Skip to Main content Skip to Navigation
New interface
Theses

Confidence Measures for Alignment and for Machine Translation

Abstract : In computational linguistics, the relation between different languages is often studied through automatic alignment techniques. Such alignments can be established at various structural levels. In particular, sentential and sub-sentential bitext alignments constitute an important source of information in various modern Natural Language Processing (NLP) applications, a prominent one being Machine Translation (MT).Effectively computing bitext alignments, however, can be a challenging task. Discrepancies between languages appear in various ways, from discourse structures to morphological constructions. Automatic alignments would, at least in most cases, contain noise harmful for the performance of application systems which use the alignments. To deal with this situation, two research directions emerge: the first is to keep improving alignment techniques; the second is to develop reliable confidence measures which enable application systems to selectively employ the alignments according to their needs.Both alignment techniques and confidence estimation can benefit from manual alignments. Manual alignments can be used as both supervision examples to train scoring models and as evaluation materials. The creation of such data is, however, an important question in itself, particularly at sub-sentential levels, where cross-lingual correspondences can be only implicit and difficult to capture.This thesis focuses on means to acquire useful sentential and sub-sentential bitext alignments. Chapter 1 provides a non-technical description of the research motivation, scope, organization, and introduces terminologies and notation. State-of-the-art alignment techniques are reviewed in Part I. Chapter 2 and 3 describe state-of-the-art methods for respectively sentence and word alignment. Chapter 4 summarizes existing manual alignments, and discusses issues related to the creation of gold alignment data. The remainder of this thesis, Part II, presents our contributions to bitext alignment, which are concentrated on three sub-tasks.Chapter 5 presents our contribution to gold alignment data collection. For sentence- level alignment, we collect manual annotations for an interesting text genre: literary bitexts, which are very useful for evaluating sentence aligners. We also propose a scheme for sentence alignment confidence annotation. For sub-sentential alignment, we annotate one-to-one word links with a novel 4-way labelling scheme, and design a new approachfor facilitating the collection of many-to-many links. All the collected data is released on-line.Improving alignment methods remains an important research subject. We pay special attention to sentence alignment, which often lies at the beginning of the bitext alignment pipeline. Chapter 6 presents our contributions to this task. Starting by evaluating state-of-the-art aligners and analyzing their models and results, we propose two new sentence alignment methods, which achieve state-of-the-art performance on a difficult dataset.The other important subject that we study is confidence estimation. In Chapter 7, we propose confidence measures for sentential and sub-sentential alignments. Experiments show that confidence estimation of alignment links is a challenging problem, and more works on enhancing the confidence measures will be useful.Finally, note that these contributions have been employed in a real world application: the development of a bilingual reading tool aimed at facilitating the reading in a foreign language.
Complete list of metadata

Cited literature [177 references]  Display  Hide  Download

https://theses.hal.science/tel-01399222
Contributor : ABES STAR :  Contact
Submitted on : Friday, November 18, 2016 - 2:47:08 PM
Last modification on : Saturday, June 25, 2022 - 10:22:31 PM
Long-term archiving on: : Monday, March 20, 2017 - 4:10:36 PM

File

73143_XU_2016_diffusion.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01399222, version 1

Citation

Yong Xu. Confidence Measures for Alignment and for Machine Translation. Signal and Image Processing. Université Paris Saclay (COmUE), 2016. English. ⟨NNT : 2016SACLS270⟩. ⟨tel-01399222⟩

Share

Metrics

Record views

293

Files downloads

690