Advances in Fully-Automatic and Interactive Phrase-Based Statistical Machine Translation

Martínez, Daniel Ortiz

doi:10.4995/thesis/10251/12127

Cited by 12 publications

(13 citation statements)

References 122 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of user trials (Macklovitch, 2006) showed gains in productivity (measured in number of words translated per hour) of around 15-20%. A number of projects (Koehn, 2009;Ortiz-Martínez, 2011;Alabau et al, 2010Alabau et al, , 2013 have recently continued the research where TransType2 left it off. As regards tools, both Caitra (Koehn, 2009) and the CASMACAT Workbench (Alabau et al, 2013) are web applications with an underlying SMT-based ITP system.…”

Section: Related Workmentioning

confidence: 99%

An Open-Source Web-Based Tool for Resource-Agnostic Interactive Translation Prediction

Torregrosa¹,

Forcada²,

Pérez-Ortiz³

2014

The Prague Bulletin of Mathematical Linguistics

View full text Add to dashboard Cite

We present a web-based open-source tool for interactive translation prediction (ITP) and describe its underlying architecture. ITP systems assist human translators by making context-based computer-generated suggestions as they type. Most of the ITP systems in literature are strongly coupled with a statistical machine translation system that is conveniently adapted to provide the suggestions. Our system, however, follows a resource-agnostic approach and suggestions are obtained from any unmodified black-box bilingual resource. This paper reviews our ITP method and describes the architecture of Forecat, a web tool, partly based on the recent technology of web components, that eases the use of our ITP approach in any web application requiring this kind of translation assistance. We also evaluate the performance of our method when using an unmodified Moses-based statistical machine translation system as the bilingual resource.

show abstract

Section: Related Workmentioning

confidence: 99%

An Open-Source Web-Based Tool for Resource-Agnostic Interactive Translation Prediction

Torregrosa¹,

Forcada²,

Pérez-Ortiz³

2014

The Prague Bulletin of Mathematical Linguistics

View full text Add to dashboard Cite

show abstract

“…For this purpose, a log-linear SMT model where all its score components are incrementally updateable is defined. The implemented proposal uses the incremental version of the EM algorithm (Neal and Hinton, 1998) and the specific details can be found in (Ortiz-Martínez et al, 2010;Ortiz-Martínez, 2011). Empirical results obtained with THOT and reported in (Ortiz-Martínez et al, 2010;OrtizMartínez, 2011) show that incremental learning allows to significantly reduce the user effort in IMT tasks with respect to that required by a conventional IMT system.…”

Section: Incremental Learning For Smtmentioning

confidence: 99%

“…Such a formalisation was introduced in (Ortiz-Martínez, 2011) and it generates the suffixes required in IMT by partially aligning a prefix of the target hypotheses with the user prefix. Once the partial alignment is determined, the suffix is given by the unaligned portion of the target sentence.…”

Section: Interactive Machine Translationmentioning

confidence: 99%

The New Thot Toolkit for Fully-Automatic and Interactive Statistical Machine Translation

Ortiz-Martínez

Casacuberta

2014

Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguisti

View full text Add to dashboard Cite

We present the new THOT toolkit for fullyautomatic and interactive statistical machine translation (SMT). Initial public versions of THOT date back to 2005 and did only include estimation of phrase-based models. By contrast, the new version offers several new features that had not been previously incorporated. The key innovations provided by the toolkit are computeraided translation, including post-editing and interactive SMT, incremental learning and robust generation of alignments at phrase level. In addition to this, the toolkit also provides standard SMT features such as fully-automatic translation, scalable and parallel algorithms for model training, client-server implementation of the translation functionality, etc. The toolkit can be compiled in Unix-like and Windows platforms and it is released under the GNU Lesser General Public License (LGPL).

show abstract

“…If the user feedback leads to a specific state in the word graph that has no path to any final state, the system fails. An error correction method is used to overcome this issue (Barrachina et al, 2009;Ortiz-Martínez, 2011), but it may lead to successive wrong hypotheses. NMT systems handle the out-of-vocabulary problem by applying splitting unknown words, using BPE.…”

Section: Prefix-based Interactionmentioning

confidence: 99%

Interactivity, Adaptation and Multimodality in Neural Sequence-to-sequence Learning

Abril¹

View full text Add to dashboard Cite

Chapter 1 frames the scope of this thesis, introducing the pattern recognition field and, more specifically, the MT field. It reviews the different historical approaches devised to tackle this problem. Moreover, it sets the experimental framework followed in this thesis and the main scientific objectives. Chapter 2 describes the mathematical model that represents the core of the thesis: neural networks. It addresses the parameter estimation process, describes different neural architectures and a number of techniques used along the thesis to improve the generalization capability of the model. Chapter 3 introduces the neural machine translation technology, describing the most common architectures and decoding process. Moreover, it reviews different aspects relating the NMT field that nowadays receive the attention of the research community. It also compares NMT in the different translation tasks that will be tackled in the thesis. Chapter 4 introduces the interactive-predictive pattern recognition field, that aims to minimize the effort spent by the user while supervising an automatic system. It proposes the application of this theoretical framework to the neural technology, introducing alternative interaction protocols. After that, these interactivepredictive neural systems are evaluated. Chapter 5 describes the adaptation of NMT systems via online learning techniques. After receiving a corrected sample, the system can be updated to include this new knowledge. Here are described the methods to perform this adaptation and introduces two novel alternatives. In addition, an active learning framework for neural systems is proposed, useful for a situation that requires the translation of large amounts of data. All these scenarios are thoroughly evaluated in a variety of conditions, including a user evaluation involving professional post-editors. Chapter 6 departs from the MT problem to tackle different multimodal sequenceto-sequence tasks. More precisely, it is focused on the generation textual descriptions of videos. These techniques are also applied to the captioning of daily events, captured with an egocentric camera. Finally, the interactive-predictive framework described in Chapter 4 is applied to these multimodal systems. Chapter 7 draws the main conclusions of the thesis, describing the scientific contributions and publications derived from it and traces several lines of future research. These chapters are complemented by two appendices. Appendix A describes NMT-Keras, an open-source library developed to build neural models, that has been used to carry out most of the experiments described in the thesis. In Appendix B we provide the results of a survey carried out in the scope of Chapter 5.

show abstract

Advances in Fully-Automatic and Interactive Phrase-Based Statistical Machine Translation

Cited by 12 publications

References 122 publications

An Open-Source Web-Based Tool for Resource-Agnostic Interactive Translation Prediction

An Open-Source Web-Based Tool for Resource-Agnostic Interactive Translation Prediction

The New Thot Toolkit for Fully-Automatic and Interactive Statistical Machine Translation

Interactivity, Adaptation and Multimodality in Neural Sequence-to-sequence Learning

Contact Info

Product

Resources

About