41 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
42 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
43 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
44 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
45 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
46 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
47 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
48 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
49 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
50 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
51 |
Definiteness across languages
|
|
|
|
In: Language Science Press; (2019)
|
|
BASE
|
|
Show details
|
|
52 |
A morpho-semantic account of weak definites and bare institutional singulars in English ...
|
|
|
|
BASE
|
|
Show details
|
|
53 |
A morpho-semantic account of weak definites and bare institutional singulars in English ...
|
|
|
|
BASE
|
|
Show details
|
|
54 |
Verb Argument Structure Alternations in Word and Sentence Embeddings
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2019)
|
|
BASE
|
|
Show details
|
|
55 |
Representing Relationality: MEG Studies on Argument Structure
|
|
|
|
BASE
|
|
Show details
|
|
56 |
XNLI: Evaluating Cross-lingual Sentence Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
57 |
Verb Argument Structure Alternations in Word and Sentence Embeddings ...
|
|
|
|
Abstract:
Verbs occur in different syntactic environments, or frames. We investigate whether artificial neural networks encode grammatical distinctions necessary for inferring the idiosyncratic frame-selectional properties of verbs. We introduce five datasets, collectively called FAVA, containing in aggregate nearly 10k sentences labeled for grammatical acceptability, illustrating different verbal argument structure alternations. We then test whether models can distinguish acceptable English verb-frame combinations from unacceptable ones using a sentence embedding alone. For converging evidence, we further construct LaVA, a corresponding word-level dataset, and investigate whether the same syntactic features can be extracted from word embeddings. Our models perform reliable classifications for some verbal alternations but not others, suggesting that while these representations do encode fine-grained lexical information, it is incomplete or can be hard to extract. Further, differences between the word- and ... : Accepted to SCiL 2019 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1811.10773 https://arxiv.org/abs/1811.10773
|
|
BASE
|
|
Hide details
|
|
58 |
The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|