Directly to content
  1. Publishing |
  2. Search |
  3. Browse |
  4. Recent items rss |
  5. Open Access |
  6. Jur. Issues |
  7. DeutschClear Cookie - decide language by browser settings

Preference Learning for Machine Translation

Simianer, Patrick

[img]
Preview
PDF, English - main document
Download (4MB) | Terms of use

Citation of documents: Please do not cite the URL that is displayed in your browser location input, instead use the DOI, URN or the persistent URL below, as we can guarantee their long-time accessibility.

Abstract

Automatic translation of natural language is still (as of 2017) a long-standing but unmet promise. While advancing at a fast rate, the underlying methods are still far from actually being able to reliably capture syntax or semantics of arbitrary utterances of natural language, way off transporting the encoded meaning into a second language. However, it is possible to build useful translating machines when the target domain is well known and the machine is able to learn and adapt efficiently and promptly from new inputs. This is possible thanks to efficient and effective machine learning methods which can be applied to automatic translation.

In this work we present and evaluate methods for three distinct scenarios:

a) We develop algorithms that can learn from very large amounts of data by exploiting pairwise preferences defined over competing translations, which can be used to make a machine translation system robust to arbitrary texts from varied sources, but also enable it to learn effectively to adapt to new domains of data;

b) We describe a method that is able to efficiently learn external models which adhere to fine-grained preferences that are extracted from a constricted selection of translated material, e.g. for adapting to users or groups of users in a computer-aided translation scenario;

c) We develop methods for two machine translation paradigms, neural- and traditional statistical machine translation, to directly adapt to user-defined preferences in an interactive post-editing scenario, learning precisely adapted machine translation systems.

In all of these settings, we show that machine translation can be made significantly more useful by careful optimization via preference learning.

Item Type: Dissertation
Supervisor: Riezler, Prof. Dr. Stefan
Date of thesis defense: 23 April 2018
Date Deposited: 31 Oct 2018 12:40
Date: 2018
Faculties / Institutes: Neuphilologische Fakultät > Institut für Computerlinguistik
Subjects: 004 Data processing Computer science
Controlled Keywords: machine translation, discriminative training, computer-aided translation
About | FAQ | Contact | Imprint |
OA-LogoDINI certificate 2013Logo der Open-Archives-Initiative