Technology for Interactive MT

by Spence Green
3 Minute Read

This article describes the technology behind Lilt’s interactive translation suggestions. The details were first published in an academic conference paper, Models and Inference for Prefix-Constrained Machine Translation.

Machine translation systems can translate whole sentences or documents, but they can also be used to finish translations that were started by a person — a form of autocomplete at the sentence level. In the computational linguistics literature, predicting the rest of a sentence is called prefix-constrainedmachine translation. The prefix of a sentence is the portion authored by a translator. A suffix is suggested by the machine to complete the translation. These suggestions are proposed interactively to translators after each word they type. Translators can accept all or part of the proposed suffix with a single keystroke, saving time by automating the most predictable parts of the translation process.

null
In cooperation with Stanford University’s Minh-Thang Luong, Lilt’s research department recently published several new scientific contributions to the field of prefix-constrained machine translation.at the 54th Annual Meeting of the Association for Computational Linguistics in Berlin. In addition to extending a neural machine translation model to perform prefix-constrained translation for the first time in the literature, the paper describes three improvements to the widely used statistical phrase-based paradigm: new ways of measuring suffix accuracy, new machine learning techniques, and new suggestion algorithms. The paper describes how each of these innovations improves the suggestion quality of an interactive translation system in large-scale English-German experiments. The methods described in the paper are used in all production systems deployed by Lilt.

In an interactive setting, the first words of the suggested suffix are critical; these words are the focus of the user’s attention when composing a translation. The system described in this paper is trained to be particularly sensitive to these first words. To achieve this effect, the system includes a new way of accounting for what parts of the sentence have already been translated, so that the suggestion of what the translator will type next is not redundant with existing content. The technical details include a novel beam search strategy and a hierarchical joint model of alignment and translation that together improve suggestions dramatically. For English-German news, next-word accuracy increases from 28.5% to 41.2%.

An interactive MT system could also display multiple suggestions to the user. We describe an algorithm for efficiently finding the n-best next words directly following a prefix and their corresponding best suffixes. Our experiments show that this approach to n-best list extraction, combined with our other improvements, increased next-word suggestion accuracy of 10-best lists from 33.4% to 55.5%. We also train a recurrent neural translation system for prefix-constrained translation. This neural system provides even more accurate predictions than our improved phrase-based system. However, inference is two orders of magnitude slower, which is problematic for an interactive setting. (Stay tuned for upcoming results about fast prefix-constrained neural translation.)

The paper concludes with a manual error analysis that reveals the strengths and weaknesses of both the phrase-based and neural approaches to prefix-constrained translation. Neural models are particularly good at producing grammatically correct and well-formed target language output. However, they also show a tendency to drop important content words.

null

Interactive and Adaptive Computer Aided Translation

5 Minute Read

Originally published on Kirti Vashee’s blog eMpTy Pages. Lilt is an interactive and adaptive computer-aided translation tool that integrates machine translation, translation memories, and termbases into one interface that learns from translators. Using Lilt is an entirely different experience from post-editing machine translations — an experience that our users love, and one that yields substantial productivity gains without compromising quality. The first step toward using this new kind of tool is to understand how interactive and adaptive machine assistance is different from conventional MT, and how these technologies relate to exciting new developments in neural MT and deep learning. Interactive MT doesn’t just translate each segment once and leave the translator to clean up the mess. Instead, each word that the translator types into the Lilt environment is integrated into a new automatic translation suggestion in real time. While text messaging apps autocomplete words, interactive MT autocompletes whole sentences. Interactive MT actually improves translation quality. In conventional MT post-editing, the computer knows what segment will be translated, but doesn’t know anything about the phrasing decisions that a translator will make. Interactive translations are more accurate because they can observe what the translator has typed so far and update their suggestions based on all available information.

Read More
IQT_logo_color_CMYK

Lilt Announces Strategic Partnership with In-Q-Tel (IQT)

2 Minute Read

Partnership fuels company growth and enables U.S. government agencies to translate materials accurately and quickly.

Read More