Discourse Relations and Conjoined VPs: Automated Sense Recognition
| Autor: | Valentina Pyatkin, Bonnie Webber |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Discourse relation
Parsing Computer science business.industry linguistics computational linguistics discourse parser Verb 02 engineering and technology computer.software_genre Pipeline (software) Linguistics 030507 speech-language pathology & audiology 03 medical and health sciences ComputingMethodologies_PATTERNRECOGNITION 0202 electrical engineering electronic engineering information engineering Feature (machine learning) 020201 artificial intelligence & image processing Artificial intelligence 0305 other medical science business computer Scope (computer science) Natural language processing |
| Zdroj: | EACL (Student Research Workshop) |
| DOI: | 10.18653/v1/e17-4004 |
| Popis: | Sense classification of discourse relations is a sub-task of shallow discourse parsing. Discourse relations can occur both across sentences (inter-sentential) and within sentences (intra-sentential), and more than one discourse relation can hold between the same units. Using a newly available corpus of discourse-annotated intra-sentential conjoined verb phrases, we demonstrate a sequential classification pipeline for their multi-label sense classification. We assess the importance of each feature used in the classification, the feature scope, and what is lost in moving from gold standard manual parses to the output of an off-the-shelf parser. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|