1 |
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Positional Artefacts Propagate Through Masked Language Model Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Attention Can Reflect Syntactic Structure (If You Let It) ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Schrödinger's Tree -- On Syntax and Neural Language Models ...
|
|
|
|
Abstract:
In the last half-decade, the field of natural language processing (NLP) has undergone two major transitions: the switch to neural networks as the primary modeling paradigm and the homogenization of the training regime (pre-train, then fine-tune). Amidst this process, language models have emerged as NLP's workhorse, displaying increasingly fluent generation capabilities and proving to be an indispensable means of knowledge transfer downstream. Due to the otherwise opaque, black-box nature of such models, researchers have employed aspects of linguistic theory in order to characterize their behavior. Questions central to syntax -- the study of the hierarchical structure of language -- have factored heavily into such work, shedding invaluable insights about models' inherent biases and their ability to make human-like generalizations. In this paper, we attempt to take stock of this growing body of literature. In doing so, we observe a lack of clarity across numerous dimensions, which influences the hypotheses ... : preprint, submitted to Frontiers in Artificial Intelligence: Perspectives for Natural Language Processing between AI, Linguistics and Cognitive Science ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2110.08887 https://dx.doi.org/10.48550/arxiv.2110.08887
|
|
BASE
|
|
Hide details
|
|
5 |
Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Do Neural Language Models Show Preferences for Syntactic Formalisms? ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing -- A Tale of Two Parsers Revisited ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|