ROBO, an edit distance for sentence comparison Application to automatic summarization
Dans cet article, nous proposons une mesure de distance entre phrases fond{\'e}e sur la distance de Levenshtein, doublement pond{\'e}r{\'e}e par la fr{\'e}quence des mots et par le type d{'}op{\'e}ration r{\'e}alis{\'e}e. Nous l{'}{\'e}valuons au sein d{'}un syst{\e}me de r{\'e}sum{\'e} automatique dont la m{\'e}thode de calcul est volontairement limit{\'e}e {\a} une approche fond{\'e}e sur la similarit{\'e} entre phrases. Nous sommes donc ainsi en mesure d{'}{\'e}valuer indirectement la performance de cette nouvelle mesure de distance.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSimilar Papers 제목 키워드 기반
Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance
This paper revisits recent code similarity evaluation metrics, particularly focusing on the application of Abstract Syntax Tree (AST) editing distance in diverse programming languages. In particular, we explore the usefu…
BoschAI @ PLABA 2023: Leveraging Edit Operations in End-to-End Neural Sentence Simplification
Automatic simplification can help laypeople to comprehend complex scientific text. Language models are frequently applied to this task by translating from complex to simple language. In this paper, we describe our system…
SentenceIntelligent Translation Memory Matching and Retrieval with Sentence Encoders
Matching and retrieving previously translated segments from a Translation Memory is the key functionality in Translation Memories systems. However this matching and retrieving process is still limited to algorithms based…
RetrievalSentenceTranslationSoft edit distance for differentiable comparison of symbolic sequences
Edit distance, also known as Levenshtein distance, is an essential way to compare two strings that proved to be particularly useful in the analysis of genetic sequences and natural language processing. However, edit dist…
ClusteringProofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction
This paper explores the idea of robot editors, automated proofreaders that enable journalists to improve the quality of their articles. We propose a novel neural model of multi-task learning that both generates proofread…
ArticlesGrammatical Error CorrectionMulti-Task LearningSentence