Given Bilingual Terminology in Statistical Machine Translation: MWE-Sensitve Word Alignment and Hierarchical Pitman-Yor Process-Based Translation Model Smoothing
Explore this paper's citation graph
Summary
This paper considers a scenario when the authors are given almost perfect knowledge about bilingual terminology in terms of a test corpus in Statistical Machine Translation (SMT), and introduces a Multi-Word Expression-sensitive (MWE-sensitive) word aligner and a hierarchical Pitman-Yor process-based translation model smoothing.
- Type
- article
- Published
- 2011-03-20
- Cited by
- 9
- References
- 28
- OpenAlex
- https://openalex.org/W10287945
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:6470513
Keywords
Terminology, Computer science, Natural language processing, Artificial intelligence, Machine translation
References
- Gap Between Theory and Practice: Noise Sensitive Word Alignment in Machine Translation
- Multi-Word Expression-Sensitive Word Alignment
- SRILM - an extensible language modeling toolkit
- The Mathematics of Statistical Machine Translation: Parameter Estimation
- Lexical Transfer Using a Vector-Space Model
- Exchangeable and partially exchangeable random partitions
- Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling
- Factored Translation Models
- Phrasetable Smoothing for Statistical Machine Translation
- Contextual Dependencies in Unsupervised Word Segmentation
- An Algorithm for Finding Noun Phrase Correspondences in Bilingual Corpora
- Moses: Open Source Toolkit for Statistical Machine Translation
- Bayesian Unsupervised Word Segmentation with Nested Pitman-Yor Language Modeling
- Improved Statistical Machine Translation Using Paraphrases
- Minimum Error Rate Training in Statistical Machine Translation
- A Hierarchical Phrase-Based Model for Statistical Machine Translation
- Statistical Phrase-Based Translation
- A Hierarchical Bayesian Language Model Based On Pitman-Yor Processes
- A Systematic Comparison of Various Statistical Alignment Models
- Fast Methods for Kernel-Based Text Analysis
Cited by
- Sentence-Level Quality Estimation for MT System Combination
- Topic Modeling-based Domain Adaptation for System Combination
- Annotated Corpora for Word Alignment between Japanese and English and its Evaluation with MAP-based Word Aligner
- Joint Space Neural Probabilistic Language Model for Statistical Machine Translation
- Neural Probabilistic Language Model for System Combination
- A Deep Analysis of the Impact of Multiword Expressions and Named Entities on Chinese-English Machine Translations
- DCU Confusion Network-based System Combination for ML 4 HMT
- DCU Confusion Network-based System Combination for ML 4 HMT
- Minimum Bayes Risk Decoding with Enlarged Hypothesis Space in System Combination
Related papers
- Recursive alignment block classification technique for word reordering in statistical machine translation
- A Markov Model of Machine Translation using Non-parametric Bayesian Inference
- Phrase Translation Extraction Based on HMM
- Distortion Models for Statistical Machine Translation
- Multi-Word Expression-Sensitive Word Alignment
- Improving Statistical Machine Translation with Word Class Models
- Learning Bilingual Projections of Embeddings for Vocabulary Expansion in Machine Translation
- A word-to-phrase statistical translation model
- Hierarchical Phrase-Based Translation