Matches in ScholarlyData for { ?s ?p ?o. }
- item-4 type ListItem.
- item-4 hasContent dirk-geeraerts.
- item-4 previous item-3.
- 785 creator arne-mauser.
- 785 creator hermann-ney.
- 785 creator sasa-hasan.
- 785 type InProceedings.
- 785 label "Automatic Evaluation Measures for Statistical Machine Translation System Optimization".
- 785 sameAs 785.
- 785 abstract "Evaluation of machine translation (MT) output is a challenging task. In most cases, there is no single correct translation. In the extreme case, two translations of the same input can have completely different words and sentence structure while still both being perfectly valid. Large projects and competitions for MT research raised the need for reliable and efficient evaluation of MT systems. For the funding side, the obvious motivation is to measure performance and progress of research. This often results in a specific measure or metric taken as primarily evaluation criterion. Do improvements in one measure really lead to improved MT performance? How does a gain in one evaluation metric affect other measures? This paper is going to answer these questions by a number of experiments.".
- 785 hasAuthorList authorList.
- 785 hasTopic Linguistics.
- 785 isPartOf proceedings.
- 785 keyword "Evaluation methodologies".
- 785 keyword "Machine Translation, SpeechToSpeech Translation".
- 785 keyword "Statistical methods".
- 785 title "Automatic Evaluation Measures for Statistical Machine Translation System Optimization".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent arne-mauser.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent sasa-hasan.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent hermann-ney.
- item-3 previous item-2.
- 786 creator rudolf-muhr.
- 786 type InProceedings.
- 786 label "The Pronouncing Dictionary of Austrian German (AGPD) and the Austrian Phonetic Database (ADABA): Report on a large Phonetic Resources Database of the three Major Varieties of German".
- 786 sameAs 786.
- 786 abstract "The paper gives a comprehensive overview over the results, the concepts and the methods which were developed and used to create the Pronouncing Dictionary of Austrian German (ÖAWB) and the Austrian Pronouncing Database ADABA. The ÖAWB contains 42,000 entries which are based on a large audio corpus of 75,964 realisations of two model speakers each from Austria, Germany and Switzerland. The ADABA database provides 9 different ways to search the data. It also contains 24 model texts and another 30 texts showing linguistic and phonetic variation in Austria and in the other German speaking countries. The codification of Austrian standard pronunciation was based on the concept of German as a pluricentric language and on the concept of media presentation language . Austrian pronunciation forms are presented in parallel with those of Germany and Switzerland to allow the comparison of differences between linguistically close national varieties of a language. The paper also gives a detailed characterisation of the software (transcriber, database) which was developed during the project that was supported by the Austrian national broadcasting corporation ORF and the University for Music and Dramatic Arts in Graz. Some of the software and the data can be obtained from the web site www.adaba.at.".
- 786 hasAuthorList authorList.
- 786 hasTopic Linguistics.
- 786 isPartOf proceedings.
- 786 keyword "Phonetic Databases, Phonology".
- 786 keyword "Speech recognition and understanding".
- 786 keyword "Speech resource/database".
- 786 title "The Pronouncing Dictionary of Austrian German (AGPD) and the Austrian Phonetic Database (ADABA): Report on a large Phonetic Resources Database of the three Major Varieties of German".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent rudolf-muhr.
- 787 creator einar-meister.
- 787 creator jaak-vilo.
- 787 type InProceedings.
- 787 label "Strengthening the Estonian Language Technology".
- 787 sameAs 787.
- 787 abstract "The paper will give an overview of developments in Estonia in the field of Human Language Technologies. Despite of the fact that Estonian is one of the smallest official languages in EU and therefore in less favourable position in the HLT-market, the national initiatives are undertaken in order to promote HLT development in Estonia. The paper will introduce recent activities in Estonia, including National Programme for Estonian Language Technology (2006-2010).".
- 787 hasAuthorList authorList.
- 787 hasTopic Linguistics.
- 787 isPartOf proceedings.
- 787 keyword "LR national/international projects, organizational/policy issues".
- 787 title "Strengthening the Estonian Language Technology".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent einar-meister.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent jaak-vilo.
- item-2 previous item-1.
- 788 creator benoit-habert.
- 788 creator claude-barras.
- 788 creator gilles-adda.
- 788 creator martine-adda-decker.
- 788 creator patrick-paroubek.
- 788 creator philippe-boula-de-mareuil.
- 788 type InProceedings.
- 788 label "Annotation and analysis of overlapping speech in political interviews".
- 788 sameAs 788.
- 788 abstract "Looking for a better understanding of spontaneous speech-related phenomena and to improve automatic speech recognition (ASR), we present here a study on the relationship between the occurrence of overlapping speech segments and disfluencies (filled pauses, repetitions, revisions) in political interviews. First we present our data, and our overlap annotation scheme. We detail our choice of overlapping tags and our definition of disfluencies; the observed ratios of the different overlapping tags are examined, as well as their correlation with of the speaker role and propose two measures to characterise speakers interacting attitude: the attack/resist ratio and the attack density. We then study the relationship between the overlapping speech segments and the disfluencies in our corpus, before concluding on the perspectives that our experiments offer.".
- 788 hasAuthorList authorList.
- 788 hasTopic Linguistics.
- 788 isPartOf proceedings.
- 788 keyword "Corpus (creation, annotation, etc.)".
- 788 keyword "Speech recognition and understanding".
- 788 keyword "Speech resource/database".
- 788 title "Annotation and analysis of overlapping speech in political interviews".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasItem item-4.
- authorList hasItem item-5.
- authorList hasItem item-6.
- authorList hasLastItem item-6.
- item-1 type ListItem.