Matches in ScholarlyData for { ?s ?p ?o. }
- item-1 hasContent martine-adda-decker.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent claude-barras.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent gilles-adda.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent patrick-paroubek.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent philippe-boula-de-mareuil.
- item-5 next item-6.
- item-5 previous item-4.
- item-6 type ListItem.
- item-6 hasContent benoit-habert.
- item-6 previous item-5.
- 789 creator michael-white.
- 789 creator stephen-boxwell.
- 789 type InProceedings.
- 789 label "Projecting Propbank Roles onto the CCGbank".
- 789 sameAs 789.
- 789 abstract "This paper describes a method of accurately projecting Propbank roles onto constituents in the CCGbank and automatically annotating verbal categories with the semantic roles of their arguments. This method will be used to improve the structure of the derivations in the CCGbank and to facilitate research on semantic role tagging and broad coverage generation with CCG.".
- 789 hasAuthorList authorList.
- 789 hasTopic Linguistics.
- 789 isPartOf proceedings.
- 789 keyword "Corpus (creation, annotation, etc.)".
- 789 keyword "Semantics".
- 789 keyword "Tagging".
- 789 title "Projecting Propbank Roles onto the CCGbank".
- 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 stephen-boxwell.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent michael-white.
- item-2 previous item-1.
- 79 creator jonas-sjoebergh.
- 79 creator kenji-araki.
- 79 type InProceedings.
- 79 label "What is poorly Said is a Little Funny".
- 79 sameAs 79.
- 79 abstract "We implement several different methods for generating jokes in English. The common theme is to intentionally produce poor utterances by breaking Grice s maxims of conversation. The generated jokes are evaluated and compared to human made jokes. They are in general quite weak jokes, though there are a few high scoring jokes and many jokes that score higher than the most boring human joke.".
- 79 hasAuthorList authorList.
- 79 hasTopic Linguistics.
- 79 isPartOf proceedings.
- 79 keyword "Emotions".
- 79 keyword "Generation".
- 79 keyword "Other".
- 79 title "What is poorly Said is a Little Funny".
- 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 jonas-sjoebergh.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent kenji-araki.
- item-2 previous item-1.
- 790 creator kiyotaka-uchimoto.
- 790 creator yasuharu-den.
- 790 type InProceedings.
- 790 label "Word-level Dependency-structure Annotation to Corpus of Spontaneous Japanese and its Application".
- 790 sameAs 790.
- 790 abstract "In Japanese, the syntactic structure of a sentence is generally represented by the relationship between phrasal units, bunsetsus in Japanese, based on a dependency grammar. In many cases, the syntactic structure of a bunsetsu is not considered in syntactic structure annotation. This paper gives the criteria and definitions of dependency relationships between words in a bunsetsu and their applications. The target corpus for the word-level dependency annotation is a large spontaneous Japanese-speech corpus, the Corpus of Spontaneous Japanese (CSJ). One application of word-level dependency relationships is to find basic units for constructing accent phrases.".
- 790 hasAuthorList authorList.
- 790 hasTopic Linguistics.
- 790 isPartOf proceedings.
- 790 keyword "Corpus (creation, annotation, etc.)".
- 790 keyword "Speech resource/database".
- 790 keyword "Syntax".
- 790 title "Word-level Dependency-structure Annotation to Corpus of Spontaneous Japanese and its Application".
- 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 kiyotaka-uchimoto.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent yasuharu-den.
- item-2 previous item-1.
- 791 creator caroline-lavecchia.
- 791 creator david-langlois.
- 791 creator kamel-smaili.
- 791 type InProceedings.
- 791 label "Phrase-Based Machine Translation based on Simulated Annealing".
- 791 sameAs 791.
- 791 abstract "In this paper, we propose a new phrase-based translation model based on inter-lingual triggers. The originality of our method is double. First we identify common source phrases. Then we use inter-lingual triggers in order to retrieve their translations. Furthermore, we consider the way of extracting phrase translations as an optimization issue. For that we use simulated annealing algorithm to find out the best phrase translations among all those determined by inter-lingual triggers. The best phrases are those which improve the translation quality in terms of Bleu score. Tests are achieved on movie subtitle corpora. They show that our phrase-based machine translation (PBMT) system outperforms a state-of-the-art PBMT system by almost 7 points.".