Name: Christos Theodoropoulos
Type: User
Company: KU Leuven
Bio: Ph.D. researcher at KU Leuven, with a keen interest in Natural Language Processing, Continual Learning, Information Extraction and Deep Learning.
Location: Belgium - Greece
Blog: https://christos42.github.io
Christos Theodoropoulos's Projects
This repo is used to release code that is generated by the AI Horizons Network as needed to supplement conference papers and workshops.
Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning framework that trains sentence embeddings to encode the relations in a graph structure. Given a sentence (unstructured text) and its graph, we use contrastive learning to impose relation-related structure on the token level representations of the sentence obtained with a CharacterBERT (El Boukkouri et al., 2020) model. The resulting relation-aware sentence embeddings achieve state-of-the-art results on the relation extraction task using only a simple KNN classifier, thereby demonstrating the success of the proposed method. Additional visualization by a tSNE analysis shows the effectiveness of the learned representation space compared to baselines. Furthermore, we show that we can learn a different space for named entity recognition, again using a contrastive learning objective, and demonstrate how to successfully combine both representation spaces in an entity-relation task.
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Ontology representing a 360-view of a person (or cohort) that spans across multiple domains, from health to social.
An Information Extraction Study: Take In Mind the Tokenization! (official repository of the paper)
Public repo for DeepLearning.AI MLEP Specialization