상세정보
Export to Refworks부가기능
Do It Like a Syntactician: Using Binary Grammaticality Judgements to Train Sentence Encoders and Assess Their Sensitivity to Syntactic Structure
상세 프로파일
| 자료유형 | 학위논문 |
|---|---|
| 서명/저자사항 | Do It Like a Syntactician: Using Binary Grammaticality Judgements to Train Sentence Encoders and Assess Their Sensitivity to Syntactic Structure. |
| 개인저자 | Gonzalez Martinez, Pablo . |
| 단체저자명 | City University of New York. Linguistics. |
| 발행사항 | [S.l.]: City University of New York., 2019. |
| 발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
| 형태사항 | 105 p. |
| 기본자료 저록 | Dissertations Abstracts International 81-04B. Dissertation Abstract International |
| ISBN | 9781392688106 |
| 학위논문주기 | Thesis (Ph.D.)--City University of New York, 2019. |
| 일반주기 |
Source: Dissertations Abstracts International, Volume: 81-04, Section: B.
Advisor: Sakas, William. |
| 이용제한사항 | This item must not be sold to any third party vendors. |
| 요약 | The binary nature of grammaticality judgments and their use to access the structure of syntax are a staple of modern linguistics. However, computational models of natural language rarely make use of grammaticality in their training or application. Furthermore, developments in modern neural NLP have produced a myriad of methods that push the baselines in many complex tasks, but those methods are typically not evaluated from a linguistic perspective. In this dissertation I use grammaticality judgements with artificially generated ungrammatical sentences to assess the performance of several neural encoders and propose them as a suitable training target to make models learn specific syntactic rules. I generate artificial ungrammatical sentences via two methods. First by randomly pulling words following the n-gram distribution of a corpus of real sentences (I call these Word salads). Second, by corrupting sentences from a real corpus by altering them (changing verbal or adjectival agreement or removing the main verb). We then train models with an encoder using word embeddings and long short term memory (LSTMs) to discriminate between real sentences and ungrammatical sentences. We show that word salads can be distinguished by the model well for low order n-grams but that the model does not generalize well for higher orders. Furthermore, the word salads do not help the model in recognizing corrupted sentences. We then test the contributions of pre-trained word embeddings, deep LSTM and bidirectional LSTM. We find that the biggest contribution is adding pre-trained word embeddings. We also find that additional layers contribute differently to the performance of unidirectional and bidirectional models and that deeper models have more performance variability across training runs. |
| 일반주제명 | Linguistics. Computer science. Artificial intelligence. |
| 언어 | 영어 |
| 바로가기 | 
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |
