| 1 |
Phrasal Spellout and Partial Overwrite: On an alternative to backtracking
|
|
|
|
In: Glossa: a journal of general linguistics; Vol 6, No 1 (2021); 62 ; 2397-1835 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Predicting Declension Class from Form and Meaning
|
|
|
|
In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs ...
|
|
Warstadt, Alex; Cao, Yu; Grosu, Ioana; Peng, Wei; Blix, Hagen; Nie, Yining; Alsop, Anna; Bordia, Shikha; Liu, Haokun; Parrish, Alicia; Wang, Sheng-Fu; Phang, Jason; Mohananey, Anhad; Htut, Phu Mon; Jeretič, Paloma; Bowman, Samuel R.. - : arXiv, 2019
|
|
Abstract:
Though state-of-the-art sentence representation models can perform tasks requiring significant knowledge of grammar, it is an open question how best to evaluate their grammatical knowledge. We explore five experimental methods inspired by prior work evaluating pretrained sentence representation models. We use a single linguistic phenomenon, negative polarity item (NPI) licensing in English, as a case study for our experiments. NPIs like "any" are grammatical only if they appear in a licensing environment like negation ("Sue doesn't have any cats" vs. "Sue has any cats"). This phenomenon is challenging because of the variety of NPI licensing environments that exist. We introduce an artificially generated dataset that manipulates key features of NPI licensing for the experiments. We find that BERT has significant knowledge of these features, but its success varies widely across different experimental methods. We conclude that a variety of methods is necessary to reveal all relevant aspects of a model's ... : Accepted to EMNLP 2019; Added link to code+dataset ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1909.02597
https://dx.doi.org/10.48550/arxiv.1909.02597
|
|
BASE
|
|
Hide details
|
|
|
|
|
