1 |
Finding the best way to put media bias research into practice via an annotation app ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Are neural language models sensitive to false belief? A computational study. ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Similarity between person roles in a card sorting experiment ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Statistical detection of format dialects using the weighted Dowker complex ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Clustering and compatibility-based approach for large-scale group decision making with hesitant fuzzy linguistic preference relations: An application in e-waste recycling ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Identifying the preschool home learning experiences that predict early number skills: Evidence from a longitudinal study ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Can distributional semantics explain performance on the false belief task? ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Characterizing News Portrayal of Civil Unrest in Hong Kong, 1998–2020 ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Elastic Full Procrustes Analysis of Plane Curves via Hermitian Covariance Smoothing ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
An enriched category theory of language: from syntax to semantics ...
|
|
|
|
Abstract:
State of the art language models return a natural language text continuation from any piece of input text. This ability to generate coherent text extensions implies significant sophistication, including a knowledge of grammar and semantics. In this paper, we propose a mathematical framework for passing from probability distributions on extensions of given texts, such as the ones learned by today's large language models, to an enriched category containing semantic information. Roughly speaking, we model probability distributions on texts as a category enriched over the unit interval. Objects of this category are expressions in language, and hom objects are conditional probabilities that one expression is an extension of another. This category is syntactical -- it describes what goes with what. Then, via the Yoneda embedding, we pass to the enriched category of unit interval-valued copresheaves on this syntactical category. This category of enriched copresheaves is semantic -- it is where we find meaning, ... : 29 pages; v2 major revision with new proofs and computations ...
|
|
Keyword:
Category Theory math.CT; Computation and Language cs.CL; FOS Computer and information sciences; FOS Mathematics
|
|
URL: https://arxiv.org/abs/2106.07890 https://dx.doi.org/10.48550/arxiv.2106.07890
|
|
BASE
|
|
Hide details
|
|
18 |
Development of language and the use of musical engagement as a stress coping mechanism during the COVID-19 pandemic ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Measuring Equity Mindsets and Improvisational Practices Through Language Patterns in Equity Simulations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|