Unsupervised Rewriter for Multi-Sentence Compression
Multi-sentence compression (MSC) aims to generate a grammatical but reduced compression from multiple input sentences while retaining their key information. Previous dominating approach for MSC is the extraction-based word graph approach. A few variants further leveraged lexical substitution to yield more abstractive compression. However, two limitations exist. First, the word graph approach that simply concatenates fragments from multiple sentences may yield non-fluent or ungrammatical compression. Second, lexical substitution is often inappropriate without the consideration of context information. To tackle the above-mentioned issues, we present a neural rewriter for multi-sentence compression that does not need any parallel corpus. Empirical studies have shown that our approach achieves comparable results upon automatic evaluation and improves the grammaticality of compression based on human evaluation. A parallel corpus with more than 140,000 (sentence group, compression) pairs is also constructed as a by-product for future research.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSentence CompressionSimilar Papers 제목 키워드 기반
Rewriter-Evaluator Architecture for Neural Machine Translation
Encoder-decoder has been widely used in neural machine translation (NMT). A few methods have been proposed to improve it with multiple passes of decoding. However, their full potential is limited by a lack of appropriate…
DecoderMachine TranslationNMTSentence+1Rewriter-Evaluator Framework for Neural Machine Translation
Encoder-decoder architecture has been widely used in neural machine translation (NMT). A few methods have been proposed to improve it with multiple passes of decoding. However, their full potential is limited by a lack o…
DecoderMachine TranslationNMTSentence+1The User-Aware Arabic Gender Rewriter
We introduce the User-Aware Arabic Gender Rewriter, a user-centric web-based system for Arabic gender rewriting in contexts involving two users. The system takes either Arabic or English sentences as input, and provides …
Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning
Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality. Unsupervised objective driven methods for sentence compression can be used to create …
reinforcement-learningReinforcement Learning (RL)SentenceSentence Compression+1Improving Unsupervised Visual Program Inference with Code Rewriting Families
Programs offer compactness and structure that makes them an attractive representation for visual data. We explore how code rewriting can be used to improve systems for inferring programs from visual data. We first propos…