论文信息 - TectoMT: Highly Modular MT System with Tectogrammatics Used as Transfer Layer - 字舞流文

TectoMT: Highly Modular MT System with Tectogrammatics Used as Transfer Layer

We present a new English→Czech machine translation system combining linguistically motivated layers of language description (as defined in the Prague Dependency Treebank annotation scenario) with statistical NLP approaches.

Petr Pajas | Zdenek Zabokrtský | Jan Ptácek | Z. Žabokrtský | P. Pajas | J. Ptáček

[1] Ondrej Bojar,et al. CzEng: Czech-English Parallel Corpus release version 0.5 , 2006, Prague Bull. Math. Linguistics.

[2] Hermann Ney,et al. A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[3] John A. Carroll,et al. Robust, applied morphological generation , 2000, INLG.

[4] Arul Menezes,et al. A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora , 2001, DDMMT@ACL.

[5] Michael Collins,et al. Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[6] P. Sgall,et al. Generativní popis jazyka a česká deklinace , 1967 .

[7] Jan Hajic. Disambiguation of Rich Inflection - Computational Morphology of Czech , 2004 .

[8] Fernando Pereira,et al. Non-Projective Dependency Parsing using Spanning Tree Algorithms , 2005, HLT.

[9] Jan Hajic,et al. The Prague Dependency Treebank , 2003 .

[10] Beatrice Santorini,et al. Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[11] Thorsten Brants,et al. TnT – A Statistical Part-of-Speech Tagger , 2000, ANLP.