Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- ArticleDecember 2009
Segmenting Long Sentence Pairs for Statistical Machine Translation
IALP '09: Proceedings of the 2009 International Conference on Asian Language ProcessingPages 53–58https://doi.org/10.1109/IALP.2009.20In phrase-based statistical machine translation, the knowledge about phrase translation and phrase reordering is learned from the bilingual corpora. However, words may be poorly aligned in long sentence pairs in practice, which will then do harm to the ...
Incremental maintenance of length normalized indexes for approximate string matching
SIGMOD '09: Proceedings of the 2009 ACM SIGMOD International Conference on Management of dataPages 429–440https://doi.org/10.1145/1559845.1559891Approximate string matching is a problem that has received a lot of attention recently. Existing work on information retrieval has concentrated on a variety of similarity measures TF/IDF, BM25, HMM, etc.) specifically tailored for document retrieval ...
- ArticleAugust 2006
Using small XML elements to support relevance
SIGIR '06: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrievalPages 693–694https://doi.org/10.1145/1148170.1148321Small XML elements are often estimated relevant by the retrieval model but they are not desirable retrieval units. This paper presents a generic model that exploits the information obtained from small elements. We identify relationships between small ...
- research-articleDecember 2005
The Importance of Length Normalization for XML Retrieval
Information Retrieval (INFRE), Volume 8, Issue 4Pages 631–654https://doi.org/10.1007/s10791-005-0750-7AbstractXML retrieval is a departure from standard document retrieval in which each individual XML element, ranging from italicized words or phrases to full blown articles, is a retrievable unit. The distribution of XML element lengths is unlike what we ...
- ArticleJuly 2004
Length normalization in XML retrieval
SIGIR '04: Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrievalPages 80–87https://doi.org/10.1145/1008992.1009009XML retrieval is a departure from standard document retrieval in which each individual XML element, ranging from italicized words or phrases to full blown articles, is a potentially retrievable unit. The distribution of XML element lengths is unlike ...
