FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W899096206> ?p ?o ?g. }

• W899096206 abstract "With the arrival of free on-line translation (MT) systems, came the possibility to improve automatic translations with the help of daily users. One of the methods to achieve such improvements is to ask to users themselves for a better translation. It is possible that the system had made a mistake and if the user is able to detect it, it would be a valuable help to let the user teach the system where it made the mistake so it does not make it again if it finds a similar situation. Most of the translation systems you can find on-line provide a text area for users to suggest a better translation (like Google translator) or a ranking system for them to use (like Microsoft's). In 2009, as part of the Seventh Framework Programme of the European Commission, the FAUST project started with the goal of developing machine translation (MT) systems which respond rapidly and intelligently to user feedback. Specifically, one of the project objective was to develop mechanisms for instantaneously incorporating user feedback into the MT engines that are used in production environments, .... As a member of the FAUST project, this thesis focused on developing one such mechanism.Formally, the general objective of this work was to design and implement a strategy to improve the translation quality of an already trained Statistical Machine Translation (SMT) system, using translations of input sentences that are corrections of the system's attempt to translate them. To address this problem we divided it in three specific objectives:1. Define a relation between the words of a correction sentence and the words in the system's translation, in order to detect the errors that the former is aiming to solve.2. Include the error corrections in the original system, so it learns how to solve them in case a similar situation occurs.3. Test the strategy in different scenarios and with different data, in order to validate the applications of the proposed methodology.The main contributions made to the SMT field that can be found in this Ph.D. thesis are: - We defined a similarity function that compares an MT system output with a translation reference for that output and align the errors made by the system with the correct translations found in the reference. This information is then used to compute an alignment between the original input sentence and the reference.- We defined a method to perform domain adaptation based on the alignment mentioned before. Using this alignment with an in-domain parallel corpus, we extract new translation units that correspond both to units found in the system and were correctly chosen during translation and new units that include the correct translations found in the reference. These new units are then scored and combined with the units in the original system in order to improve its quality in terms of both human an automatic metrics. - We succesfully applied the method in a new task: to improve a SMT translation quality using post-editions provided by real users of the system. In this case, the alignment was computed over a parallel corpus build with post-editions, extracting translation units that correspond both to units found in the system and were correctly chosen during translation and new units that include the corrections found in the feedback provided.- The method proposed in this dissertation is able to achieve significant improvements in translation quality with a small learning material, corresponding to a 0.5% of the training material used to build the original system. Results from our evaluations also indicate that the improvement achieved with the domain adaptation strategy is measurable by both automatic a human-based evaluation metrics." @default.
• W899096206 created "2016-06-24" @default.
• W899096206 creator A5034758933 @default.
• W899096206 creator A5046725772 @default.
• W899096206 date "2014-03-07" @default.
• W899096206 modified "2023-09-27" @default.
• W899096206 title "Improving statistical machine translation through adaptation and learning" @default.
• W899096206 cites W1205016396 @default.
• W899096206 cites W122999227 @default.
• W899096206 cites W1550982044 @default.
• W899096206 cites W1578533488 @default.
• W899096206 cites W1601740268 @default.
• W899096206 cites W1603508585 @default.
• W899096206 cites W1631260214 @default.
• W899096206 cites W1665921526 @default.
• W899096206 cites W16951757 @default.
• W899096206 cites W16967297 @default.
• W899096206 cites W1895614922 @default.
• W899096206 cites W1916559533 @default.
• W899096206 cites W1934041838 @default.
• W899096206 cites W1965660534 @default.
• W899096206 cites W1969974515 @default.
• W899096206 cites W1991133427 @default.
• W899096206 cites W1991522508 @default.
• W899096206 cites W2006969979 @default.
• W899096206 cites W203147164 @default.
• W899096206 cites W2038698865 @default.
• W899096206 cites W2061910127 @default.
• W899096206 cites W2078861931 @default.
• W899096206 cites W2080373976 @default.
• W899096206 cites W2082092506 @default.
• W899096206 cites W2085086335 @default.
• W899096206 cites W2086202918 @default.
• W899096206 cites W2087735403 @default.
• W899096206 cites W2095755718 @default.
• W899096206 cites W2096175520 @default.
• W899096206 cites W2096384330 @default.
• W899096206 cites W2097333193 @default.
• W899096206 cites W2098057009 @default.
• W899096206 cites W2098507980 @default.
• W899096206 cites W2101105183 @default.
• W899096206 cites W2103414875 @default.
• W899096206 cites W2105410942 @default.
• W899096206 cites W2110417778 @default.
• W899096206 cites W2111798208 @default.
• W899096206 cites W2116042738 @default.
• W899096206 cites W2116265812 @default.
• W899096206 cites W2120349760 @default.
• W899096206 cites W2120644359 @default.
• W899096206 cites W2123301721 @default.
• W899096206 cites W2123635983 @default.
• W899096206 cites W2124202134 @default.
• W899096206 cites W2124807415 @default.
• W899096206 cites W2132001515 @default.
• W899096206 cites W2137387514 @default.
• W899096206 cites W2138309071 @default.
• W899096206 cites W2144879357 @default.
• W899096206 cites W2146574666 @default.
• W899096206 cites W2148504207 @default.
• W899096206 cites W2149327368 @default.
• W899096206 cites W2151594415 @default.
• W899096206 cites W2152263452 @default.
• W899096206 cites W2153204578 @default.
• W899096206 cites W2154590816 @default.
• W899096206 cites W2156001539 @default.
• W899096206 cites W2156985047 @default.
• W899096206 cites W2158614781 @default.
• W899096206 cites W2159755860 @default.
• W899096206 cites W2161227214 @default.
• W899096206 cites W2169724380 @default.
• W899096206 cites W2171074980 @default.
• W899096206 cites W2171960770 @default.
• W899096206 cites W2180952760 @default.
• W899096206 cites W2182115895 @default.
• W899096206 cites W2182800199 @default.
• W899096206 cites W2183744857 @default.
• W899096206 cites W22168010 @default.
• W899096206 cites W222053410 @default.
• W899096206 cites W2250255003 @default.
• W899096206 cites W2288542159 @default.
• W899096206 cites W2294809693 @default.
• W899096206 cites W2340221426 @default.
• W899096206 cites W2356613612 @default.
• W899096206 cites W2394860946 @default.
• W899096206 cites W2398285446 @default.
• W899096206 cites W2401082558 @default.
• W899096206 cites W2408675770 @default.
• W899096206 cites W2437005631 @default.
• W899096206 cites W2532704541 @default.
• W899096206 cites W2595813107 @default.
• W899096206 cites W2610485724 @default.
• W899096206 cites W2764433274 @default.
• W899096206 cites W2892587090 @default.
• W899096206 cites W3083113686 @default.
• W899096206 cites W3202354456 @default.
• W899096206 cites W3202971710 @default.
• W899096206 cites W3203347510 @default.
• W899096206 cites W3204895712 @default.
• W899096206 cites W43934831 @default.
• W899096206 cites W82303372 @default.

• next