Sentence Fusion

18 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

Most implemented papers

Leveraging Pre-trained Checkpoints for Sequence Generation Tasks

huggingface/transformers TACL 2020

Unsupervised pre-training of large neural models has recently revolutionized Natural Language Processing.

Encode, Tag, Realize: High-Precision Text Editing

google-research/lasertagger IJCNLP 2019

We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task.

Scoring Sentence Singletons and Pairs for Abstractive Summarization

ucfnlp/summarization-sing-pair-mix ACL 2019

There is thus a crucial gap between sentence selection and fusion to support summarizing by both compressing single sentences and fusing pairs.

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

google-research-datasets/discofuse NAACL 2019

We author a set of rules for identifying a diverse set of discourse phenomena in raw text, and decomposing the text into two independent sentences.

Felix: Flexible Text Editing Through Tagging and Insertion

google-research/google-research Findings of the Association for Computational Linguistics 2020

We achieve this by decomposing the text-editing task into two sub-tasks: tagging to decide on the subset of input tokens and their order in the output text and insertion to in-fill the missing tokens in the output not present in the input.

Understanding Points of Correspondence between Sentences for Abstractive Summarization

ucfnlp/points-of-correspondence ACL 2020

We create a dataset containing the documents, source and fusion sentences, and human annotations of points of correspondence between sentences.

Seq2Edits: Sequence Transduction Using Span-level Edit Operations

tensorflow/tensor2tensor EMNLP 2020

For text normalization, sentence fusion, and grammatical error correction, our approach improves explainability by associating each edit operation with a human-readable tag.

Learning to Fuse Sentences with Transformers for Summarization

ucfnlp/sent-fusion-transformers EMNLP 2020

The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts.

Data-to-Text Generation with Iterative Text Editing

kasnerz/d2t_iterative_editing INLG (ACL) 2020

Our approach maximizes the completeness and semantic accuracy of the output text while leveraging the abilities of recent pre-trained models for text editing (LaserTagger) and language modeling (GPT-2) to improve the text fluency.