Open AccessProceedings Article
Head-Driven Hierarchical Phrase-based Translation
Junhui Li,Zhaopeng Tu,Guodong Zhou,Josef van Genabith +3 more
- pp 33-37
Reads0
Chats0
TLDR
An extension of Chiang's hierarchical phrase-based (HPB) model is presented, called Head-Driven HPB (HD-HPB), which incorporates head information in translation rules to better capture syntax-driven information, as well as improved reordering between any two neighboring non-terminals at any stage of a derivation to explore a larger reordering search space.Abstract:
This paper presents an extension of Chiang's hierarchical phrase-based (HPB) model, called Head-Driven HPB (HD-HPB), which incorporates head information in translation rules to better capture syntax-driven information, as well as improved reordering between any two neighboring non-terminals at any stage of a derivation to explore a larger reordering search space. Experiments on Chinese-English translation on four NIST MT test sets show that the HD-HPB model significantly outperforms Chiang's model with average gains of 1.91 points absolute in BLEU.read more
Citations
More filters
Proceedings ArticleDOI
Dependency-Based Bilingual Language Models for Reordering in Statistical Machine Translation
Ekaterina Garmash,Christof Monz +1 more
TL;DR: This paper presents a novel approach to improve reordering in phrase-based machine translation by using richer, syntactic representations of units of bilingual language models (BiLMs) with significant improvements in BLEU and TER.
Proceedings Article
A Machine Learning Method to Distinguish Machine Translation from Human Translation
Yitong Li,Rui Wang,Hai Zhao +2 more
TL;DR: This paper introduces a machine learning approach to distinguish machine translation texts from human texts in the sentence level automatically and presents an indicator to measure how much a sentence generated by a machine translation system looks like a real human translation.
Proceedings ArticleDOI
Do Contexts Help in Phrase-Based, Statistical Source Code Migration?
TL;DR: The empirical results show a good direction of using SMT with semantic features at different levels of abstraction to improve its accuracy, and as individual features added to the baseline SMT model, token association and data dependencies contribute much with highest relative improvement in semantic correctness.
Proceedings ArticleDOI
Dependency Graph-to-String Translation
Liangyou Li,Andy Way,Qun Liu +2 more
TL;DR: Large-scale experiments show that the proposed synchronous graph-to-string grammar for statistical machine translation is significantly better than the state-of-the-art hierarchical phrase-based (HPB) model and a recently improved dependency tree- to-string model on BLEU, METEOR and TER scores.
Proceedings ArticleDOI
Learning Semantic Representations for Nonterminals in Hierarchical Phrase-Based Translation
Xing Wang,Deyi Xiong,Min Zhang +2 more
TL;DR: A framework to refine nonterminals in hierarchical translation rules with real-valued semantic representations is proposed and results show that the proposed model significantly improves translation quality on NIST test sets.
References
More filters
Proceedings ArticleDOI
Statistical phrase-based translation
TL;DR: The empirical results 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 translation.
Proceedings ArticleDOI
Minimum Error Rate Training in Statistical Machine Translation
TL;DR: It is shown that significantly better results can often be obtained if the final evaluation criterion is taken directly into account as part of the training procedure.
Journal ArticleDOI
Head-Driven Statistical Models for Natural Language Parsing
TL;DR: Three statistical models for natural language parsing are described, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree.
Proceedings Article
A maximum-entropy-inspired parser
TL;DR: A new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less and 89.5% when trained and tested on the previously established sections of the Wall Street Journal treebank is presented.
Proceedings Article
Statistical Significance Tests for Machine Translation Evaluation.
TL;DR: The authors describe bootstrap resampling methods to compute statistical significance of test results, and validate them on the concrete example of the BLEU score for small test sizes of only 300 sentences, which may give us assurances that test result differences are real.