Predicting Non-Restrictive Noun Phrase Modifications Through Deep Semantic Analysis
CitationBal, Mustafa. 2019. Predicting Non-Restrictive Noun Phrase Modifications Through Deep Semantic Analysis. Bachelor's thesis, Harvard College.
AbstractThe difference between restrictive and non-restrictive modifier clauses has been well documented in linguistics. A model that can distinguish non-restrictive modifiers from restrictive modifiers can provide shorter sentences for Natural Language Processing applications3 and improve personal voice assistants in sounding more natural to users. Previous research has provided an annotated corpus and a relatively successful model that predicts non-restrictive modifiers in given sentences. However, this model suffers when faced with prepositional and adjectival modifiers. By utilizing this annotated corpus and learning from previously existing literature, we have made a model that can successfully predict non-restrictive noun phrase modifications through deeper semantic analysis while also performing better with prepositional and adjectival modifiers.
Citable link to this pagehttps://nrs.harvard.edu/URN-3:HUL.INSTREPOS:37364649
- FAS Theses and Dissertations