Matches in ScholarlyData for { ?s ?p ?o. }
- item-1 type ListItem.
- item-1 hasContent shunsuke-kozawa.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent hitomi-tohyama.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent kiyotaka-uchimoto.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent shigeki-matsubara.
- item-4 previous item-3.
- 17 creator harry-bunt.
- 17 creator volha-petukhova.
- 17 type InProceedings.
- 17 label "LIRICS Semantic Role Annotation: Design and Evaluation of a Set of Data Categories".
- 17 sameAs 17.
- 17 abstract "Semantic roles have often proved to be useful labels for stating linguistic generalisations of various sorts. There is, however, a lack of agreement on their defining criteria, which causes serious problems for semantic roles to be a useful classificatory device for predicate-argument relations. These criteria should (a) support the design of a semantic role set which is complete but does not contain redundant relations; (b) be based on semantic rather than morphological, lexical or syntactic properties; and (c) enable formal interpretation. In this paper we report on the analyses of alternative approaches to annotation and representation of semantic role information (such as FrameNet, PropBank and VerbNet) with respect to their models of description, granularity of semantic role sets, definitions of semantic roles concepts, consistency and reliability of annotations. We present methodological principles for characterising well-defined concepts which were developed within the LIRICS (Linguistic InfRastructure for Interoperable ResourCes and Systems; see http://lirics.loria.fr) project, as well as the designed set of semantic roles and their definitions in ISO 12620 format. We discuss evaluation results of the defined concepts for semantic role annotation concerning the redundancy and completeness of the tagset and the reliability of annotations in terms of inter-annotator agreement.".
- 17 hasAuthorList authorList.
- 17 hasTopic Linguistics.
- 17 isPartOf proceedings.
- 17 keyword "Corpus (creation, annotation, etc.)".
- 17 keyword "Semantics".
- 17 keyword "Standards for LRs".
- 17 title "LIRICS Semantic Role Annotation: Design and Evaluation of a Set of Data Categories".
- 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 volha-petukhova.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent harry-bunt.
- item-2 previous item-1.
- 172 creator abdenour-mokrane.
- 172 creator jean-yves-antoine.
- 172 creator nathalie-friburger.
- 172 type InProceedings.
- 172 label "Automatic Rich Annotation of Large Corpus of Conversational transcribed speech: the Chunking Task of the EPAC Project".
- 172 sameAs 172.
- 172 abstract "This paper describes the use of the CasSys platform in order to achieve the chunking of conversational speech transcripts by means of cascades of Unitex transducers. Our system is involved in the EPAC project of the French National agency of Research (ANR). The aim of this project is to develop robust methods for the annotation of audio/multimedia document collections which contains conversational speech sequences such as TV or radio programs. At first, this paper presents the EPAC project and the adaptation of a former chunking system (Romus) which was developed in the restricted framework of dedicated spoken man-machine dialogue. Then, it describes the problems that are arising due to 1) spontaneous speech disfluencies and 2) errors for the previous stages of processing (automatic speech recognition and POS tagging).".
- 172 hasAuthorList authorList.
- 172 hasTopic Linguistics.
- 172 isPartOf proceedings.
- 172 keyword "Corpus (creation, annotation, etc.)".
- 172 keyword "Parsing Systems".
- 172 keyword "Tagging".
- 172 title "Automatic Rich Annotation of Large Corpus of Conversational transcribed speech: the Chunking Task of the EPAC Project".
- 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 jean-yves-antoine.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent abdenour-mokrane.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent nathalie-friburger.
- item-3 previous item-2.
- 173 creator vincent-claveau.
- 173 type InProceedings.
- 173 label "Automatic Translation of Biomedical Terms by Supervised Machine Learning".
- 173 sameAs 173.
- 173 abstract "In this paper, we present a simple yet efficient automatic system to translate biomedical terms. It mainly relies on a machine learning approach able to infer rewriting rules from pair of terms in two languages. Given a new term, these rules are then used to transform the initial term into its translation. Since conflicting rules may produce different translations, we also use language modeling to single out the best candidate. We report experiments on different language pairs (including Czech, English, French, Italian, German, Portuguese, Spanish and even Russian); our approach yields good results (varying according to the considered languages) and outperforms existing ones for the French-English pair.".
- 173 hasAuthorList authorList.
- 173 hasTopic Linguistics.
- 173 isPartOf proceedings.
- 173 keyword "Acquisition, Machine Learning".
- 173 keyword "Machine Translation, SpeechToSpeech Translation".
- 173 keyword "Multilinguality".
- 173 title "Automatic Translation of Biomedical Terms by Supervised Machine Learning".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent vincent-claveau.
- 174 creator guillaume-gravier.
- 174 creator pascale-sebillot.
- 174 creator stephane-huet.
- 174 type InProceedings.
- 174 label "Morphosyntactic Resources for Automatic Speech Recognition".
- 174 sameAs 174.
- 174 abstract "Texts generated by automatic speech recognition (ASR) systems have some specificities, related to the idiosyncrasies of oral productions or the principles of ASR systems, that make them more difficult to exploit than more conventional natural language written texts. This paper aims at studying the interest of morphosyntactic information as a useful resource for ASR. We show the ability of automatic methods to tag outputs of ASR systems, by obtaining a tag accuracy similar for automatic transcriptions to the 95-98 % usually reported for written texts, such as newspapers. We also demonstrate experimentally that tagging is useful to improve the quality of transcriptions by using morphosyntactic information in a post-processing stage of speech decoding. Indeed, we obtain a significant decrease of the word error rate with experiments done on French broadcast news from the ESTER corpus; we also notice an improvement of the sentence error rate and observe that a significant number of agreement errors are corrected.".
- 174 hasAuthorList authorList.
- 174 hasTopic Linguistics.
- 174 isPartOf proceedings.
- 174 keyword "Language modelling".
- 174 keyword "Speech recognition and understanding".
- 174 keyword "Tagging".
- 174 title "Morphosyntactic Resources for Automatic Speech Recognition".