Corpus ID: 11116896

Cross-Language Document Summarization Based on Machine Translation Quality Prediction

@inproceedings{Wan2010CrossLanguageDS,
  title={Cross-Language Document Summarization Based on Machine Translation Quality Prediction},
  author={Xiaojun Wan and Huiying Li and J. Xiao},
  booktitle={ACL},
  year={2010}
}
Cross-language document summarization is a task of producing a summary in one language for a document set in a different language. [...] Key Method 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. Finally, the English sentences with high translation quality and high informative-ness are selected and translated to form the Chinese summary…Expand
Using Bilingual Information for Cross-Language Document Summarization
TLDR
Two summarization methods (SimFusion and CoRank) are proposed to leverage the bilingual information in the graph-based ranking framework for cross-language summary extraction to improve the effectiveness of these methods on the DUC2001 dataset. Expand
Cross-language document summarization via extraction and ranking of multiple summaries
TLDR
A new framework for addressing the task of cross-language document summarization by extraction and ranking of multiple summaries in the target language by proposing several schemes for improving the upper-bound quality of the summaries is proposed. Expand
Cross-Language Text Summarization Using Sentence and Multi-Sentence Compression
TLDR
A French-to-English cross-lingual summarization framework that analyzes the information in both languages to identify the most relevant sentences and introduces the use of chunks and two compression methods at the sentence and multi-sentence levels. Expand
Abstractive Cross-Language Summarization via Translation Model Enhanced Predicate Argument Structure Fusing
TLDR
The experimental results on English-to-Chinese cross-language summarization demonstrate that the proposed method outperforms the state-of-the-art extractive systems in both automatic and manual evaluations. Expand
A Graph-based Approach to Cross-language Multi-document Summarization
TLDR
A graph-based approach to multi-document summarization that integrates machine translation quality scores in the sentence extraction process is proposed and results indicate that the approach improves the readability of the generated summaries without degrading their informativity. Expand
SuMT: A Framework of Summarization and MT
TLDR
A novel system combination of machine translation and text summarization which provides high quality summary translations superior to the baseline translation of the entire document and can balance between improving MT quality and maintaining a decent summarization quality is presented. Expand
Cross - Language based Multi-Document Summarization Model using Machine Learning Technique
Cross-Language Multi-document summarization (CLMDS) process produces a summary generated from multiple documents in which the summary language is different from the source document language. TheExpand
Attend, Translate and Summarize: An Efficient Method for Neural Cross-Lingual Summarization
TLDR
A novel method inspired by the translation pattern in the process of obtaining a cross-lingual summary is proposed, which can significantly outperform the baselines and achieve comparable performance with the state-of-the-art. Expand
GuideRank: A Guided Ranking Graph Model for Multilingual Multi-document Summarization
TLDR
A novel graph model based on guided edge weighting method in which both informativeness and readability of summaries are taken into consideration fully is proposed, which significantly outperforms other baseline methods. Expand
Exploring content selection strategies for Multilingual Multi-Document Summarization based on the Universal Network Language (UNL)
TLDR
This experiment shows that “concept frequency normalized by the number of concepts in the sentence” is the measure that best ranks the sentences selected by humans, however, it does not outperform the superficial strategy based on the position of the sentences in the texts. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 39 REFERENCES
Multi-Document Summarization Using Cross-Language Texts
TLDR
This work tries to generate a summary in source language, using translated documents by a machine translator and a summarization system in target language, and shows the possibility of multi-documents summarization, using crosslanguage texts. Expand
Improving Multilingual Summarization: Using Redundancy in the Input to Correct MT errors
TLDR
The information redundancy in multilingual input is used to correct errors in machine translation and thus improve the quality of multilingual summaries, in the case of multi-document summarization. Expand
Evaluation of a Cross-lingual Romanian-English Multi-document Summariser
TLDR
An experiment is presented in which Maximal Marginal Relevance (MMR), a well known multi-document summarisation method, is used to produce summaries from Romanian news articles and it is revealed that they still contain a significant portion of the important information from the original texts. Expand
Experiments in Cross Language Query Focused Multi-Document Summarization
The twin challenges of massive information overload via the web and ubiquitous computers present us with an unavoidable task: developing techniques to handle multilingual information robustly andExpand
EUSUM: extracting easy-to-understand english summaries for non-native readers
TLDR
The proposed EUSUM system can produce more easy-to-understand summaries for non-native readers than existing summarization systems, with very little sacrifice of the summary's informativeness. Expand
Predicting the Fluency of Text with Shallow Structural Features: Case Studies of Machine Translation and Human-Written Text
TLDR
The results of an initial study into the predictive power of surface syntactic statistics for the task and fluency assessments done for the purpose of evaluating machine translation find that these features are weakly but significantly correlated with fluency. Expand
Sentence-level MT evaluation without reference translations: beyond language modeling
TLDR
It is shown that the correlation between automatically-generated scores and human judgments can be substantially improved by combining these perplexity scores with class probabilities from a machine-learned classifier. Expand
Using Cross-Document Random Walks for Topic-Focused Multi-Document
  • Xiaojun Wan, Jianwu Yang, J. Xiao
  • Computer Science
  • 2006 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2006 Main Conference Proceedings)(WI'06)
  • 2006
TLDR
The relevance of the sentences to the specified topic is integrated into the graph-ranking based method for topic-focused multi-document summarization and the great importance of the cross-document relationships between sentences is demonstrated. Expand
Extractive Summarization Using Supervised and Semi-Supervised Learning
TLDR
This paper investigates co-training by combining labeled and unlabeled data and shows that this semi-supervised learning approach achieves comparable performance to its supervised counterpart and saves about half of the labeling time cost. Expand
Improving the Confidence of Machine Translation Quality Estimates
TLDR
This work uses the theory of Inductive Confidence Machines (ICM) to identify a threshold to map a continuous predicted score into “good” / “bad” categories for filtering out bad-quality cases in a translation post-edition task. Expand
...
1
2
3
4
...