2 |
How Furiously Can Colourless Green Ideas Sleep? Sentence Acceptability in Context ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Ellipsis Resolution at S-Structure
|
|
|
|
In: North East Linguistics Society (2020)
|
|
BASE
|
|
Show details
|
|
4 |
Predication and Raising
|
|
|
|
In: North East Linguistics Society (2020)
|
|
BASE
|
|
Show details
|
|
5 |
θ-Roles and NP Movement
|
|
|
|
In: North East Linguistics Society (2020)
|
|
BASE
|
|
Show details
|
|
6 |
How Furiously Can Colorless Green Ideas Sleep? Sentence Acceptability in Context
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 8, Pp 296-310 (2020) (2020)
|
|
Abstract:
We study the influence of context on sentence acceptability. First we compare the acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our results show that context induces a cognitive load for humans, which compresses the distribution of ratings. Moreover, in relevant contexts we observe a discourse coherence effect that uniformly raises acceptability. Next, we test unidirectional and bidirectional language models in their ability to predict acceptability ratings. The bidirectional models show very promising results, with the best model achieving a new state-of-the-art for unsupervised acceptability prediction. The two sets of experiments provide insights into the cognitive aspects of sentence processing and central issues in the computational modeling of text and discourse.
|
|
Keyword:
Computational linguistics. Natural language processing; P98-98.5
|
|
URL: https://doaj.org/article/c0c8c94e11234a2194b475c938f95f09 https://doi.org/10.1162/tacl_a_00315
|
|
BASE
|
|
Hide details
|
|
11 |
The Probabilistic Representation of Linguistic Knowledge: Linguistic Data Sets Annotated for Grammatical Acceptability ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Type-theoretic logic with an operational account of intensionality
|
|
|
|
BASE
|
|
Show details
|
|
|
|