Baskaran Sankaran

Coverage Embedding Models for Neural Machine Translation.

In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT. For each source word, our model starts with a full coverage embedding vector to track the coverage status, and then keeps updating it with neural networks as the translation goes. Experiments on the large-scale Chinese-to-English task show that our enhanced model improves the translation quality significantly on various test sets over the strong large vocabulary NMT system.

Zero-Resource Translation with Multi-Lingual Neural Machine Translation

In this paper, we propose a novel finetuning algorithm for the recently introduced multi-way, mulitlingual neural machine translate that enables zero-resource machine translation. When used together with novel many-to-one translation strategies, we empirically show that this finetuning algorithm allows the multi-way, multilingual model to translate a zero-resource language pair (1) as well as a single-pair neural translation model trained with up to 1M direct parallel sentences of the same language pair and (2) better than pivot-based translation strategy, while keeping only one additional copy of attention-related parameters.

Kriya - An end-to-end Hierarchical Phrase-based MT System

Kriya - An end-to-end Hierarchical Phrase-based MT System This paper describes Kriya - a new statistical machine translation (SMT) system that uses hierarchical phrases, which were first introduced in the Hiero machine translation system (Chiang, 2007). Kriya supports both a grammar extraction module for synchronous context-free grammars (SCFGs) and a CKY-based decoder. There are several re-implementations of Hiero in the machine translation community, but Kriya offers the following novel contributions: (a) Grammar extraction in Kriya supports extraction of the full set of Hiero-style SCFG rules but also supports the extraction of several types of compact rule sets which leads to faster decoding for different language pairs without compromising the BLEU scores. Kriya currently supports extraction of compact SCFGs such as grammars with one non-terminal and grammar pruning based on certain rule patterns, and (b) The Kriya decoder offers some unique improvements in the implementation of cube-pruning, such as increasing diversity in the target language n-best output and novel methods for language model (LM) integration. The Kriya decoder can take advantage of parallelization using a networked cluster. Kriya supports both KENLM and SRILM for language model queries. This paper also provides several experimental results which demonstrate that the translation quality of Kriya compares favourably to the Moses (Koehn et al., 2007) phrase-based system in several language pairs while showing a substantial improvement for Chinese-English similar to Chiang (2007). We also quantify the model sizes for phrase-based and Hiero-style systems and also present experiments comparing variants of Hiero models.

n-best reranking for the efficient integration of word sense disambiguation and statistical machine translation

Although it has been always thought that Word Sense Disambiguation (WSD) can be useful for Machine Translation, only recently efforts have been made towards integrating both tasks to prove that this assumption is valid, particularly for Statistical Machine Translation (SMT). While different approaches have been proposed and results started to converge in a positive way, it is not clear yet how these applications should be integrated to allow the strengths of both to be exploited. This paper aims to contribute to the recent investigation on the usefulness of WSD for SMT by using n-best reranking to efficiently integrate WSD with SMT. This allows using rich contextual WSD features, which is otherwise not done in current SMT systems. Experiments with English-Portuguese translation in a syntactically motivated phrase-based SMT system and both symbolic and probabilistic WSD models showed significant improvements in BLEU scores.

Domain adaptation techniques for machine translation and their evaluation in a real-world setting

Statistical Machine Translation (SMT) is currently used in real-time and commercial settings to quickly produce initial translations for a document which can later be edited by a human. The SMT models specialized for one domain often perform poorly when applied to other domains. The typical assumption that both training and testing data are drawn from the same distribution no longer applies. This paper evaluates domain adaptation techniques for SMT systems in the context of end-user feedback in a real world application. We present our experiments using two adaptive techniques, one relying on log-linear models and the other using mixture models. We describe our experimental results on legal and government data, and present the human evaluation effort for post-editing in addition to traditional automated scoring techniques (BLEU scores). The human effort is based primarily on the amount of time and number of edits required by a professional post-editor to improve the quality of machine-generated translations to meet industry standards. The experimental results in this paper show that the domain adaptation techniques can yield a significant increase in BLEU score (up to four points) and a significant reduction in post-editing time of about one second per word.

Incremental translation using hierarchichal phrase-based translation system

Hierarchical phrase-based machine translation [1] (Hiero) is a prominent approach for Statistical Machine Translation usually comparable to or better than conventional phrase-based systems. But Hiero typically uses the CKY decoding algorithm which requires the entire input sentence before decoding begins, as it produces the translation in a bottom-up fashion. Left-to-right (LR) decoding [2] is a promising decoding algorithm for Hiero that produces the output translation in left to right order. In this paper we focus on simultaneous translation using the Hiero translation framework. In simultaneous translation, translations are generated incrementally as source language speech input is processed. We propose a novel approach for incremental translation by integrating segmentation and decoding in LR-Hiero. We compare two incremental decoding algorithms for LR-Hiero and present translation quality scores (BLEU) and the latency of generating translations for both decoders on audio lectures from the TED collection.