3 accepted papers
We present a novel retrofitting method to induce emotion aspects into pre-trained language models (PLMs) such as BERT and RoBERTa. Our method updates pre-trained network weights using contrastive learning so that the text fragments exhibiting similar emotions are encoded nearby in the representation…
Word embeddings learned using the distributional hypothesis (e.g., GloVe, Word2vec) are good at encoding various lexical-semantic relations. However, they do not capture the emotion aspects of words. We present a novel retrofitting method for updating the vectors of emotion bearing words like fun, o…
We present a novel retrofitting model that can leverage relational knowledge available in a knowledge resource to improve word embeddings. The knowledge is captured in terms of relation inequality constraints that compare similarity of related and unrelated entities in the context of an anchor entit…