Phrase-based Compressive Cross-Language Summarization

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 118–127, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Phrase-based Compressive Cross-Language Summarization Jin-ge Yao Xiaojun Wan Jianguo Xiao Institute of Computer Science and Technology, Peking University, Beijing 100871, China Key Laboratory of Computational Linguistic (Peking University), MOE, China {yaojinge, wanxiaojun, xiaojianguo}@pku.edu.cn Abstract The task of cross-language document summarization is to create a summary in a target language from documents in a dif- ferent source language. Previous meth- ods only involve direct extraction of au- tomatically translated sentences from the original documents. Inspired by phrase- based machine translation, we propose a phrase-based model to simultaneously perform sentence scoring, extraction and compression. We design a greedy algo- rithm to approximately optimize the score function. Experimental results show that our methods outperform the state-of-the- art extractive systems while maintaining similar grammatical quality. 1 Introduction The task of cross-language summarization is to produce a summary in a target language from documents written in a different source language. This task is particularly useful for readers to quickly get the main idea of documents written in a source language that they are not familiar with. Following Wan (2011), we focus on English-to- Chinese summarization in this work. The simplest and the most straightforward way to perform cross-language summarization is pipelining general summarization and machine translation. Such systems either translate all the documents before running generic summarization algorithms on the translated documents, or sum- marize from the original documents and then only translate the produced summary into the target lan- guage. Wan (2011) show that such pipelining ap- proaches are inferior to methods that utilize in- formation from both sides. In that work, the au- thor proposes graph-based models and achieves fair amount of improvement. However, to the best of our knowledge, no previous work of this task tries to focus on summarization beyond pure sen- tence extraction. On the other hand, cross-language summariza- tion can be seen as a special kind of machine trans- lation: translating the original documents into a brief summary in a different language. Inspired by phrase-based machine translation models (Koehn et al., 2003), we propose a phrase-based scoring scheme for cross-language summarization in this work. Since our framework is based on phrases, we are not limited to produce extractive summaries. We can use the scoring scheme to perform joint sentence selection and compression. Unlike typi- cal sentence compression methods, our proposed algorithm does not require additional syntactic preprocessing such as part-of-speech tagging or syntactic parsing. We only utilize information from translated texts with phrase alignments. The scoring function consists of a submodular term of compressed sentences and a bounded distortion penalty term. We design a greedy procedure to efficiently get approximate solutions. For experimental evaluation, we use the DUC2001 dataset with manually translated refer- ence Chinese summaries. Results based on the ROUGE metrics show the effectiveness of our pro- posed methods. We also conduct manual evalua- tion and the results suggest that the linguistic qual- ity …

Content truncated to 500 words