Phrase-based Compressive Cross-Language Summarization

By Jin-ge Yao, Xiaojun Wan, Jianguo Xiao. 2015

57 citations recorded by the source corpus.

The task of cross-language document summarization is to create a summary in a target language from documents in a different source language. Previous methods only involve direct extraction of automatically translated sentences from the original documents. Inspired by phrasebased machine translation, we propose a phrase-based model to simultaneously perform sentence scoring, extraction and compression. We design a greedy algorithm to approximately optimize the score function. Experimental results show that our methods outperform the state-of-theart extractive systems while maintaining similar grammatical quality.

Subfields: Artificial Intelligence, Natural Language Processing, Summarization

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Summarization

Citations in the corpus

WikiLingua: A New Benchmark Dataset for Multilingual Abstractive Summarization (2020, background): “Scarcity of cross-lingual summarization data has limited prior work to a few languages, and mostly in the news domain (Wan et al., 2010; Wan, 2011; Yao et al., 2015; Zhang et al., 2016; Wan et al., 2019).”
A Robust Abstractive System for Cross-Lingual Summarization (2019, unknown): “Yao et al. (2015) scored aligned phrases from the original English documents and the Chinese translations to perform sentence extraction and compression based on both salience and translation quality.”
Recent advances in document summarization (2017, background): “Currently proposed solutions include bilingual graph coranking [183] and other approaches inspired by statistical machine translation [205,213].”
Zero-Shot Cross-Lingual Neural Headline Generation (2018, background): “[3] presents a machine translation inspired scoring paradigm to construct the summary.”
Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention (2019, methodology): “, 2010), sentence ranking based on cross-lingual sentence similarity (Wan, 2011), or abstractive summarization based on phrase pair (Yao et al., 2015) and predicate-argument structure fusing (Zhang et al.”
NCLS: Neural Cross-Lingual Summarization (2019, methodology): “…graph-based summarization methods to leverage both the English-side and Chinese-side information in the task of English-to-Chinese CLS. Inspired by the phrase-based translation models, Yao et al. (2015) introduce a compressive CLS, which simultaneously performs sentence selection and compression.”
Cross-language document summarization via extraction and ranking of multiple summaries (2019, methodology): “[27] and relied merely on the English-side information for English sentence ranking in the original documents.”
Abstractive Cross-Language Summarization via Translation Model Enhanced Predicate Argument Structure Fusing (2016, methodology): “In this study, we employ the same dataset12 used by [2], [3] to evaluate the performance of our method.”