Entropy Guided Transformation Learning (ETL) is a new machine learning strategy that combines the advantages of decision trees (DT) and Transformation Based Learning (TBL). In this work, we apply the ETL framework to four phrase chunking tasks: Portuguese noun phrase chunking, English base noun phrase chunking, English text chunking and Hindi text chunking. In all four tasks, ETL shows better r...

We present an unsupervised inference procedure for phrase-based translation models based on the minimum description length principle. In comparison to current inference techniques that rely on long pipelines of training heuristics, this procedure represents a theoretically wellfounded approach to directly infer phrase lexicons. Empirical results show that the proposed inference procedure has th...

Reordering is of essential importance for phrase based statistical machine translation (SMT). In this paper, we would like to present a new method of reordering in phrase based SMT. We inspired from (Xia and McCord, 2004) using preprocessing reordering approaches. We used shallow parsing and transformation rules to reorder the source sentence. The experiment results from English-Vietnamese pair...

In this paper, we give a description of the DCU machine translation systems submitted to the evaluation campaign of The International Workshop on Spoken Language Translation (IWSLT) 2010. We participated in the BTEC Arabic-to-English task in addition to the DIALOG task for translation between English and Chinese in both directions. We explore different extensions to Phrase-Based and Hierarchica...

This paper describes QCRI’s machine translation systems for the IWSLT 2016 evaluation campaign. We participated in the Arabic→English and English→Arabic tracks. We built both Phrase-based and Neural machine translation models, in an effort to probe whether the newly emerged NMT framework surpasses the traditional phrase-based systems in Arabic-English language pairs. We trained a very strong ph...

N-gram-based models co-exist with their phrase-based counterparts as an alternative SMT framework. Both techniques have pros and cons. While the N-gram-based framework provides a better model that captures both source and target contexts and avoids spurious phrasal segmentation, the ability to memorize and produce larger translation units gives an edge to the phrase-based systems during decodin...