On integrating a language model into neural machine translation

Date

2017-09-01

Author

Gulcehre, Caglar
Firat, Orhan
Xu, Kelvin
Cho, Kyunghyun
Bengio, Yoshua

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

222
views

0
downloads

Recent advances in end-to-end neural machine translation models have achieved promising results on high-resource language pairs such as En -> Fr and En -> De. One of the major factor behind these successes is the availability of high quality parallel corpora. We explore two strategies on leveraging abundant amount of monolingual data for neural machine translation. We observe improvements by both combining scores from neural language model trained only on target monolingual data with neural machine translation model and fusing hidden-states of these two models. We obtain up to 2 BLEU improvement over hierarchical and phrase-based baseline on low-resource language pair, Turkish -> English. Our method was initially motivated towards tasks with less parallel data, but we also show that it extends to high resource languages such as Cs -> En and De -> En translation tasks, where we obtain 0.39 and 0.47 BLEU improvements over the neural machine translation baselines, respectively.

Subject Keywords

Theoretical Computer Science, Human-Computer Interaction, Software

URI

https://hdl.handle.net/11511/68185

Journal

COMPUTER SPEECH AND LANGUAGE

DOI

https://doi.org/10.1016/j.csl.2017.01.014

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Coupling speech recognition and rule-based machine translation Köprü, Selçuk; Yazıcı, Adnan; Department of Computer Engineering (2008) The objective of this thesis was to study the coupling of automatic speech recognition (ASR) systems with rule-based machine translation (MT) systems. In this thesis, a unique approach to integrating ASR with MT for speech translation (ST) tasks was proposed. The proposed approach is unique, essentially because it includes the rst rule-based MT system that can process speech data in a word graph format. Compared to other rule-based MT systems, our system processes both a word graph and a stream of words. Th...
A clustering method for the problem of protein subcellular localization Bezek, Perit; Atalay, Mehmet Volkan; Department of Computer Engineering (2006) In this study, the focus is on predicting the subcellular localization of a protein, since subcellular localization is helpful in understanding a protein’s functions. Function of a protein may be estimated from its sequence. Motifs or conserved subsequences are strong indicators of function. In a given sample set of protein sequences known to perform the same function, a certain subsequence or group of subsequences should be common; that is, occurrence (frequency) of common subsequences should be high. Our ...
Analysis of extended feature models with constraint programming Karataş, Ahmet Serkan; Oğuztüzün, Mehmet Halit S.; Department of Computer Engineering (2010) In this dissertation we lay the groundwork of automated analysis of extended feature models with constraint programming. Among different proposals, feature modeling has proven to be very effective for modeling and managing variability in Software Product Lines. However, industrial experiences showed that feature models often grow too large with hundreds of features and complex cross-tree relationships, which necessitates automated analysis support. To address this issue we present a mapping from extended fe...
Natural language query processing in ontology based multimedia databases Aygül, Filiz Alaca; Çiçekli, Fehime Nihan; Department of Computer Engineering (2010) In this thesis a natural language query interface is developed for semantic and spatio-temporal querying of MPEG-7 based domain ontologies. The underlying ontology is created by attaching domain ontologies to the core Rhizomik MPEG-7 ontology. The user can pose concept, complex concept (objects connected with an “AND” or “OR” connector), spatial (left, right . . . ), temporal (before, after, at least 10 minutes before, 5 minutes after . . . ), object trajectory and directional trajectory (east, west, southe...
Improvement of corpus-based semantic word similarity using vector space model Esin, Yunus Emre; Alpaslan, Ferda Nur; Department of Computer Engineering (2009) This study presents a new approach for finding semantically similar words from corpora using window based context methods. Previous studies mainly concentrate on either finding new combination of distance-weight measurement methods or proposing new context methods. The main di fference of this new approach is that this study reprocesses the outputs of the existing methods to update the representation of related word vectors used for measuring semantic distance between words, to improve the results further. ...

Citation Formats

C. Gulcehre, O. Firat, K. Xu, K. Cho, and Y. Bengio, “On integrating a language model into neural machine translation,” COMPUTER SPEECH AND LANGUAGE, pp. 137–148, 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/68185.