Recursive alignment block classification technique for word reordering in statistical machine translation.
Statistical machine translation (SMT) is based on alignment models which learn from bilingual corpora the word correspondences between source and target language. These models are assumed to be capable of learning reorderings. However, the difference in word order between two languages is one of the...
| Publicado en: | Language Resources & Evaluation Vol. 45; no. 2; pp. 165 - 180 |
|---|---|
| Autores principales: | , , |
| Formato: | Artículo |
| Publicado: |
Springer Nature
May2011
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=60133439&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 60133439 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: May2011 vid: 45 iid: 2 pid: 237 pub: Springer Nature artinfo: ui: 60133439 10.1007/s10579-010-9133-9 ppf: 165 ppct: 15 formats: fmt: @attributes: type: P size: 677KB tig: atl: Recursive alignment block classification technique for word reordering in statistical machine translation. aug: au: Costa-jussà, Marta Fonollosa, José Monte, Enric affil: Barcelona Media Innovation Center, Av. Diagonal 177 08018 Barcelona Spain Universitat Politècnica de Catalunya, TALP Research Center, Jordi Girona 1-3 08034 Barcelona Spain su: Machine translating Bilingualism Corpora Vocabulary Error analysis in foreign language education Learning Experiments sug: subj: Machine translating Bilingualism Corpora Vocabulary Error analysis in foreign language education Learning Experiments keyword: Automatic evaluation Statistical classification Statistical machine translation Word reordering ab: Statistical machine translation (SMT) is based on alignment models which learn from bilingual corpora the word correspondences between source and target language. These models are assumed to be capable of learning reorderings. However, the difference in word order between two languages is one of the most important sources of errors in SMT. In this paper, we show that SMT can take advantage of inductive learning in order to solve reordering problems. Given a word alignment, we identify those pairs of consecutive source blocks (sequences of words) whose translation is swapped, i.e. those blocks which, if swapped, generate a correct monotonic translation. Afterwards, we classify these pairs into groups, following recursively a co-occurrence block criterion, in order to infer reorderings. Inside the same group, we allow new internal combination in order to generalize the reorder to unseen pairs of blocks. Then, we identify the pairs of blocks in the source corpora (both training and test) which belong to the same group. We swap them and we use the modified source training corpora to realign and to build the final translation system. We have evaluated our reordering approach both in alignment and translation quality. In addition, we have used two state-of-the-art SMT systems: a Phrased-based and an Ngram-based. Experiments are reported on the EuroParl task, showing improvements almost over 1 point in the standard MT evaluation metrics (mWER and BLEU). pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Language Resources & Evaluation is a copyright of Springer, 2011. All Rights Reserved. item: Language Resources & Evaluation holder: Springer Nature dt: @attributes: year: 2011 holdings: @attributes: islocal: N |
|---|