Implicit Argument Prediction as Reading Comprehension

AAAI 2019 pp. 6284-6291

doi:10.1609/AAAI.V33I01.33016284 /aaai/2019/cheng2019aaai-implicit/

Abstract

Implicit arguments, which cannot be detected solely through syntactic cues, make it harder to extract predicate-argument tuples. We present a new model for implicit argument prediction that draws on reading comprehension, casting the predicate-argument tuple with the missing argument as a query. We also draw on pointer networks and multi-hop computation. Our model shows good performance on an argument cloze task as well as on a nominal implicit argument prediction task.

PDF AAAI Semantic Scholar

Cite

Text

Cheng and Erk. "Implicit Argument Prediction as Reading Comprehension." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33016284

Markdown

[Cheng and Erk. "Implicit Argument Prediction as Reading Comprehension." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/cheng2019aaai-implicit/) doi:10.1609/AAAI.V33I01.33016284

BibTeX

@inproceedings{cheng2019aaai-implicit,
  title     = {{Implicit Argument Prediction as Reading Comprehension}},
  author    = {Cheng, Pengxiang and Erk, Katrin},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {6284-6291},
  doi       = {10.1609/AAAI.V33I01.33016284},
  url       = {https://mlanthology.org/aaai/2019/cheng2019aaai-implicit/}
}