paper-with-me

Papers

Controllable Abstractive Dialogue Summarization with Sketch Supervision

2021-05-28 · Findings (ACL) 2021 8 · Chien-Sheng Wu, Linqing Liu, Wenhao Liu, Pontus Stenetorp, Caiming Xiong

In this paper, we aim to improve abstractive dialogue summarization quality and, at the same time, enable granularity control. Our model has two primary components and stages: 1) a two-stage generation strategy that generates a preliminary summary sketch serving as the basis for the final summary. This summary sketch provides a weakly supervised signal in the form of pseudo-labeled interrogative pronoun categories and key phrases extracted using a constituency parser. 2) A simple strategy to control the granularity of the final summary, in that our model can automatically determine or control the number of generated summary sentences for a given dialogue by predicting and highlighting different text spans from the source text. Our model achieves state-of-the-art performance on the largest dialogue summarization corpus SAMSum, with as high as 50.79 in ROUGE-L score. In addition, we conduct a case study and show competitive human evaluation results and controllability to human-annotated summaries.

📄 PDF Abstract BibTeX arXiv:2105.14064

Code (1)

salesforce/ConvSumm 공식 구현 pytorch

Tasks

Abstractive Dialogue Summarization

Similar Papers 제목 키워드 기반

CorDial: Coarse-to-fine Abstractive Dialogue Summarization with Controllable Granularity

2021-01-01 · Chien-Sheng Wu, Linqing Liu, Wenhao Liu, Pontus Stenetorp 외

Dialogue summarization is challenging due to its multi-speaker standpoints, casual spoken language, and limited labeled data. In this paper, we propose CorDial, aiming to improve the abstractive dialogue summarization qu…

Abstractive Dialogue Summarization

MACSum: Controllable Summarization with Mixed Attributes

2022-11-09 · Yusen Zhang, Yang Liu, ZiYi Yang, Yuwei Fang 외

Controllable summarization allows users to generate customized summaries with specified attributes. However, due to the lack of designated annotations of controlled summaries, existing works have to craft pseudo datasets…

ArticlesAttributeSpecificity

Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization

2022-09-01 · Hyunjae Lee, Jaewoong Yun, Hyunjin Choi, Seongho Joe 외

Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natur…

Abstractive Dialogue SummarizationAbstractive Text SummarizationArticlesDecoder+5

Long Input Dialogue Summarization with Sketch Supervision for Summarization of Primetime Television Transcripts

2022-10-01 · COLING (CreativeSumm) 2022 10 · Nataliia Kees, Thien Nguyen, Tobias Eder, Georg Groh

This paper presents our entry to the CreativeSumm 2022 shared task. Specifically tackling the problem of prime-time television screenplay summarization based on the SummScreen Forever Dreaming dataset. Our approach utili…

A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarization

2021-11-01 · Findings (EMNLP) 2021 11 · Yuejie Lei, Fujia Zheng, Yuanmeng Yan, Keqing He 외

Although abstractive summarization models have achieved impressive results on document summarization tasks, their performance on dialogue modeling is much less satisfactory due to the crude and straight methods for dialo…

Abstractive Dialogue SummarizationAbstractive Text SummarizationDocument Summarization