While standard approaches, such as fine-tuning, are resource-intensive, simpler methods like prompt en…

Prompt Engineering

Priberam Compressive Summarization Corpus: A New Multi-Document Summarization Corpus for European Portuguese

2014-05-01 · LREC 2014 5 · Miguel B. Almeida, Mariana S. C. Almeida, Andr{\'e} F. T. Martins, Helena Figueira 외

In this paper, we introduce the Priberam Compressive Summarization Corpus, a new multi-document summarization corpus for European Portuguese. The corpus follows the format of the summarization corpora for English in rece…

Document SummarizationInformation RetrievalMulti-Document SummarizationSentence+2

NEWSFARM: the Largest Chinese Corpus for Long News Summarization

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Recently, driven by a large number of datasets, the field of natural language processing(NLP) has developed rapidly. However, the lack of large-scale and high-quality Chinese datasets is still a critical bottleneck for f…

News SummarizationSemantic SimilaritySemantic Textual SimilarityText Summarization