1 |
Horse or pony? Visual Typicality and Lexical Frequency Affect Variability in Object Naming ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
The interaction between cognitive ease and informativeness shapes the lexicons of natural languages ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Horse or pony? Visual Typicality and Lexical Frequency Affect Variability in Object Naming
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
4 |
The interaction between cognitive ease and informativeness shapes the lexicons of natural languages
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution ...
|
|
|
|
Abstract:
It is often posited that more predictable parts of a speaker's meaning tend to be made less explicit, for instance using shorter, less informative words. Studying these dynamics in the domain of referring expressions has proven difficult, with existing studies, both psycholinguistic and corpus-based, providing contradictory results. We test the hypothesis that speakers produce less informative referring expressions (e.g., pronouns vs. full noun phrases) when the context is more informative about the referent, using novel computational estimates of referent predictability. We obtain these estimates training an existing coreference resolution system for English on a new task, masked coreference resolution, giving us a probability distribution over referents that is conditioned on the context but not the referring expression. The resulting system retains standard coreference resolution performance while yielding a better estimate of human-derived referent predictability than previous attempts. A statistical ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2109.13105 https://arxiv.org/abs/2109.13105
|
|
BASE
|
|
Hide details
|
|
7 |
Deep daxes: Mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
A closer look at scalar diversity using contextualized semantic similarity
|
|
|
|
In: Sinn und Bedeutung; Bd. 24 Nr. 2 (2020): Proceedings of Sinn und Bedeutung 24; 439-454 ; Proceedings of Sinn und Bedeutung; Vol 24 No 2 (2020): Proceedings of Sinn und Bedeutung 24; 439-454 ; 2629-6055 (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Recurrent Instance Segmentation using Sequences of Referring Expressions ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Don't Blame Distributional Semantics if it can't do Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
What do Entity-Centric Models Learn? Insights from Entity Linking in Multi-Party Dialogue ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Putting words in context: LSTM language models and lexical ambiguity ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Living a discrete life in a continuous world: Reference with distributed representations ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
The LAMBADA dataset: Word prediction requiring a broad discourse context ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
"Show me the cup": Reference with Continuous Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Zipf’s Law for Word Frequencies: Word Forms versus Lemmas in Long Texts
|
|
|
|
BASE
|
|
Show details
|
|
|
|