A multilingual news summarizer

Chen, Hsin-Hsi; Lin, Chuan-Jie

doi:10.3115/990820.990844

Cited by 40 publications

(24 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we mentioned, the dictionary-based MLDC approach [6,12] has difficulty translating terms that are ambiguous or have multiple meanings, as well as those that do not appear in the cross-lingual dictionary (e.g., abbreviations, technical terms, named entities, slang). For example, existing dictionary-based MLDC techniques fail to address [12] or just adopt a simple heuristic rule [6] to deal with word sense disambiguation.…”

Section: Multilingual Document Clustering Techniquesmentioning

confidence: 99%

“…In addition, they develop a name transliteration mechanism to translate Chinese named entities into English. The clusters initially in different languages therefore are in the same language (i.e., English), and similar clusters can be merged to form larger clusters, each of which pertains to a single event [6].…”

Section: Multilingual Document Clustering Techniquesmentioning

confidence: 99%

“…Chen and Lin [6] propose a multilingual news summarization system that is capable of summarizing news documents from multiple sources in different languages (in their study, English and Chinese). In their multilingual news summarization system, they propose a MLDC technique and use it to group multilingual news documents into clusters (events), each of which becomes the input to a news summarizer.…”

Section: Multilingual Document Clustering Techniquesmentioning

confidence: 99%

“…Similar to the aforementioned MLDC technique [6], non-English documents are first translated into English, and then both the translated documents and the documents originally written in English are clustered using an existing monolingual document clustering algorithm. Several cross-lingual dictionaries (e.g., Japanese, Russian) have been developed to translate non-English documents to English.…”

Section: Multilingual Document Clustering Techniquesmentioning

confidence: 99%

“…Among the proposed MLDC techniques, most rely on a cross-lingual dictionary [6,12] or a multilingual ontology [27] for language translations. On the basis of a cross-lingual dictionary, the dictionary-based MLDC approach performs translations of documents from one language to another and then applies an existing, monolingual document clustering technique.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Latent Semantic Indexing-based approach to multilingual document clustering

Wei

Yang

Lin³

2008

Decision Support Systems

View full text Add to dashboard Cite

Section: Multilingual Document Clustering Techniquesmentioning

confidence: 99%

Section: Multilingual Document Clustering Techniquesmentioning

confidence: 99%

Section: Multilingual Document Clustering Techniquesmentioning

confidence: 99%

Section: Multilingual Document Clustering Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Latent Semantic Indexing-based approach to multilingual document clustering

Wei

Yang

Lin³

2008

Decision Support Systems

View full text Add to dashboard Cite

Multilingual News Document Clustering: Two Algorithms Based on Cognate Named Entities

Montalvo

Martínez²,

Casillas

et al. 2006

Text, Speech and Dialogue

View full text Add to dashboard Cite

This paper presents an approach for Multilingual News Document Clustering in comparable corpora. We have implemented two algorithms of heuristic nature that follow the approach. They use as unique evidence for clustering the identification of cognate named entities between both sides of the comparable corpora. In addition, no information about the right number of clusters has to be provided to the algorithms. The applicability of the approach only depends on the possibility of identifying cognate named entities between the languages involved in the corpus. The main difference between the two algorithms consists of whether a monolingual clustering phase is applied at first or not. We have tested both algorithms with a comparable corpus of news written in English and Spanish. The performance of both algorithms is slightly different; the one that does not apply the monolingual phase reaches better results. In any case, the obtained results with both algorithms are encouraging and show that the use of cognate named entities can be enough knowledge for deal with multilingual clustering of news documents.

show abstract

Clustering and Visualization in a Multi-lingual Multi-document Summarization System

Chen

Kuo

2003

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

To measure the similarity of words, sentences, and documents is one of the major issues in multi-lingual multi-document summarization. This paper presents five strategies to compute the multilingual sentence similarity. The experimental results show that sentence alignment without considering the word position or order in a sentence obtains the best performance. Besides, two strategies are proposed for multilingual document clustering. The two-phase strategy (translation after clustering) is better than one-phase strategy (translation before clustering). Translation deferred to sentence clustering, which reduces the propagation of translation errors, is most promising. Moreover, three strategies are proposed to tackle the sentence clustering. Complete link within a cluster has the best performance, however, the subsumptionbased clustering has the advantage of lower computation complexity and similar performance. Finally, two visualization models (i.e., focusing and browsing), which consider the users' language preference, are proposed. Similarity Measurement MethodsWord exact matching cannot resolve paraphrase problem. Relaxation with WordNetlike resources (Fellbaum, 1998) postulates that words in the same synset are similar.

show abstract

A multilingual news summarizer

Cited by 40 publications

References 6 publications

A Latent Semantic Indexing-based approach to multilingual document clustering

A Latent Semantic Indexing-based approach to multilingual document clustering

Multilingual News Document Clustering: Two Algorithms Based on Cognate Named Entities

Clustering and Visualization in a Multi-lingual Multi-document Summarization System

Contact Info

Product

Resources

About