title | authors | fieldsOfStudy | meta_key | numCitedBy | reading_status | ref_count | tags | urls | venue | year | |||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Statistical Phrase-Based Translation |
|
|
2003-statistical-phrase-based-translation |
3757 |
TBD |
21 |
|
NAACL |
2003 |
We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models out-perform word-based models. Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translations. Surprisingly, learning phrases longer than three words and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance. Learning only syntactically motivated phrases degrades the performance of our systems.
- Improved Alignment Models for Statistical Machine Translation
- Improved Statistical Alignment Models
- The Mathematics of Statistical Machine Translation - Parameter Estimation
- A Syntax-based Statistical Translation Model
- A Phrase-Based, Joint Probability Model for Statistical Machine Translation
- An Efficient A* Search Algorithm for Statistical Machine Translation
- Three Generative, Lexicalised Models for Statistical Parsing
- Robust German Noun Chunking With a Probabilistic Context-Free Grammar
- Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora
- Bleu - a Method for Automatic Evaluation of Machine Translation
- Statistical methods for speech recognition
- Statistical language modeling using the CMU-cambridge toolkit
- The mathematics of statistical machine translation
- Application of translation knowledge acquired by hierarchical phrase alignment for pattern-based MT.
- Fast Decoding and Optimal Decoding for Machine Translation