Vivek Srikumar

Yichu Zhou and Vivek Srikumar

*SEM, 2019.

Most word embeddings today are trained by optimizing a language modeling goal of scoring words in their context, modeled as a multi-class classification problem. Despite the successes of this assumption, it is incomplete: in addition to its context, orthographical or morphological aspects of words can offer clues about their meaning. In this paper, we define a new modeling framework for training word embeddings that captures this intuition. Our framework is based on the well-studied problem of multi-label classification and, consequently, exposes several design choices for featurizing words and contexts, loss functions for training and score normalization. Indeed, standard models such as CBOW and FastText are specific choices along each of these axes. We show via experiments that by combining feature engineering with embedding learning, our method can outperform CBOW using only 10% of the training data in both the standard word embedding evaluations and also text classification experiments.

@inproceedings{zhou2019beyond,
  author = {Zhou, Yichu and Srikumar, Vivek},
  title = {{Beyond Context: A New Perspective for Word Embeddings}},
  booktitle = {*SEM},
  year = {2019}
}