Search

This paper gives the system description of the neural probabilistic language modeling (NPLM) team of Dublin City University for our participation in the system combination task in the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT (ML4HMT-12). We used the information obtained by NPLM as meta information to the system combination module. For the Spanish-English data, our paraphrasing approach achieved 25.81 BLEU points, which lost 0.19 BLEU points absolute compared to the standard confusion network-based system combination. We note that our current usage of NPLM is very limited due to the difficulty in combining NPLM and system combination.

This paper provides the system description of the IHMM team of Dublin City University for our participation in the system combination task in the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT (ML4HMT-12). Our work is based on a confusion network-based approach to system combination. We propose a new method to build a confusion network for this: (1) incorporate extra alignment information extracted from given meta data, treating them as sure alignments, into the results from IHMM, and (2) decode together with this information. We also heuristically set one of the system outputs as the default backbone. Our results show that this backbone, which is the RBMT system output, achieves an 0.11% improvement in BLEU over the backbone chosen by TER, while the extra information we added in the decoding part does not improve the results.

We describe the second edition of the ML4HMT shared task which challenges participants to create hybrid translations from the translation output of several individual MT systems. We provide an overview of the shared task and the data made available to participants before briefly describing the individual systems. We report on the results using automatic evaluation metrics and conclude with a summary of ML4HMT-12 and an outlook to future work.

This paper gives the system description of the domain adaptation team of Dublin City University for our participation in the system combination task in the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT (ML4HMT-12). We used the results of unsupervised document classification as meta information to the system combination module. For the Spanish-English data, our strategy achieved 26.33 BLEU points, 0.33 BLEU points absolute improvement over the standard confusion-network-based system combination. This was the best score in terms of BLEU among six participants in ML4HMT-12.

This paper provides the system description of the Dublin City University system combination module for our participation in the system combination task in the Second Workshop on Applying Machine Learning Techniques to Optimize the Division of Labour in Hybrid MT (ML4HMT- 12). We incorporated a sentence-level quality score, obtained by sentence-level Quality Estimation (QE), as meta information guiding system combination. Instead of using BLEU or (minimum average) TER, we select a backbone for the confusion network using the estimated quality score. For the Spanish-English data, our strategy improved 0.89 BLEU points absolute compared to the best single score and 0.20 BLEU points absolute compared to the standard system combination strategy

This thesis discusses how to incorporate linguistic knowledge into an SMT system. Although one important category of linguistic knowledge is that obtained by a constituent / dependency parser, a POS / super tagger, and a morphological analyser, linguistic knowledge here includes larger domains than this: Multi-Word Expressions, Out-Of-Vocabulary words, paraphrases, lexical semantics (or non-literal translations), named-entities, coreferences, and transliterations. The first discussion is about word alignment where we propose a MWE-sensitive word aligner. The second discussion is about the smoothing methods for a language model and a translation model where we propose a hierarchical Pitman-Yor process-based smoothing method. The common grounds for these discussion are the examination of three exceptional cases from real-world data: the presence of noise, the availability of prior knowledge, and the problem of underfitting. Notable characteristics of this design are the careful usage of (Bayesian) priors in order that it can capture both frequent and linguistically important phenomena. This can be considered to provide one example to solve the problems of statistical models which often aim to learn from frequent examples only, and often overlook less frequent but linguistically important phenomena.

This paper gives the system description of the Dublin City University Machine Translation system MaTrEx for our participation in the translation subtask in the NTCIR-8 Patent Translation Task under under the team ID of DCUMT. Four techniques are deployed in our systems: supertagged PB-SMT, context informed PB-SMT, noise reduction, and system combination. For EN-JP, our system stood second in terms of BLEU reference score among six participants.

Word alignment is to estimate a lexical translation probability p(e|f), or to estimate the correspondence g(e, f) where a function g outputs either 0 or 1, between a source word f and a target word e for given bilingual sentences. In practice, this formulation does not consider the existence of ‘noise’ (or outlier) which may cause problems depending on the corpus. N-to-m mapping objects, such as paraphrases, non-literal translations, and multiword expressions, may appear as both noise and also as valid training data. From this perspective, this paper tries to answer the following two questions: 1) how to detect stable patterns where noise seems legitimate, and 2) how to reduce such noise, where applicable, by supplying extra information as prior knowledge to a word aligner.