Discourse Parsing: Inferring Discourse Structure, Modeling Coherence, and Its Applications - Ziheng Lin - Böcker - LAP LAMBERT Academic Publishing - 9783659341939 - 27 februari 2013
Om omslag och titel inte matchar är det titeln som gäller

Discourse Parsing: Inferring Discourse Structure, Modeling Coherence, and Its Applications

Pris
SEK 2.479
inkl. 6% moms vid leverans till Sverige

Beställningsvara

Förväntad leverans 9 - 17 dec
Julklappar kan bytas fram till 31:e januari
Få avisering om nya utgåvor med Ziheng Lin
Lägg till din iMusic-önskelista
eller

Inte betygsatt ännu

We investigate a natural language problem of parsing a free text into its discourse structure. Specifically, we look at how to parse free texts in the Penn Discourse Treebank representation in a fully data-driven approach. We first propose a classifier to tackle the hard problem of Implicit discourse relation classification. We then design a parsing algorithm and implement it into a full parser in a pipeline. We present a comprehensive evaluation on the parser from both component-wise and error-cascading perspectives. Textual coherence is strongly connected to a text's discourse structure. We present a novel model to represent and assess the discourse coherence of a text with the use of our discourse parser. Our model assumes that coherent text implicitly favors certain types of discourse relation transitions. We implement this model and apply it towards the text ordering ranking task, which aims to discern an original text from a permuted ordering of its sentences. Lastly, we demonstrate that incorporating discourse features can significantly improve two downstream natural language processing (NLP) tasks -- argumentative zoning and summarization -- in the scholarly domain.

Media Böcker     Pocketbok   (Bok med mjukt omslag och limmad rygg)
Releasedatum 27 februari 2013
ISBN13 9783659341939
Utgivare LAP LAMBERT Academic Publishing
Antal sidor 184
Mått 152 × 229 × 11 mm   ·   292 g
Språk Tyska