35 citations · 65 across the 2 of their papers we have counts for
3 papers
cs.CL2020★ 30 cited
A Systematic Analysis of Morphological Content in BERT Models for Multiple Languages
Daniel Edmiston
This work describes experiments which probe the hidden representations of several BERT-style models for morphological content. The goal is to examine the extent to which discrete l…
cs.CL2020★ 35 cited
Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction
Taeuk Kim, Jihun Choi, Daniel Edmiston +1
With the recent success and popularity of pre-trained language models (LMs) in natural language processing, there has been a rise in efforts to understand their inner workings. In…
cs.CL2018
Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations
Taeuk Kim, Jihun Choi, Daniel Edmiston +2
Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We pres…