FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W103796002> ?p ?o ?g. }

• W103796002 abstract "Parsing discourse is a challenging natural language processing task. In this research work first we take a data driven approach to identify arguments of explicit discourse connectives. In contrast to previous work we do not make any assumptions on the span of arguments and consider parsing as a token-level sequence labeling task. We design the argument segmentation task as a cascade of decisions based on conditional random fields (CRFs). We train the CRFs on lexical, syntactic and semantic features extracted from the Penn Discourse Treebank and evaluate feature combinations on the commonly used test split. We show that the best combination of features includes syntactic and semantic features. The comparative error analysis investigates the performance variability over connective types and argument positions. We also compare the results of cascaded pipeline with a non-cascaded structured prediction setting that shows us definitely the cascaded structured prediction is a better performing method for discourse parsing.We present a novel end-to-end discourse parser that, given a plain text document in input, identifies the discourse relations in the text, assigns them a semantic label and detects discourse arguments spans. The parsing architecture is based on a cascade of decisions supported by Conditional Random Fields (CRF). We train and evaluate three different parsers using the PDTB corpus. The three system versions are compared to evaluate their robustness with respect to deep/shallow and automatically extracted syntactic features.Next, we describe two constraint-based methods that can be used to improve the recall of a shallow discourse parser based on conditional random field chunking.These method uses a set of natural structural constraints as well as others that follow from the annotation guidelines of the Penn Discourse Treebank.We evaluated the resulting systems on the standard test set of the PDTB and achieved a rebalancing of precision and recall with improved F-measures across the board. This was especially notable when we used evaluation metrics taking partial matches into account; for these measures, we achieved F-measure improvements of several points. Finally, we address the problem of optimization in discourse parsing.A good model for discourse structure analysis needs to account both for local dependencies at the token-level and for global dependencies and statistics. We present techniques on using inter-sentential or sentence-level(global), data-driven, non-grammatical features in the task of parsing discourse.The parser model follows up previous approach based on using token-level (local) features with conditional random fields for shallow discourse parsing, which is lacking in structural knowledge of discourse. The parser adopts a two-stage approach where first the local constraints are applied and then global constraints are used on a reduced weighted search space ($n$-best). In the latter stage we experiment with different rerankers trained on the first stage $n$-best parses, which are generated using lexico-syntactic local features. The two-stage parser yields significant improvements over the best performing model of discourse parser on the PDTB corpus." @default.
• W103796002 created "2016-06-24" @default.
• W103796002 creator A5071643881 @default.
• W103796002 date "2012-04-11" @default.
• W103796002 modified "2023-09-28" @default.
• W103796002 title "End-to-End Discourse Parsing with Cascaded Structured Prediction" @default.
• W103796002 hasPublicationYear "2012" @default.
• W103796002 type Work @default.
• W103796002 sameAs 103796002 @default.
• W103796002 citedByCount "1" @default.
• W103796002 countsByYear W1037960022013 @default.
• W103796002 crossrefType "dissertation" @default.
• W103796002 hasAuthorship W103796002A5071643881 @default.
• W103796002 hasConcept C152565575 @default.
• W103796002 hasConcept C154945302 @default.
• W103796002 hasConcept C186644900 @default.
• W103796002 hasConcept C204321447 @default.
• W103796002 hasConcept C206134035 @default.
• W103796002 hasConcept C2775953691 @default.
• W103796002 hasConcept C2777530160 @default.
• W103796002 hasConcept C41008148 @default.
• W103796002 hasConcept C67277372 @default.
• W103796002 hasConceptScore W103796002C152565575 @default.
• W103796002 hasConceptScore W103796002C154945302 @default.
• W103796002 hasConceptScore W103796002C186644900 @default.
• W103796002 hasConceptScore W103796002C204321447 @default.
• W103796002 hasConceptScore W103796002C206134035 @default.
• W103796002 hasConceptScore W103796002C2775953691 @default.
• W103796002 hasConceptScore W103796002C2777530160 @default.
• W103796002 hasConceptScore W103796002C41008148 @default.
• W103796002 hasConceptScore W103796002C67277372 @default.
• W103796002 hasLocation W1037960021 @default.
• W103796002 hasOpenAccess W103796002 @default.
• W103796002 hasPrimaryLocation W1037960021 @default.
• W103796002 hasRelatedWork W1517148511 @default.
• W103796002 hasRelatedWork W1563792215 @default.
• W103796002 hasRelatedWork W1569397218 @default.
• W103796002 hasRelatedWork W1810532455 @default.
• W103796002 hasRelatedWork W2052369622 @default.
• W103796002 hasRelatedWork W2118871236 @default.
• W103796002 hasRelatedWork W2120262106 @default.
• W103796002 hasRelatedWork W2154407881 @default.
• W103796002 hasRelatedWork W2251201446 @default.
• W103796002 hasRelatedWork W2251249019 @default.
• W103796002 hasRelatedWork W2251285603 @default.
• W103796002 hasRelatedWork W2251790405 @default.
• W103796002 hasRelatedWork W2408247135 @default.
• W103796002 hasRelatedWork W2516462586 @default.
• W103796002 hasRelatedWork W2783661857 @default.
• W103796002 hasRelatedWork W2795277576 @default.
• W103796002 hasRelatedWork W2905102582 @default.
• W103796002 hasRelatedWork W2912327294 @default.
• W103796002 hasRelatedWork W2949072528 @default.
• W103796002 hasRelatedWork W2975928086 @default.
• W103796002 isParatext "false" @default.
• W103796002 isRetracted "false" @default.
• W103796002 magId "103796002" @default.
• W103796002 workType "dissertation" @default.