activity
20192022
most citedImproving BERT Pretraining with Syntactic Supervision

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CL2022

Discontinuous Constituency and BERT: A Case Study of Dutch

Konstantinos Kogkalidis, Gijs Wijnholds

In this paper, we set out to quantify the syntactic capacity of BERT in the evaluation regime of non-context free patterns, as occurring in Dutch. We devise a test suite based on a…

cs.CL20211 cited

Improving BERT Pretraining with Syntactic Supervision

Giorgos Tziafas, Konstantinos Kogkalidis, Gijs Wijnholds +1

Bidirectional masked Transformers have become the core theme in the current NLP landscape. Despite their impressive benchmarks, a recurring theme in recent research has been to que…

cs.CL2021

Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble

Giorgos Tziafas, Konstantinos Kogkalidis, Tommaso Caselli

This paper describes the TOKOFOU system, an ensemble model for misinformation detection tasks based on six different transformer-based pre-trained encoders, implemented in the cont…

cs.CL2020

Neural Proof Nets

Konstantinos Kogkalidis, Michael Moortgat, Richard Moot

Linear logic and the linear λ-calculus have a long standing tradition in the study of natural language form and meaning. Among the proof calculi of linear logic, proof nets are of…

cs.CL2019

Extracting and Learning a Dependency-Enhanced Type Lexicon for Dutch

Konstantinos Kogkalidis

This thesis is concerned with type-logical grammars and their practical applicability as tools of reasoning about sentence syntax and semantics. The focal point is narrowed to Dutc…

cs.CL2019

Constructive Type-Logical Supertagging with Self-Attention Networks

Konstantinos Kogkalidis, Michael Moortgat, Tejaswini Deoskar

We propose a novel application of self-attention networks towards grammar induction. We present an attention-based supertagger for a refined type-logical grammar, trained on constr…