Matches in ScholarlyData for { ?s ?p ?o. }
- item-4 type ListItem.
- item-4 hasContent torbjoern-svendsen.
- item-4 previous item-3.
- 487 creator olga-uryupina.
- 487 type InProceedings.
- 487 label "Error Analysis for Learning-based Coreference Resolution".
- 487 sameAs 487.
- 487 abstract "State-of-the-art coreference resolution engines show similar performance figures (low sixties on the MUC-7 data). Our system with a rich linguistically motivated feature set yields significantly better performance values for a variety of machine learners, but still leaves substantial room for improvement. In this paper we address a relatively unexplored area of coreference resolution - we present a detailed error analysis in order to understand the issues raised by corpus-based approaches to coreference resolution.".
- 487 hasAuthorList authorList.
- 487 hasTopic Linguistics.
- 487 isPartOf proceedings.
- 487 keyword "Anaphora, Coreference".
- 487 keyword "Discourse".
- 487 keyword "Statistical methods".
- 487 title "Error Analysis for Learning-based Coreference Resolution".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasLastItem item-1.
- item-1 type ListItem.
- item-1 hasContent olga-uryupina.
- 49 creator anne-marie-mineur.
- 49 creator frederik-coppens.
- 49 creator geert-kloosterman.
- 49 creator gosse-bouma.
- 49 creator iris-hendrickx.
- 49 creator jean-luc-verschelde.
- 49 creator joeri-van-der-vloet.
- 49 creator veronique-hoste.
- 49 creator walter-daelemans.
- 49 type InProceedings.
- 49 label "A Coreference Corpus and Resolution System for Dutch".
- 49 sameAs 49.
- 49 abstract "We present the main outcomes of the COREA project: a corpus annotated with coreferential relations and a coreference resolution system for Dutch. In the project we developed annotation guidelines for coreference resolution for Dutch and annotated a corpus of 135K tokens. We discuss these guidelines, the annotation tool, and the inter-annotator agreement. We also show a visualization of the annotated relations. The standard approach to evaluate a coreference resolution system is to compare the predictions of the system to a hand-annotated gold standard test set (cross-validation). A more practically oriented evaluation is to test the usefulness of coreference relation information in an NLP application. We run experiments with an Information Extraction module for the medical domain, and measure the performance of this module with and without the coreference relation information. We present the results of both this application-oriented evaluation of our system and of a standard cross-validation evaluation. In a separate experiment we also evaluate the effect of coreference information produced by a simple rule-based coreference module in a Question Answering application.".
- 49 hasAuthorList authorList.
- 49 hasTopic Linguistics.
- 49 isPartOf proceedings.
- 49 keyword "Anaphora, Coreference".
- 49 keyword "LR Infrastructures and Architectures".
- 49 keyword "Tools, systems, applications".
- 49 title "A Coreference Corpus and Resolution System for Dutch".
- 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 hasItem item-7.
- authorList hasItem item-8.
- authorList hasItem item-9.
- authorList hasLastItem item-9.
- item-1 type ListItem.
- item-1 hasContent iris-hendrickx.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent gosse-bouma.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent frederik-coppens.
- item-3 next item-4.
- item-3 previous item-2.
- item-4 type ListItem.
- item-4 hasContent walter-daelemans.
- item-4 next item-5.
- item-4 previous item-3.
- item-5 type ListItem.
- item-5 hasContent veronique-hoste.
- item-5 next item-6.
- item-5 previous item-4.
- item-6 type ListItem.
- item-6 hasContent geert-kloosterman.
- item-6 next item-7.
- item-6 previous item-5.
- item-7 type ListItem.
- item-7 hasContent anne-marie-mineur.
- item-7 next item-8.
- item-7 previous item-6.
- item-8 type ListItem.
- item-8 hasContent joeri-van-der-vloet.
- item-8 next item-9.
- item-8 previous item-7.
- item-9 type ListItem.
- item-9 hasContent jean-luc-verschelde.
- item-9 previous item-8.
- 490 creator antonella-bristot.
- 490 creator rodolfo-delmonte.
- 490 creator sara-tonelli.
- 490 type InProceedings.
- 490 label "Enriching the Venice Italian Treebank with Dependency and Grammatical Relations".
- 490 sameAs 490.
- 490 abstract "In this paper we propose a rule-based approach to extract dependency and grammatical functions from the Venice Italian Treebank, a Treebank of written text with PoS and constituent labels consisting of 10,200 utterances and about 274,000 tokens. As manual corpus annotation is expensive and time-consuming, we decided to exploit this existing constituency-based Treebank to derive dependency structures with lower effort. After describing the procedure to extract heads and dependents, based on a head percolation table for Italian, we introduce the rules adopted to add grammatical relation labels. To this purpose, we manually relabeled all non-canonical arguments, which are very frequent in Italian, then we automatically labeled the remaining complements or arguments following some syntactic restrictions based on the position of the constituents w.r.t to parent and sibling nodes. The final section of the paper describes evaluation results. Evaluation was carried out in two steps, one for dependency relations and one for grammatical roles. Results are in line with similar conversion algorithms carried out for other languages, with 0.97 precision on dependency arcs and F-measure for the main grammatical functions scoring 0.96 or above, except for obliques with 0.75.".
- 490 hasAuthorList authorList.
- 490 hasTopic Linguistics.
- 490 isPartOf proceedings.
- 490 keyword "Corpus (creation, annotation, etc.)".
- 490 keyword "Syntax".
- 490 keyword "Tagging".