Undirected Machine Translation with Discriminative Reinforcement Learning

Gesmundo, Andréa; Henderson, James

doi:10.3115/v1/e14-1002

Cited by 2 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This idea inspired and is closely related to our potential BLEU, except that in our case, computing an admissible heuristic is too costly, so our potential BLEU is more like an average potential. Gesmundo and Henderson (2014) also consider the rankings between partial translation pairs as well. However, they evaluate a partial translation through extending it to a complete translation by re-decoding, and thus they need many passes of decoding for many partial translations, while ours only need one pass of decoding for all partial translations and thus is much more efficient.…”

Section: Related Workmentioning

confidence: 99%

Search-Aware Tuning for Machine Translation

Liu¹,

Huang²

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Parameter tuning is an important problem in statistical machine translation, but surprisingly, most existing methods such as MERT, MIRA and PRO are agnostic about search, while search errors could severely degrade translation quality. We propose a searchaware framework to promote promising partial translations, preventing them from being pruned. To do so we develop two metrics to evaluate partial derivations. Our technique can be applied to all of the three above-mentioned tuning methods, and extensive experiments on Chinese-to-English and English-to-Chinese translation show up to +2.6 BLEU gains over search-agnostic baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

Search-Aware Tuning for Machine Translation

Liu¹,

Huang²

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…This is the essential observation behind so-called cube pruning and cube growing approaches (Gesmundo and Henderson, 2010; Huang and Chiang, 2005) for enumerating k best derivations.…”

Section: Methodsmentioning

confidence: 99%

“…Algorithm 1 formalizes this process. The process can be made even more efficient using the faster cube pruning approach introduced by Gesmundo and Henderson (2010).…”

Section: Methodsmentioning

confidence: 99%

Predicting protein interactions via parsimonious network history inference

Patro¹,

Kingsford²

2013

Bioinformatics

View full text Add to dashboard Cite

Motivation: Reconstruction of the network-level evolutionary history of protein–protein interactions provides a principled way to relate interactions in several present-day networks. Here, we present a general framework for inferring such histories and demonstrate how it can be used to determine what interactions existed in the ancestral networks, which present-day interactions we might expect to exist based on evolutionary evidence and what information extant networks contain about the order of ancestral protein duplications.Results: Our framework characterizes the space of likely parsimonious network histories. It results in a structure that can be used to find probabilities for a number of events associated with the histories. The framework is based on a directed hypergraph formulation of dynamic programming that we extend to enumerate many optimal and near-optimal solutions. The algorithm is applied to reconstructing ancestral interactions among bZIP transcription factors, imputing missing present-day interactions among the bZIPs and among proteins from five herpes viruses, and determining relative protein duplication order in the bZIP family. Our approach more accurately reconstructs ancestral interactions than existing approaches. In cross-validation tests, we find that our approach ranks the majority of the left-out present-day interactions among the top 2 and 17% of possible edges for the bZIP and herpes networks, respectively, making it a competitive approach for edge imputation. It also estimates relative bZIP protein duplication orders, using only interaction data and phylogenetic tree topology, which are significantly correlated with sequence-based estimates.Availability: The algorithm is implemented in C++, is open source and is available at http://www.cs.cmu.edu/ckingsf/software/parana2.Contact: robp@cs.cmu.edu or carlk@cs.cmu.eduSupplementary information: Supplementary data are available at Bioinformatics online.

show abstract

Undirected Machine Translation with Discriminative Reinforcement Learning

Cited by 2 publications

References 23 publications

Search-Aware Tuning for Machine Translation

Search-Aware Tuning for Machine Translation

Predicting protein interactions via parsimonious network history inference

Contact Info

Product

Resources

About