Sökning: onr:"swepub:oai:DiVA.org:liu-64329" >
A knowledge-lite ap...
-
Ahrenberg, Lars,1948-Linköpings universitet,NLPLAB - Laboratoriet för databehandling av naturligt språk,Tekniska högskolan,NLPLab, HCS
(författare)
A knowledge-lite approach to word alignment
- Artikel/kapitelEngelska2000
Förlag, utgivningsår, omfång ...
-
Dordrecht, The Netherlands :Kluwer Academic Publishers,2000
-
printrdacarrier
Nummerbeteckningar
-
LIBRIS-ID:oai:DiVA.org:liu-64329
-
https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-64329URI
-
https://doi.org/10.1007/978-94-017-2535-4_5DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:vet swepub-contenttype
-
Ämneskategori:kap swepub-publicationtype
Anmärkningar
-
The most promising approach to word alignment is to combine statistical methods with non-statistical information sources. Some of the proposed non-statistical sources, including bilingual dictionaries, POS-taggers and lemmatizers, rely on considerable linguistic knowledge, while other knowledge-lite sources such as cognate heuristics and word order heuristics can be implemented relatively easy. While knowledge-heavy sources might be expected to give better performance, knowledge-lite systems are easier to port to new language pairs and text types, and they can give sufficiently good results for many purposes, e.g. if the output is to be used by a human user for the creation of a complete word-aligned bitext. In this paper we describe the current status of the Linköping Word Aligner (LWA), which combines the use of statistical measures of co-occurrence with four knowledge-lite modules for (i)) word categorization, (ii) morphological variation, (iii) word order, and (iv) phrase recognition. We demonstrate the portability of the system (from English-Swedish texts to French-English texts) and present results for these two language-pairs. Finally, we will report observations from an error analysis of system output, and identify the major strengths and weaknesses of the system.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Merkel, MagnusLinköpings universitet,NLPLAB - Laboratoriet för databehandling av naturligt språk,Tekniska högskolan,NLPLab, IDA(Swepub:liu)magme91
(författare)
-
Linköpings universitetNLPLAB - Laboratoriet för databehandling av naturligt språk
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:Parallel Text ProcessingDordrecht, The Netherlands : Kluwer Academic Publishers, s. 97-11697890481555529789401725354
Internetlänk
Hitta via bibliotek
Till lärosätets databas