1. Articles in category: Machine Translation

    7345-7368 of 8104 « 1 2 ... 304 305 306 307 308 309 310 ... 336 337 338 »
    1. MSD Recombination for Statistical Machine Translation into Highly-Inflected Languages

      Freely available tools and language resources were used to build the VoiceTRAN statistical machine translation (SMT) system. Various configuration variations of the system are presented and evaluated. The VoiceTRAN SMT system outperformed the baseline conventional rule-based MT system in both English-Slovenian in-domain test setups. To further increase the generalization capability of the translation model for lower-coverage out-of-domain test sentences, an “MSD-recombination” approach was proposed. This approach not only allows a better exploitation of conventional translation models, but also performs well in the more demanding translation direction; that is, into a highly inflectional language. Using this approach in the out-of-domain setup ...
      Read Full Article
      Mentions: Slovenia Ljubljana
    2. Cross Sentence Alignment for Structurally Dissimilar Corpus Based on Singular Value Decomposition

      Extracting the alignment pairs is a critical step for constructing bilingual corpus knowledge base for Example Based Machine Translation Systems. Different methods have been proposed in aligning parallel corpus between two different languages. However, most of them focus on structurally similar languages like English-French. This paper presents a method of cross aligning Portuguese-Chinese bilingual comparable corpus. The proposed approach is based on Singular Value Decomposition techniques and similarity measurement, which covers the problem in aligning structurally dissimilar corpus and enhances the accuracy of the alignment result. Content Type Book ChapterDOI 10.1007/978-3-540-85984-0_104Authors Anna Ho, University of Macau Faculty of ...
      Read Full Article
    3. Semantic language and multi-language MT approach based on SL

      Abstract  Any natural language is regarded as a representation of semantic language. The translation between two languages (I, J) is regarded as a transformation between two representations. A natural language-I is translated into another natural language-J only by two steps. One is semantic-analysis of language-I based on “semantic-element-representation-base of language-I”, the other is deploying into the representation of language-J baded on “semantic-element-representation-base of language-J”. For translating inN natural languages, it is needed to developN translation systems only, rather thanN(N-1)/2, or 2N systems. Content Type Journal ArticleDOI 10.1007/BF02945475Authors QingShi Gao, University of Science and Technology 100083 Beijing ...
      Read Full Article
    4. ParaMT: A Paraphraser for Machine Translation

      In this paper we present ParaMT, a bilingual/multilingual paraphraser to be applied in machine translation. We select paraphrases of support verb constructions and use the NooJ linguistic environment to formalize and generate translation equivalences through the use of dictionary and local grammars with syntactic and semantic content. Our research shows that linguistic paraphrasal knowledge constitutes a key element in conversion of source language into controlled language text that presents more successful translation results. Content Type Book ChapterDOI 10.1007/978-3-540-85980-2_21Authors Anabela Barreiro, New York University Faculdade de Letras da Universidade do Porto & CLUP-Linguateca Book Series Lecture Notes in Computer ...
      Read Full Article
    5. Statistical Machine Translation of Broadcast News from Spanish to Portuguese

      In this paper we describe the work carried out to develop an automatic system for translation of broadcast news from Spanish to Portuguese. Two challenging topics of speech and language processing were involved: Automatic Speech Recognition (ASR) of the Spanish News and Statistical Machine Translation (SMT) of the results to the Portuguese language. ASR of broadcast news is based on the AUDIMUS.MEDIA system, a hybrid ANN/HMM system with multiple stream decoding. A 22.08% Word Error Rate (WER) was achieved in a Spanish Broadcast News task, which is comparable to other international state of the art systems. Parallel ...
      Read Full Article
    6. Adaptive Translation: Finding Interlingual Mappings Using Self-Organizing Maps

      This paper presents a method for creating interlingual word-to-word or phrase-to-phrase mappings between any two languages using the self-organizing map algorithm. The method can be used as a component in a statistical machine translation system. The conceptual space created by the self-organizing map serves as a kind of interlingual representation. The specific problems of machine translation are discussed in some detail. The proposed method serves in alleviating two problems. The main problem addressed here is the fact that different languages divide the conceptual space differently. The approach can also help in dealing with lexical ambiguity. Content Type Book ChapterDOI 10 ...
      Read Full Article
    7. Parsing with dynamic rule selection

      Abstract  Although many linguistic theories and formalisms have been developed and discussed on the problem of parsing algorithm in the past decades, the efficiency and accuracy of parsing are still serious problems in practical machine translation systems. This paper presents a parsing algorithm with dynamic rule selection and the experimental results. By describing the design and practice of the improved algorithm, the paper discusses in detail the designing method for a high speed and efficient parser. Content Type Journal ArticleDOI 10.1007/BF02943148Authors Chengqing Zong, The Chinese Academy of Sciences IMT Research Center, Institute of Computing Technology 100080 BeijingZhaoxiong Chen ...
      Read Full Article
    8. Asia Online to Double the Size of the Thai-Language Internet: World's Largest Literacy Project leverages Translation ...

