Karteikarten
Machine Translator
Karten in diesem Stapel (12)
- 1—Machine Translation Approaches:
Issues and
Challenges - 2Machine translation (MT), a subfield under Artificial Intelligence is the application of computers to the task of translating texts from one natural (human) language to another. Many approaches have been used in the recent times to develop an MT system.The idea of machine translation may be traced back to the 17th
century. - 3MT on the web started with SYSTRAN Offering free translation of small texts (1996), followed by AltaVista Babelfish, which racked up 500,000 requests a day (1997). Franz-Josef Och (the future head of Translation Development AT Google) won DARPA‘s speed MT competition (2003).Google announced that
Google Translate translates roughly enough text to fill 1 million
books in one day (2012). - 4RBMT Machine Translation Approach
- 5RBMT Issues and challenges- Insufficient amount of really good dictionaries.
- Building new dictionaries is expensive.
- Some linguistic information still needs to be set manually.
- It is hard to deal with rule interactions in big systems, ambiguity, and idiomatic expressions. - 6Direct Machine Translation (DMT) ApproachDMT approach is the oldest and less popular approach. Direct translation is made at the word level. Machine translation systems that use this
approach are capable of translating a language, called source language (SL) directly to another language, called target
language (TL). - 7DMT Issues and challenges- It can be characterized as word-for-word‘ translation with some local word-order adjustment.
- Grammatical relationships
between the principal parts of the sentences. - 8Interlingual Machine Translation ApproachInterlingual machine translation is one instance of rule-based machine-translation approaches. In this approach,
the source language, i.e. the text to be translated, is transformed into an interlingual language, i.e. a ―language neutral representation that is independent of any language. - 9Issues and challenges- It is difficult to extract meaning from texts in the original languages to create the intermediate representation.
- Semantic differentiation is target-language specific and making such distinctions is comparable to lexical transfer not all distinctions needed for translation. - 10Other MT approaches- Transfer-based Machine Translation Approach
- Corpus-based Machine Translation
Approach
- Statistical Machine Translation Approach
- Hybrid Machine Translation Approach
- - 11Some Challenges- The results are unexpected. Superficial fluency can be deceiving.
- The benefits are overemphasized for European languages.
- It is difficult to do as much work as possible in reusable modules of analysis and synthesis. - 12More Challenges- It is difficult to keep transfer modules as simple as possible.
- It is difficult to extract meaning from texts in the original languages to create the intermediate representation.
-
Informationen
- Beschreibung
- Periodismo Karteikarten am Machine Translator , erstellt von Julian Patino am 25/10/2017.
- Erstellt von
- Julian Patino
- Aufrufe
- 2
- Bewertung