Sentence Fusion

19 papers with code • 1 benchmarks • 3 datasets

Sentence Fusion is the task of combining several independent sentences into a single coherent text. Sentence Fusion is important in many NLP applications, including retrieval-based dialogue, text summarization and question answering.

Source: DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion

Latest papers with no code

EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start

no code yet • 24 May 2022

This is achieved by decomposing the generation process into three sub-tasks: (1) tagging to decide on the subset of input tokens to be preserved in the output, (2) re-ordering to define their order in the output text, and (3) insertion to infill the missing tokens that are not present in the input.

Large-Scale Multi-Document Summarization with Information Extraction and Compression

no code yet • 1 May 2022

We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents.

Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations

no code yet • ACL ARR January 2022

NLP models that process multiple texts often struggle in recognizing corresponding and salient information that is often differently phrased, and consolidating the redundancies across texts.

Extractive and Abstractive Sentence Labelling of Sentiment-bearing Topics

no code yet • 29 Aug 2021

Our experimental results on three real-world datasets show that both the extractive and abstractive approaches outperform four strong baselines in terms of facilitating topic understanding and interpretation.

Unsupervised Text Style Transfer with Padded Masked Language Models

no code yet • EMNLP 2020

This allows us to identify the source tokens to delete to transform the source text to match the style of the target domain.

Analyzing Sentence Fusion in Abstractive Summarization

no code yet • WS 2019

While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences.

Extraction Meets Abstraction: Ideal Answer Generation for Biomedical Questions

no code yet • WS 2018

The growing number of biomedical publications is a challenge for human researchers, who invest considerable effort to search for relevant documents and pinpointed answers.

Abstractive Unsupervised Multi-Document Summarization using Paraphrastic Sentence Fusion

no code yet • COLING 2018

Furthermore, we apply our sentence level model to implement an abstractive multi-document summarization system where documents usually contain a related set of sentences.

Deep Learning Approaches to Text Production

no code yet • NAACL 2018

Each text production task raises a slightly different communication goal (e. g, how to take the dialogue context into account when producing a dialogue turn; how to detect and merge relevant information when summarising a text; or how to produce a well-formed text that correctly capture the information contained in some input data in the case of data-to-text generation).

Abstractive Meeting Summarization UsingDependency Graph Fusion

no code yet • 22 Sep 2016

Automatic summarization techniques on meeting conversations developed so far have been primarily extractive, resulting in poor summaries.