Computational Representation of Chinese Characters: Comparison Between Singular Value Decomposition and Variational Autoencoder
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Being a notoriously complex problem, writing is generally decomposed into a series of subtasks: idea generation, expression, revision, etc. Given some goal, the author generates a set of ideas (brainstorming), which he integrates into some skeleton (outline, text plan, outline). This leads to a first draft which is submitted then for revision possibly yielding changes at various levels (content, structure, form). Having made a draft, authors usually revise, edit, and proofread their documents. We confine ourselves here only to academic writing, focusing on sentence production. While there has been quite some work on this topic, most writing assistance has mainly dealt with grammatical errors, editing and proofreading, the goal being the correction of surface-level problems such as typography, spelling, or grammatical errors. We broaden the scope by also including cases where the entire sentence needs to be rewritten in order to express properly all of the information planned. Hence, Sentence-level Revision (SentRev) becomes part of our writing assistance task. Obviously, systems performing well in this task can be of considerable help for inexperienced authors by producing fluent, well-formed sentences based on the user’s drafts. In order to evaluate our SentRev model, we have built a new, freely available crowdsourced evaluation dataset which consists of a set of incomplete sentences produced by nonnative writers paired with final version sentences extracted from published academic papers. We also used this dataset to establish baseline performance on SentRev.
Abstract
Being a notoriously complex problem, writing is generally decomposed into a series of subtasks: idea generation, expression, revision, etc. Given some goal, the author generates a set of ideas (brainstorming), which he integrates into some skeleton (outline, text plan, outline). This leads to a first draft which is submitted then for revision possibly yielding changes at various levels (content, structure, form). Having made a draft, authors usually revise, edit, and proofread their documents. We confine ourselves here only to academic writing, focusing on sentence production. While there has been quite some work on this topic, most writing assistance has mainly dealt with grammatical errors, editing and proofreading, the goal being the correction of surface-level problems such as typography, spelling, or grammatical errors. We broaden the scope by also including cases where the entire sentence needs to be rewritten in order to express properly all of the information planned. Hence, Sentence-level Revision (SentRev) becomes part of our writing assistance task. Obviously, systems performing well in this task can be of considerable help for inexperienced authors by producing fluent, well-formed sentences based on the user’s drafts. In order to evaluate our SentRev model, we have built a new, freely available crowdsourced evaluation dataset which consists of a set of incomplete sentences produced by nonnative writers paired with final version sentences extracted from published academic papers. We also used this dataset to establish baseline performance on SentRev.
참고문헌 (27)
- Baayen, R. H., "An amorphous model for morphological processing in visual comprehension based on naive discriminative learning", Psychological review, 118, pp.438~481 (2011)
- Bansal, N., "Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?", Paper presented in 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) (2018)
- "Enriching Word Vectors with Subword Information" (2016)[URL]
- Chomsky, N., "Syntactic Structures" (1957), Mouton
- Christiansen, M. H., "The Now-or-Never bottleneck : A fundamental constraint on language", Behavioral and Brain Sciences, 39, pp.e62~ (2016)
- Chuang, D. M., "Database of Chinese character orthography: Development and application" (2005), International Conference on Chinese character and globalization
- Martha J. Farah, "The inverted face inversion effect in prosopagnosia : Evidence for mandatory, face-specifi c perceptual mechanisms", Vision Research, 35, pp.2089~2093 (1995)
- Goldberg, A. E., "The Oxford Handbook of Construction Grammar", pp.15~31 (2013), Oxford University Press
- Goodfellow, I., "Deep Learning" (2016), MIT Press
- Huang, Chu-Ren, "The Oxford handbook of Chinese linguistics", pp.290~305 (2015), Oxford University Press
- Kingma, D. P., "Auto-Encoding Variational Bayes", International Conference on Learning and Representation 2014 (2014)
- Kingma, D. P., "Adam: a method for stochastic optimization", International Conference on Learning and Representation 2015 (2015)
- "An introduction to variational autoencoders" (2019)[URL]
- Klys, J., "Learning latent subspaces in variational autoencoders", Paper presented in 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) (2018)
- Landauer, T. K., "A solution to Plato's problem : The latent semantic analysis theory of acquisition, induction, and representation of knowledge", Psychological review, 104, pp.211~ (1997)
- Lo, M., "C-CAT2 : A computer software used to analyze traditional and simplifi ed Chinese characters, character components and neighbors", Chinese Journal of Psychology, 54, pp.243~252 (2012)
- Long H., "Handwritten Chinese character recognition using eigenspace decomposition", Science China, 53, pp.1~10 (2011)
- McCauley, S. M., "Language learning as language use : A cross-linguistic model of child language development", Psychological Review, 126, pp.1~ (2019)
- Miller, G. A., "The magical number seven, plus or minus two : Some limits on our capacity for processing information", Psychological review, 101(2), pp.343~ (1956)
- Sirovich, L., "Low-dimensional procedure for the characterization of human faces", Journal of the Optical Society of America A, 4, pp.519~524 (1987)
- Taft, M., "Positional specificity of radicals in Chinese character recognition", Journal of Memory and Language, 40(4), pp.498~519 (1999)
- O’toole, A. J., "Structural aspects of face recognition and the other race effect", Memory & Cognition, 22, pp.208~224 (1994)
- Tseng, Y. H., "Eigencharacter: an embedding of Chinese character orthography", Paper presented in The First Workshop Beyond Vision and Language: integrating real-world knowledge, EMNLP-IJCNLP Workshop (2019)
- Yeh S. L., "Role of structure and component in judgments of visual similarity of Chinese characters", Journal of Experimental Psychology : Human Perception and Performance, 28, pp.933~947 (2002)
- Yeh, S. L., "Lexical processing of Chinese sub-character components : Semantic activation of phonetic radicals as revealed by the Stroop effect", Scientific Reports, 7, pp.15782~ (2017)
- Zhang, B., "Localization and functional characterization of an occipital visual word form sensitive area", Scientific Reports, pp.8~ (2018)
- Zock, M., "Recent Advances in Natural Language Processing. Series: Current Issues in Linguistic Theory", pp.317~352 (1997), Benjamins