Papers by Konstantinos Kogkalidis
OYXOY: A Modern NLP Test Suite for Modern Greek (2024.findings-eacl)
Copied to clipboard
Konstantinos Kogkalidis, Stergios Chatzikyriakidis, Eirini Giannikouri, Vasiliki Katsouli, Christina Klironomou, Christina Koula, Dimitris Papadakis, Thelka Pasparaki, Erofili Psaltaki, Efthymia Sakellariou, Charikleia Soupiona
| Challenge: | a select few languages claim the lion's share in the literature, boasting a plethora of models and a constant stream of results. |
| Approach: | They propose a linguistically motivated evaluation suite for Greek NLP . they propose linguistic-motivated tasks for natural language inference, word sense disambiguation and metaphor detection . |
| Outcome: | The proposed evaluation suite for Greek NLP is linguistically motivated and technically relevant. |
SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention (2023.eacl-demo)
Copied to clipboard
| Challenge: | SPINDLE is an open source Python module that parses text input into programs for meaning composition expressed as terms. |
| Approach: | They describe SPINDLE, an open source Python module that parses text input into programs for meaning composition expressed as terms. |
| Outcome: | The proposed parser captures two orthogonal axes of syntax and provides proof search and visualization tools. |
ÆTHEL: Automatically Extracted Typelogical Derivations for Dutch (2020.lrec-1)
Copied to clipboard
| Challenge: | THEL contains a lexicon of supertags for about 900 000 words in context. |
| Approach: | They propose to extract a lexicon of supertags for 900 000 words in context and provide 72 192 validated derivations on the basis of these types. |
| Outcome: | The proposed dataset contains lexicon of supertags for about 900 000 words in context. |
Discontinuous Constituency and BERT: A Case Study of Dutch (2022.findings-acl)
Copied to clipboard
| Challenge: | a recent study has shown that large-scale language models fail to acquire aspects of linguistic theory due to their unanticipated performance. |
| Approach: | They propose to use a context-sensitive formalism to derive grammars that capture verb nesting and verb raising in Dutch. |
| Outcome: | The proposed model fails to acquire the dependencies examined in Dutch. |