Naslov
Computational and Psycholinguistic Approaches to Structural Ambiguity: The Case of Garden Path Sentences

Autori
Bajac, Petra

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, diplomski rad, diplomski

Fakultet
Filozofski fakultet

Mjesto
Zagreb

Datum
03.07

Godina
2020

Stranica
54

Mentor
Zovko Dinković, Irena

Ključne riječi
computational linguistics, psycholinguistics, garden-path sentences, natural language processing, multidisciplinary research

Sažetak
By approaching the phenomenon of structural ambiguity from two different perspectives – psycholinguistic and computational, this thesis shows how linguistic research can have practical applications in improving NLP systems. The analyses of specific sentences show breakdowns in processing, present possible explanations behind them through principles such as Minimal Attachment/Late closure and Lexical preference, and demonstrate the backtracking needed in order to achieve a full, successful parsing of ambiguous sentences. The sentences chosen for research in this thesis are the so-called garden-path sentences, which induce a lot of difficulty in processing for both humans and machines, making them a perfect choice to demonstrate the similarities and differences between human and machine sentence processing. The research employs a combination of computational methods, both rule-based and statistical, and psycholinguistic hypotheses to explain the parsing process of garden-path sentences. The results show that in order for an NLP system to fully process highly ambiguous sentences such as these, it needs theoretical input to repair the partly parsed structures and successfully complete the parsing process. This implies a strong need for multidisciplinary research involving programmers, linguists, and cognitive scientists in order to succeed in emulating human intelligence in complex AI systems.

Izvorni jezik
Engleski

Znanstvena područja
Filologija

POVEZANOST RADA