      As part of Asia Online's corporate goal of providing Asian nations with the same level of access to knowledge and information enjoyed by the developed economies of the world, the company is making more than 3 million education-oriented pages available in the Thai language. The project couples newly developed translation technology that learns from the collective skills of humans to deliver ...
      Read Full Article
    9. Windows Live Messenger translation bot now available!

      The Microsoft Translator team is excited to announce the new translation bot for Windows Live Messenger! This Messenger bot does translations for you. Just add mtbot@hotmail.com to your contacts and start chatting. You can have one-on-one conversations with the bot, or you can invite a friend and chat in different languages with the bot translating for you.  As usual, remember that machine translation isn’t perfect – slang especially will give the engine trouble. You can also access Windows Live Messenger on your smartphone to use the bot to translate simple sentences while you’re traveling to other countries ...
      Read Full Article
    10. Full-form lexicon with tagged data and methods of constructing and using the same

      CROSS-REFERENCE TO RELATED APPLICATIONSReference is hereby made to the following co-pending and commonly assigned patent applications: U.S. application Ser. No. 10/804,930, filed Mar. 19, 2004, entitled "Compound Word Breaker and Spell Checker" and U.S. application Ser. No.10/804,883, filed Mar. 19, 2004, entitled "System and Method for Performing Analysis on Word Variants", both of which are incorporated by reference in their entirety.BACKGROUND OF THE INVENTIONThe present invention relates to
      Read Full Article
    11. A Reordering Model for Phrase-Based Machine Translation

      This paper presents a new method for reordering in phrase based statistical machine translation (PBSMT). Our method is based on previous chunk-level reordering methods for PBSMT. Our method is a global reordering. First, we parse the source language sentence to a chunk tree, according to the method developed by [1]. Second, we apply a series of transformation rules, which are learnt automatically from the parallel corpus to the chunk tree over chunk level. Finally, we solve phenomena for the overlapping of phrases and chunks, and integrate a global reordering model directly in a decoder as a graph of phrases. The ...
      Read Full Article
    12. German Compounds in Factored Statistical Machine Translation

      An empirical method for splitting German compounds is explored by varying it in a number of ways to investigate the consequences for factored statistical machine translation between English and German in both directions. Compound splitting is incorporated into translation in a preprocessing step, performed on training data and on German translation input. For translation into German, compounds are merged based on part-of-speech in a postprocessing step. Compound parts are marked, to separate them from ordinary words. Translation quality is improved in both translation directions and the number of untranslated words in the English output is reduced. Different versions of the ...
      Read Full Article
      Mentions: Sweden
    7345-7368 of 8104 « 1 2 ... 304 305 306 307 308 309 310 ... 336 337 338 »
  1. Categories

    1. Default:

      Discourse, Entailment, Machine Translation, NER, Parsing, Segmentation, Semantic, Sentiment, Summarization, WSD
  2. Popular Articles

  3. Organizations in the News

    1. (25 articles) Google
    2. (16 articles) Microsoft
    3. (9 articles) Google Translate
    4. (7 articles) Apple
    5. (5 articles) Microsoft Translator
    6. (5 articles) AGI
    7. (5 articles) NLP
    8. (5 articles) IBM
    9. (4 articles) IoT
    10. (4 articles) Simon & Schuster
    11. (4 articles) Johns Hopkins University
    12. (4 articles) Symantec
  4. Locations in the News

    1. (10 articles) China
    2. (6 articles) Japan
    3. (6 articles) Doha
    4. (6 articles) Qatar
    5. (6 articles) Russian
    6. (5 articles) Amazon
    7. (5 articles) Canada
    8. (5 articles) France
    9. (5 articles) Maidenhead
    10. (4 articles) Russia
    11. (4 articles) Paris
    12. (4 articles) Baidu
  5. People in the News

    1. (4 articles) Philipp Koehn
    2. (2 articles) Dion Wiggins
    3. (2 articles) Andrew Ng
    4. (1 articles) Alan Turing
    5. (1 articles) Robert Mercer
    6. (1 articles) Yoav Goldberg
    7. (1 articles) Yann LeCun
    8. (1 articles) George Washington
    9. (1 articles) Geoff Hinton
    10. (1 articles) Jeff Dean
    11. (1 articles) Kenji Takeda
    12. (1 articles) Yoshua Bengio