• Corpus ID: 5498777

Bilingual distributed phrase representations for statistical machin translation

  title={Bilingual distributed phrase representations for statistical machin translation},
  author={Chris Hokamp and Qun Liu},
  booktitle={Machine Translation Summit},
Phrase–based machine translation (PBMT) relies upon the phrase-table as the main resource for bilingual knowledge at decoding time. A phrase table in its basic form includes aligned phrases along with four probabilities indicating aspects of the co-occurrence statistics for each phrase pair. In this paper we add a new semantic similarity score as a statistical feature to enrich the phrase table. The new feature is inferred from a bilingual corpus by a neural network (NN), and estimates the… 

Figures and Tables from this paper

Enriching Phrase Tables for Statistical Machine Translation Using Mixed Embeddings

This work proposes new scores generated by a Convolutional Neural Network which indicate the semantic relatedness of phrase pairs, and evaluates the model in different experimental settings with different language pairs.

Research of Uyghur-Chinese Machine Translation System Combination Based on Semantic Information

A system combination method which was generated multiple new systems from a single Statistical Machine Translation (SMT) engine and combined together based on a bilingual phrase semantic representation model.

Neural Pre-Translation for Hybrid Machine Translation

A cascaded hybrid framework to combine NMT and PB-SMT to improve translation quality is proposed and it is shown that the proposed framework can significantly improve performance by 2.38 BLEU points and 4.22 BLEu points, respectively, compared to the baseline NMT system.

Improving Phrase-Based SMT Using Cross-Granularity Embedding Similarity

Six new features which express the semantic relatedness of bilingual phrases are defined which are inferred from a bilingual corpus by a neural network (NN) and evaluated on the English–Farsi and English–Czech pairs.



Learning Semantic Representations for the Phrase Translation Model

The results show that the new semantic-based phrase translation model significantly improves the performance of a state-of-the-art phrase-based statistical machine translation sys-tem, leading to a gain of 0.7-1.0 BLEU points.

Exploiting Similarities among Languages for Machine Translation

This method can translate missing word and phrase entries by learning language structures based on large monolingual data and mapping between languages from small bilingual data and uses distributed representation of words and learns a linear mapping between vector spaces of languages.

A Semantic Feature for Statistical Machine Translation

A semantic feature for statistical machine translation, based on Latent Semantic Indexing, is proposed and evaluated, which aims at favoring those translation units that were extracted from training sentences that are semantically related to the current input sentence being translated.

Learning Translation Models from Monolingual Continuous Representations

This work proposes a much faster and simpler method that directly hallucinates translation rules for infrequent phrases based on phrases with similar continuous representations for which a translation is known, and investigates approximated nearest neighbor search with redundant bit vectors which is three times faster and significantly more accurate than locality sensitive hashing.

Recurrent Continuous Translation Models

We introduce a class of probabilistic continuous translation models called Recurrent Continuous Translation Models that are purely based on continuous representations for words, phrases and sentences

Joint word2vec Networks for Bilingual Semantic Representations

The word2vec framework is extended to capture meaning across languages and can be used to enrich lexicons of under-resourced languages, to identify ambiguities, and to perform clustering and classification.

Neural Machine Translation by Jointly Learning to Align and Translate

It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.

A vector-space dynamic feature for phrase-based statistical machine translation

A novel dynamic feature function is proposed and evaluated for log-linear model combinations in phrase-based statistical machine translation that aims at improving translation unit selection at decoding time by incorporating context information from the source language.

Improving Word Representations via Global Context and Multiple Word Prototypes

A new neural network architecture is presented which learns word embeddings that better capture the semantics of words by incorporating both local and global document context, and accounts for homonymy and polysemy by learning multiple embedDings per word.

Word’s Vector Representations meet Machine Translation

A bilingual extension of the CBOW architecture is proposed to handle ambiguous words for which the different senses are conflated in the monolingual setup to improve consistency and coherence of Machine Translation.