Blending Dependency Parsers With Language Models

Nicos Isaak

2023

Abstract

Recent advances in the AI field triggered an increasing interest in tackling various NLP tasks with language models. Experiments on several benchmarks demonstrated their effectiveness, potential, and role as a central component in modern AI systems. However, when training data are limited, specialized expertise is needed in order to help them perform complex kind-of-reasoning and achieve better results. It seems that extensive experiments with additional semantic analysis and fine-tuning are needed to achieve improvements on downstream NLP tasks. To address this complex problem of achieving better results with language models when training data are limited, we present a simplified way that automatically improves their learned representations with extra-linguistic knowledge. To this end, we show that further fine-tuning with semantics from state-of-the-art dependency parsers improves existing language models on specialized downstream tasks. Experiments on benchmark datasets we undertook show that the blending of language models with dependency parsers is promising for achieving better results.

Download


Paper Citation


in Harvard Style

Isaak N. (2023). Blending Dependency Parsers With Language Models. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 813-820. DOI: 10.5220/0011781800003393


in Bibtex Style

@conference{icaart23,
author={Nicos Isaak},
title={Blending Dependency Parsers With Language Models},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={813-820},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011781800003393},
isbn={978-989-758-623-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Blending Dependency Parsers With Language Models
SN - 978-989-758-623-1
AU - Isaak N.
PY - 2023
SP - 813
EP - 820
DO - 10.5220/0011781800003393