Complex NP Island Constraints in English: Experimental vs. Deep Learning Approach
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper examined two types of complex NP island constraints (Appositives and Relatives) in English, with an experimental approach and a deep learning approach. In the experimental approach, this paper followed the design in Author (2018). A total of 120 sentences were employed in the experiment: 40 sentences for the target and 80 sentences for the fillers. For the deep learning approach, this paper utilized the BERT-LARGE model. The dataset was composed of 240 sentences: 40 sentences for the target and 200 sentences for the fillers. These 240 sentences were used as an input dataset to the BERT-LARGE model, and the acceptability scores were calculated for each sentence. After the acceptability scores were obtained for all the target sentences in two different types of approaches, they were normalized into the z-scores and statistical analyses were applied to them. Through the analysis, the followings were observed: (i) both the experimental approach and the BERT-LARGE model correctly identified two complex NP island constraints in English, (ii) two factors (Island and Location) and their interaction (Island:Location) affected the acceptability scores of island sentences, and (iii) two approaches made different predictions on the DD scores of the two complex NP island constraints.
Abstract
This paper examined two types of complex NP island constraints (Appositives and Relatives) in English, with an experimental approach and a deep learning approach. In the experimental approach, this paper followed the design in Author (2018). A total of 120 sentences were employed in the experiment: 40 sentences for the target and 80 sentences for the fillers. For the deep learning approach, this paper utilized the BERT-LARGE model. The dataset was composed of 240 sentences: 40 sentences for the target and 200 sentences for the fillers. These 240 sentences were used as an input dataset to the BERT-LARGE model, and the acceptability scores were calculated for each sentence. After the acceptability scores were obtained for all the target sentences in two different types of approaches, they were normalized into the z-scores and statistical analyses were applied to them. Through the analysis, the followings were observed: (i) both the experimental approach and the BERT-LARGE model correctly identified two complex NP island constraints in English, (ii) two factors (Island and Location) and their interaction (Island:Location) affected the acceptability scores of island sentences, and (iii) two approaches made different predictions on the DD scores of the two complex NP island constraints.
참고문헌 (53)
- Agarap, F, "Deep Learning Using Rectified Linear Units(ReLU)", arXiv Preprint arXiv:1803.08375, ~ (2018)
- Alexopoulou, T., "Locality, Cyclicity, and Resumption : At the Interface between the Grammar and the Human Sentence Processor", Language, 83, pp.110~160 (2007)
- Annamoradnejad, I., "ColBERT : Using BERT Sentence Embedding for Humor Detection", arXiv preprint arXiv:2004.12765, ~ (2020)
- Bard, E., "Magnitude Estimation of Linguistic Acceptability", Language, 72, pp.32~68 (1996)
- Barr, D., "Random Effects Structure for Confirmatory Hypothesis Testing", Journal of Memory and Language, 68, pp.255~278 (2013)
- Carnie, A., "Syntax: A Generative Introduction" (2021), Wiley Blackwell
- Charniak, E., "BLLIP 1987-89 WSJ Corpus Release 1 LDC2000T43" (2000), Linguistic Data Consortium
- Chomsky, N, "A festschrift for Morris Halle", pp.232~286 (1973), Rinehart and Winston
- Chomsky, N., "Barriers" (1986), MIT Press
- Chomsky, N, "Step by Step: Essays on Minimalist Syntax in Honor of Howard Lasnik", pp.89~157 (2000), MIT Press
- Cowart, W., "Experimental Syntax : Applying Objective Methods to Sentence Judgments" (1997), Sage Publications
- Devlin, J., "BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding", arXiv preprint arXiv:1810.04805, ~ (2019)
- Goldberg, Y, "Assessing BERT’s Syntactic Abilities", arXiv preprint arXiv: 1901.05287, ~ (2019)
- Goodfellow, I., "Deep Learning" (2016), MIT Press
- Gulordava, K., "Colorless Green Recurrent Networks Dream Hierarchically", arXiv preprint arXiv:1803.11138, ~ (2018)
- Hagstrom, P., "Decomposing Questions", pp.1998
- Hofmeister, P., "Cognitive Constraints on Syntactic Islands", Language, 86, pp.366~415 (2010)
