Multilingual Information Retrieval Based on Document Alignment Techniques

Braschler, Martín; Schäuble, Peter

doi:10.1007/3-540-49653-x_12

Cited by 35 publications

(32 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In our experiments, we assess the alignments quality using a five-level relevance scale proposed by [7]. The five levels of relevance to assessing the alignments are defined as follows: Level 1.…”

Section: Resultsmentioning

confidence: 99%

“…Braschler and Scauble [7] employed content descriptors, publication dates, subject codes, common proper nouns, numbers and a small dictionary to align German and Italian news stories. Resnik [8] mined comparable corpora on the assumption that the pages presented in numerous languages on the Web are comparable to each other which share a similar structure such as headers, paragraphs and hyper links.…”

Section: Introductionmentioning

confidence: 99%

“…The English queries were run against the English collection and documents were aligned according to the similarity and publication dates. Their method is most akin to Braschler's method [7]. Rahimi and Shakery [10] used the similarity of the document topics and their publication dates to align the documents in their collections to build a Persian-English comparable corpus.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Creating Chinese-English Comparable Corpora

Huang

Wang

Ren

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYComparable Corpora are valuable resources for many NLP applications, and extensive research has been done on information mining based on comparable corpora in recent years. While there are not enough large-scale available public comparable corpora at present, this paper presents a bi-directional CLIR-based method for creating comparable corpora from two independent news collections in different languages. The original Chinese document collections and English documents collections are crawled from XinHuaNet respectively and formatted in a consistent manner. For each document from the two collections, the best query keywords are extracted to represent the essential content of the document, and then the keywords are translated into the language of the other collection. The translated queries are run against the collection in the same language to pick up the candidate documents in the other language and candidates are aligned based on their publication dates and the similarity scores. Results show that our approach significantly outperforms previous approaches to the construction of Chinese-English comparable corpora.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Creating Chinese-English Comparable Corpora

Huang

Wang

Ren

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Most of the research on the automatic creation of comparable corpora has involved established research corpora, such as the collections of TREC and CLEF conferences (Sheridan and Ballerini, 1996;Braschler and Schäuble, 1998). Surprisingly few studies exist on the acquisition of such corpora from the Web.…”

Section: Previous Workmentioning

confidence: 99%

Focused web crawling in the acquisition of comparable corpora

et al. 2008

View full text Add to dashboard Cite

CLIR resources, such as dictionaries and parallel corpora, are scarce for special domains. Obtaining comparable corpora automatically for such domains could be an answer to this problem. The Web, with its vast volumes of data, offers a natural source for this. We experimented with focused crawling as a means to acquire comparable corpora in the genomics domain. The acquired corpora were used to statistically translate domainspecific words. The same words were also translated using a high-quality, but non-genomics-related parallel corpus, which fared considerably worse. We also evaluated our system with standard IR experiments, combining statistical translation using the Web corpora with dictionary-based translation. The results showed improvement over pure dictionary-based translation. Therefore, mining the Web for comparable corpora seems promising.

show abstract

“…[5] The "EuroSpider" 3 systems use related methods for multilingual databases. [6,7,8] Such methods have also been investigated in the "Interspace" 4 prototype. [9,10] The main principles of this approach are discussed in section 3.2.…”

Section: Treatment Of Semantic Heterogeneitymentioning

confidence: 99%

Meta-data Extraction and Query Translation. Treatment of Semantic Heterogeneity

Strötgen¹

2002

Research and Advanced Technology for Digital Libraries

View full text Add to dashboard Cite

Abstract. The project CARMEN 1 ("Content Analysis, Retrieval and Metadata: Effective Networking") aimed among other goals at improving the expansion of searches in bibliographic databases into Internet searches. We pursued a set of different approaches to the treatment of semantic heterogeneity (meta-data extraction, query translation using statistic relations and cross-concordances). This paper describes the concepts and implementation of this approaches and the evaluation of the impact for the retrieval result.

show abstract

Multilingual Information Retrieval Based on Document Alignment Techniques

Cited by 35 publications

References 4 publications

Creating Chinese-English Comparable Corpora

Creating Chinese-English Comparable Corpora

Focused web crawling in the acquisition of comparable corpora

Meta-data Extraction and Query Translation. Treatment of Semantic Heterogeneity

Contact Info

Product

Resources

About