2019 Fiscal Year Annual Research Report
Developing a learner-adaptive captioning system to improve second language listening
| Project/Area Number |
17K02925
|
|---|
| Research Institution | Institute of Physical and Chemical Research |
|---|
Principal Investigator |
MESHGI Kourosh 国立研究開発法人理化学研究所, 革新知能統合研究センター, 研究員 (80774835)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
Mirzaei Maryam 国立研究開発法人理化学研究所, 革新知能統合研究センター, 特別研究員 (10810509)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Keywords | PSC / Surprisal Model / Cognitive Load / Lexical Complexity / Syntactic Complexity / NLP |
|---|
| Outline of Annual Research Achievements |
We constructed a data-driven surprisal model to assess the lexical and syntactic complexity of the listening material to provide necessary scaffold learners. We observed that encountering a word or sentence structure different from her expectation, learner's attention is confined, leading to confusion, cognitive overload, and misrecognition. We developed language models that adapt to learner proficiency and compute syntactic surprisal using the structural confusion of a sentence recovered by a probabilistic grammar/parser.
M.S. Mirzaei, K. Meshgi, and T. Nishida “Sentence Complexity as an Indicator of L2 Learner's Listening Difficulty,” In Proc. of EuroCALL'20, Copenhagen, Denmark, Aug 2020.
|
