%Aigaion2 BibTeX export from Idiap Publications
%Thursday 26 December 2024 09:49:38 PM

@INPROCEEDINGS{Theodoropoulos_CONLL2021_2021,
         author = {Theodoropoulos, Christos and Henderson, James and Coman, Andrei Catalin and Moens, Marie-Francine},
       projects = {Idiap},
          month = nov,
          title = {Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning},
      booktitle = {Proceedings of the 25th Conference on Computational Natural Language Learning},
           year = {2021},
          pages = {337-348},
      publisher = {Association for Computational Linguistics},
       location = {Online},
       abstract = {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.}
}