- Hu, J., "A Closer Look at the Performance of Neural Language Models on Reflexive Anaphor Licensing", Proceedings of the Society for Computation in Linguistics, pp.323~333 (2020)
- Hu, J., "A Systematic Assessment of Syntactic Generalization in Neural Language Models", arXiv preprint arXiv:2005.03692, ~ (2020)
- Keller, F., "Gradient in Grammar : Experimental and Computational Aspects of Degrees of Grammaticality", Doctor, pp.2000
- Kluender, R, "On the Distinction between Strong and Weak Islands : A Processing Perspective", Syntax and Semantics, 29, pp.241~279 (1998)
- Kluender, R, "Are Subject Islands Subject to a Processing Account?", Proceedings of the West Coast Conference on Formal Linguistics, 23, pp.475~499 (2004)
- Kluender, R., "Subjacency as a Processing Phenomenon", Language and Cognitive Processes, 8, pp.573~633 (1993)
- Lasnik, H., "On the Nature of Proper Government", Linguistic Inquiry, 15, pp.235~289 (1984)
- Lee, Y., "Corpus Linguistics and Statistics Using R" (2016), Hankuk Publishing Co
- 이용훈, "English Island Constraints Revisited: Experimental vs. Deep Learning Approach", 영어학연구, 27(3), pp.21~45 (2021), 한국영어학학회[DOI]
- 이용훈, "English Island Constraints by Natives and Korean Non-natives", 언어연구, 34(3), pp.439~455 (2018), 한국현대언어학회[DOI]
- Levy, R, "Expectation-based Syntactic Comprehension", Cognition, 106, pp.1126~1177 (2008)
- Marvin, R., "Targeted Syntactic Evaluation of Language Models", arXiv preprint arXiv:1808.09031, ~ (2018)
- Maxwell, S., "Designing Experiments and Analyzing Data : A Model Comparison Perspective" (2003), Lawrence Erlbaum Associates
- Kwonsik Park, "Deep learning can contrast the minimal pairs of syntactic data", 언어연구, 38(2), pp.395~424 (2021), 언어정보연구소[DOI]
- 박연경, "English Island Sentences by Korean EFL Learners", 영어학연구, 24(1), pp.153~172 (2018), 한국영어학학회[DOI]
- R: A Language and Environment for Statistical Computing, "R Core Team", R Foundation for Statistical Computing, ~ (2021)
- Reinhart, T, "Quantifier Scope : How Labor Is Divided between QR and Choice Functions", Linguistics and Philosophy, 20, pp.335~397 (1997)
- Rizzi, L., "Relativized Minimality" (1990), MIT Press
- Ross, J., "Constraints on Variables in Syntax", Doctor, pp.1967
- Schütze, C., "The Empirical Base of Linguistics : Grammaticality Judgments and Linguistic Methodology" (1996), University of Chicago Press
- Sprouse, J, "Magnitude Estimation and the Non-Linearity of Acceptability Judgments", Proceedings of the 27th West Coast Conference on Formal Linguistics, pp.397~403 (2008)
- Sprouse, J., "Experimental Syntax and Island Effects" (2013), Cambridge University Press
- Sprouse, J., "A Test of the Relation between Working Memory Capacity and Syntactic Island Effects", Language, 88, pp.82~123 (2012)
- Szabolcsi, A, "The Blackwell Companion to Syntax", pp.479~531 (2007), Blackwell
- Szabolcsi, A., "Weak Islands and an Algebraic Semantics of Scope Taking", Natural Language Semantics, 1, pp.235~284 (1993)
- Truswell, R, "Extraction from Adjuncts and the Structure of Events", Lingua, 117, pp.1355~1377 (2007)
- Tsai, W, "On Nominal Islands and LF Extraction in Chinese", Natural Language and Linguistic Theory, 12, pp.121~175 (1994)
- Vaswani, A., "Attention Is All You Need", arXiv preprint arXiv:1706.03762, ~ (2017)
- Wang, A., "GLUE : A Multi-task Benchmark and Analysis Platform for Natural Language Understanding", arXiv preprint arXiv: 1804.07461, ~ (2019)
- Wang, A., "SuperGLUE : A Stickier Benchmark for General-purpose Language Understanding Systems", arXiv preprint arXiv:1905.00537, ~ (2020)
- Warstadt, A., "Investigating BERT’s Knowledge of Language : Five Analysis Methods with NPIs", arXiv preprint arXiv:1909.02597, ~ (2019)
- Warstadt, A., "Neural Network Acceptability Judgments", arXiv preprint arXiv:1805.12471, ~ (2019)
- Wilcox, E., "What Syntactic Structures Block Dependencies in RNN Language Models?", arXiv preprint arXiv:1905.10431, ~ (2019)
- Wilcox, E., "Hierarchical Representation in Neural Language Models: Suppression and Recovery of Expectations", arXiv preprint arXiv:1906.04068, ~ (2019)
- Wilcox, E., "What Do RNN Language Models Learn about Filler-Gap Dependencies?", arXiv preprint arXiv:1809.00042, ~ (2018)
- Zhu, Y., "Aligning Books and Movies : Towards Story-like Visual Explanations by Watching Movies and Reading Books", Proceedings of the IEEE International Conference on Computer Vision, pp.19~27 (2015)