Matches in ScholarlyData for { ?s ?p ?o. }
- item-2 hasContent rada-mihalcea.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent janyce-wiebe.
- item-3 previous item-2.
- 702 creator jose-iria.
- 702 creator lei-xia.
- 702 type InProceedings.
- 702 label "An Approach to Modeling Heterogeneous Resources for Information Extraction".
- 702 sameAs 702.
- 702 abstract "In this paper, we describe an approach that aims to model heterogeneous resources for information extraction. Document is modeled in graph representation that enables better understanding of multi-media document and its structure which ultimately could result better cross-media information extraction. We also describe our proposed algorithm that segment document-based on the document modeling approach we described in this paper.".
- 702 hasAuthorList authorList.
- 702 hasTopic Linguistics.
- 702 isPartOf proceedings.
- 702 keyword "Information Extraction, Information Retrieval".
- 702 keyword "Knowledge representation".
- 702 keyword "Tools, systems, applications".
- 702 title "An Approach to Modeling Heterogeneous Resources for Information Extraction".
- 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 lei-xia.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent jose-iria.
- item-2 previous item-1.
- 706 creator ann-bies.
- 706 creator mohamed-maamouri.
- 706 creator seth-kulick.
- 706 type InProceedings.
- 706 label "Diacritic Annotation in the Arabic Treebank and its Impact on Parser Evaluation".
- 706 sameAs 706.
- 706 abstract "The Arabic Treebank (ATB), released by the Linguistic Data Consortium, contains multiple annotation files for each source file, due in part to the role of diacritic inclusion in the annotation process. The data is made available in both vocalized and unvocalized forms, with and without the diacritic marks, respectively. Much parsing work with the ATB has used the unvocalized form, on the basis that it more closely represents the real-world situation. We point out some problems with this usage of the unvocalized data and explain why the unvocalized form does not in fact represent real-world data. This is due to some aspects of the treebank annotation that to our knowledge have never before been published.".
- 706 hasAuthorList authorList.
- 706 hasTopic Linguistics.
- 706 isPartOf proceedings.
- 706 keyword "Corpus (creation, annotation, etc.)".
- 706 keyword "Morphology".
- 706 keyword "Parsing Systems".
- 706 title "Diacritic Annotation in the Arabic Treebank and its Impact on Parser Evaluation".
- 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 mohamed-maamouri.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent seth-kulick.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent ann-bies.
- item-3 previous item-2.
- 707 creator viktor-tron.
- 707 type InProceedings.
- 707 label "On the Durational Reduction of Repeated Mentions: Recency and Speaker Effects".
- 707 sameAs 707.
- 707 abstract "There are conflicting views in the literature as to the role of listener-adaptive processes in language production in general and articulatory reduction in particular. We present two novel pieces of corpus evidence that corroborate the hypothesis that non-lexical variation of durations is related to the speed of retrieval of stored motor code chunks and durational reduction is the result of facilitatory priming.".
- 707 hasAuthorList authorList.
- 707 hasTopic Linguistics.
- 707 isPartOf proceedings.
- 707 keyword "Phonetic Databases, Phonology".
- 707 keyword "Speech recognition and understanding".
- 707 keyword "Speech resource/database".
- 707 title "On the Durational Reduction of Repeated Mentions: Recency and Speaker Effects".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent viktor-tron.
- 709 creator janyce-wiebe.
- 709 creator josef-ruppenhofer.
- 709 creator swapna-somasundaran.
- 709 type InProceedings.
- 709 label "Finding the Sources and Targets of Subjective Expressions".
- 709 sameAs 709.
- 709 abstract "As many popular text genres such as blogs or news contain opinions by multiple sources and about multiple targets, finding the sources and targets of subjective expressions becomes an important sub-task for automatic opinion analysis systems. We argue that while automatic semantic role labeling systems (ASRL) have an important contribution to make, they cannot solve the problem for all cases. Based on the experience of manually annotating opinions, sources, and targets in various genres, we present linguistic phenomena that require knowledge beyond that of ASRL systems. In particular, we address issues relating to the attribution of opinions to sources; sources and targets that are realized as zero-forms; and inferred opinions. We also discuss in some depth that for arguing attitudes we need to be able to recover propositions and not only argued-about entities. A recurrent theme of the discussion is that close attention to specific discourse contexts is needed to identify sources and targets correctly.".
- 709 hasAuthorList authorList.
- 709 hasTopic Linguistics.
- 709 isPartOf proceedings.
- 709 keyword "Corpus (creation, annotation, etc.)".
- 709 keyword "Other".
- 709 keyword "Semantics".
- 709 title "Finding the Sources and Targets of Subjective Expressions".
- 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 josef-ruppenhofer.