Matches in ScholarlyData for { ?s ?p ?o. }
- item-2 type ListItem.
- item-2 hasContent branimir-boguraev.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent david-ferrucci.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent paul-keyser.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent anthony-levas.
- item-5 previous item-4.
- 821 creator kyoko-ohara.
- 821 type InProceedings.
- 821 label "Lexicon, Grammar, and Multilinguality in the Japanese FrameNet".
- 821 sameAs 821.
- 821 abstract "This paper discusses findings of a frame-based contrastive text analysis, using the large-scale and precise descriptions of semantic frames provided by the FrameNet project (Baker, 2006; Fillmore, 2006). It points out that even though the existing FrameNet methodology allows us to compare languages at a more detailed level than previous studies (e.g. Talmy, 2003; Slobin, 2004), in order to investigate how different languages encode the same events, it is also necessary to make cross-references to grammatical constructions rather than limiting ourselves to analyzing the semantics of frame-bearing predicates. Based on a contrastive text analysis of an English-Japanese aligned parallel corpus and on the lexicon-building project of Japanese FrameNet (Ohara et al., 2006), the paper attempts to represent interactions between lexical units and constructions of Japanese sentences in terms of the combined lexicon and constructicon , currently being developed in FrameNet (Fillmore, 2006). By applying the idea to the analysis of Japanese in Japanese FrameNet, it is hoped that the study will give support to working out the details of the new FrameNet directions.".
- 821 hasAuthorList authorList.
- 821 hasTopic Linguistics.
- 821 isPartOf proceedings.
- 821 keyword "Corpus (creation, annotation, etc.)".
- 821 keyword "LR Infrastructures and Architectures".
- 821 keyword "Multilinguality".
- 821 title "Lexicon, Grammar, and Multilinguality in the Japanese FrameNet".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent kyoko-ohara.
- 822 creator marianna-apidianaki.
- 822 type InProceedings.
- 822 label "Translation-oriented Word Sense Induction Based on Parallel Corpora".
- 822 sameAs 822.
- 822 abstract "Word Sense Disambiguation (WSD) is an intermediate task that serves as a means to an end defined by the application in which it is to be used. However, different applications have varying disambiguation needs which should have an impact on the choice of the method and of the sense inventory used. The tendency towards application-oriented WSD becomes more and more evident, mostly because of the inadequacy of predefined sense inventories and the inefficacy of application-independent methods in accomplishing specific tasks. In this article, we present a data-driven method of sense induction, which combines contextual and translation information coming from a bilingual parallel training corpus. It consists of an unsupervised method that clusters semantically similar translation equivalents of source language (SL) polysemous words. The created clusters are projected on the SL words revealing their sense distinctions. Clustered equivalents describing a sense of a polysemous word can be considered as more or less commutable translations for an instance of the word carrying this sense. The resulting sense clusters can thus be used for WSD and sense annotation, as well as for lexical selection in translation applications.".
- 822 hasAuthorList authorList.
- 822 hasTopic Linguistics.
- 822 isPartOf proceedings.
- 822 keyword "Machine Translation, SpeechToSpeech Translation".
- 822 keyword "Semantics".
- 822 keyword "Word Sense Disambiguation".
- 822 title "Translation-oriented Word Sense Induction Based on Parallel Corpora".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent marianna-apidianaki.
- 823 creator lynne-cahill.
- 823 type InProceedings.
- 823 label "Using Similarity Measures to Extend the LinGO Lexicon".
- 823 sameAs 823.
- 823 abstract "Deep processing of natural language requires large scale lexical resources that have sufficient coverage at a sufficient level of detail and accuracy (i.e. both recall and precision). Hand-crafted lexicons are extremely labour-intensive to create and maintain, and require continuous updating and extension to retain their level of usability. In this paper we present a technique for extending lexicons using similarity measures that can be extracted from corpora. The technique involves creating lexical entries for unknown words based on entries for words that are known and that are deemed to be distributionally similar. We demonstrate the applicability of the approach by providing an extended lexicon for the LinGO system using similarity measures extracted from the BNC. We also discuss the advantages and disadvantages of using such lexical extensions in different ways: principally either as part of the main lexicon or as a separate resource used only for last resort use.".
- 823 hasAuthorList authorList.
- 823 hasTopic Linguistics.
- 823 isPartOf proceedings.
- 823 keyword "Generation".
- 823 keyword "Lexicon, lexical database".
- 823 keyword "Parsing Systems".
- 823 title "Using Similarity Measures to Extend the LinGO Lexicon".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent lynne-cahill.
- 825 creator aurelien-max.
- 825 creator dave-toney.
- 825 creator eric-bilinski.
- 825 creator olivier-galibert.
- 825 creator sophie-rosset.
- 825 type InProceedings.
- 825 label "An Evaluation of Spoken and Textual Interaction in the RITEL Interactive Question Answering System".
- 825 sameAs 825.
- 825 abstract "The RITEL project aims to integrate a spoken language dialogue system and an open-domain information retrieval system in order to enable human users to ask a general question and to refine their search for information interactively. This type of system is often referred to as an Interactive Question Answering (IQA) system. In this paper, we present an evaluation of how the performance of the RITEL system differs when users interact with it using spoken versus textual input and output. Our results indicate that while users do not perceive the two versions to perform significantly differently, many more questions are asked in a typical text-based dialogue.".
- 825 hasAuthorList authorList.
- 825 hasTopic Linguistics.
- 825 isPartOf proceedings.
- 825 keyword "Dialogue & Natural Interactivity".
- 825 keyword "Question Answering".
- 825 keyword "Usability, user satisfaction".
- 825 title "An Evaluation of Spoken and Textual Interaction in the RITEL Interactive Question Answering System".
- 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 hasLastItem item-5.
- item-1 type ListItem.
- item-1 hasContent dave-toney.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent sophie-rosset.
- item-2 next item-3.
- item-2 previous item-1.