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

Non-autoregressive Text Editing with Copy-aware Latent Alignments

yzhangcs/ctc-copy 11 Oct 2023

In this work, we propose a novel non-autoregressive text editing method to circumvent the above issues, by modeling the edit process with latent CTC alignments.

16
11 Oct 2023

RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to Spans

webspellchecker/unlp-2023-shared-task 19 Sep 2023

The text editing tasks, including sentence fusion, sentence splitting and rephrasing, text simplification, and Grammatical Error Correction (GEC), share a common trait of dealing with highly similar input and output sequences.

4
19 Sep 2023

Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations

jyhuang36/intersent 24 May 2023

It is unclear whether the compositional semantics of sentences can be directly reflected as compositional operations in the embedding space.

7
24 May 2023

CoEdIT: Text Editing by Task-Specific Instruction Tuning

vipulraheja/coedit 17 May 2023

We present a large language model fine-tuned on a diverse collection of task-specific instructions for text editing (a total of 82K instructions).

85
17 May 2023

Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks

vipulraheja/iterater 2 Dec 2022

Leveraging datasets from other related text editing NLP tasks, combined with the specification of editable spans, leads our system to more accurately model the process of iterative text refinement, as evidenced by empirical results and human evaluations.

74
02 Dec 2022

ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models

szxiangjn/any-shot-data2text 9 Oct 2022

In the data disambiguation stage, we employ the prompted GPT-3 model to understand possibly ambiguous triples from the input data and convert each into a short sentence with reduced ambiguity.

14
09 Oct 2022

Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees

swarnahub/summarizationprograms 21 Sep 2022

We demonstrate that SP-Search effectively represents the generative process behind human summaries using modules that are typically faithful to their intended behavior.

24
21 Sep 2022

Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations

danielabweiss/extending-sentence-fusion-resources NAACL 2022

NLP models that compare or consolidate information across multiple documents often struggle when challenged with recognizing substantial information redundancies across the texts.

2
09 Oct 2021

Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution

jiacheng-xu/sum-interpret ACL 2021

Despite the prominence of neural abstractive summarization models, we know little about how they actually form summaries and how to understand where their decisions come from.

13
03 Jun 2021

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.

13
03 Nov 2020