Cross-Language Document Summarization Based on Machine Translation Quality Prediction
Wan, Xiaojun and Li, Huiying and Xiao, Jianguo

Article Structure

Abstract

Cross-language document summarization is a task of producing a summary in one language for a document set in a different language.

Introduction

Given a document or document set in one source language, cross-language document summarization aims to produce a summary in a different target language.

Related Work 2.1 Machine Translation Quality Prediction

Machine translation evaluation aims to assess the correctness and quality of the translation.

The Proposed Approach

Previous methods for cross-language summarization usually consist of two steps: one step for summarization and one step for translation.

Machine Translation Quality Prediction

4.1 Methodology

Cross-Language Document Summarization

5.1 Methodology

Discussion

In this study, we adopt the late translation strategy for cross-document summarization.

Conclusion and Future Work

In this study we propose a novel approach to address the cross-language document summarization task.

Topics

machine translation

Appears in 17 sentences as: Machine Translation (1) Machine translation (1) machine translation (18)
In Cross-Language Document Summarization Based on Machine Translation Quality Prediction
  1. EXisting methods simply use machine translation for document translation or summary translation.
    Page 1, “Abstract”
  2. However, current machine translation services are far from satisfactory, which results in that the quality of the cross-language summary is usually very poor, both in readability and content.
    Page 1, “Abstract”
  3. A straightforward way for cross-language document summarization is to translate the summary from the source language to the target language by using machine translation services.
    Page 1, “Introduction”
  4. However, though machine translation techniques have been advanced a lot, the machine translation quality is far from satisfactory, and in many cases, the translated texts are hard to understand.
    Page 1, “Introduction”
  5. An empirical evaluation is conducted to evaluate the performance of machine translation quality prediction, and a user study is performed to evaluate the cross-language summary quality.
    Page 1, “Introduction”
  6. results of machine translation quality prediction and cross-language summarization, respectively.
    Page 2, “Introduction”
  7. Machine translation evaluation aims to assess the correctness and quality of the translation.
    Page 2, “Related Work 2.1 Machine Translation Quality Prediction”
  8. Chae and Nenkova (2009) use surface syntactic features to assess the fluency of machine translation results.
    Page 2, “Related Work 2.1 Machine Translation Quality Prediction”
  9. In this study, we further predict the translation quality of an English sentence before the machine translation process, i.e., we do not leverage reference translation and the target sentence.
    Page 2, “Related Work 2.1 Machine Translation Quality Prediction”
  10. (2003) use machine translation for English headline generation for Hindi documents.
    Page 2, “Related Work 2.1 Machine Translation Quality Prediction”
  11. Siddharthan and McKeown (2005) use the information redundancy in multilingual input to correct errors in machine translation and thus improve the quality of multilingual summaries.
    Page 3, “Related Work 2.1 Machine Translation Quality Prediction”

See all papers in Proc. ACL 2010 that mention machine translation.

See all papers in Proc. ACL that mention machine translation.

Back to top.

translation quality

Appears in 15 sentences as: translation quality (16)
In Cross-Language Document Summarization Based on Machine Translation Quality Prediction
  1. In this paper, we propose to consider the translation quality of each sentence in the English-to-Chinese cross-language summarization process.
    Page 1, “Abstract”
  2. First, the translation quality of each English sentence in the document set is predicted with the SVM regression method, and then the quality score of each sentence is incorporated into the summarization process.
    Page 1, “Abstract”
  3. Finally, the English sentences with high translation quality and high informativeness are selected and translated to form the Chinese summary.
    Page 1, “Abstract”
  4. However, though machine translation techniques have been advanced a lot, the machine translation quality is far from satisfactory, and in many cases, the translated texts are hard to understand.
    Page 1, “Introduction”
  5. In order to address the above problem, we propose to consider the translation quality of the English sentences in the summarization process.
    Page 1, “Introduction”
  6. In particular, the translation quality of each English sentence is predicted by using the SVM regression method, and then the predicted MT quality score of each sentence is incorporated into the sentence evaluation process, and finally both informative and easy-to-translate sentences are selected and translated to form the Chinese summary.
    Page 1, “Introduction”
  7. An empirical evaluation is conducted to evaluate the performance of machine translation quality prediction, and a user study is performed to evaluate the cross-language summary quality.
    Page 1, “Introduction”
  8. results of machine translation quality prediction and cross-language summarization, respectively.
    Page 2, “Introduction”
  9. In this study, we further predict the translation quality of an English sentence before the machine translation process, i.e., we do not leverage reference translation and the target sentence.
    Page 2, “Related Work 2.1 Machine Translation Quality Prediction”
  10. Each English sentence is associated with a score indicating its translation quality .
    Page 3, “The Proposed Approach”
  11. An English sentence with high translation quality score is more likely to be selected into the original English summary, and such English summary can be translated into a better Chinese summary.
    Page 3, “The Proposed Approach”

See all papers in Proc. ACL 2010 that mention translation quality.

See all papers in Proc. ACL that mention translation quality.

Back to top.

parse tree

Appears in 5 sentences as: parse tree (8)
In Cross-Language Document Summarization Based on Machine Translation Quality Prediction
  1. We use the Stanford LeXicalized Parser (Klein and Manning, 2002) with the provided English PCFG model to parse a sentence into a parse tree .
    Page 4, “Machine Translation Quality Prediction”
  2. 1) Depth of the parse tree: It refers to the depth of the generated parse tree .
    Page 4, “Machine Translation Quality Prediction”
  3. 2) Number of SBARs in the parse tree : SBAR is defined as a clause introduced by a (possibly empty) subordinating conjunction.
    Page 4, “Machine Translation Quality Prediction”
  4. 3) Number of NPs in the parse tree: It refers to the number of noun phrases in the parse tree .
    Page 5, “Machine Translation Quality Prediction”
  5. 4) Number of VPs in the parse tree: It refers to the number of verb phrases in the parse tree .
    Page 5, “Machine Translation Quality Prediction”

See all papers in Proc. ACL 2010 that mention parse tree.

See all papers in Proc. ACL that mention parse tree.

Back to top.

news articles

Appears in 4 sentences as: news articles (4)
In Cross-Language Document Summarization Based on Machine Translation Quality Prediction
  1. and Chiorean (2008) propose to produce summaries with the MMR method from Romanian news articles and then automatically translate the summaries into English.
    Page 3, “Related Work 2.1 Machine Translation Quality Prediction”
  2. DUC2001 provided 309 English news articles for document summarization tasks, and the articles were grouped into 30 document sets.
    Page 5, “Machine Translation Quality Prediction”
  3. The news articles were selected from TREC-9.
    Page 5, “Machine Translation Quality Prediction”
  4. We chose five document sets (d04, d05, d06, d08, d1 1) with 54 news articles out of the DUC2001 document sets.
    Page 5, “Machine Translation Quality Prediction”

See all papers in Proc. ACL 2010 that mention news articles.

See all papers in Proc. ACL that mention news articles.

Back to top.