@proceedings{118056,
  author = {Mikhail Khodak and Nikunj Saunshi and Yingyu Liang and Tengyu Ma and Brandon Stewart and Sanjeev Arora},
  title = {A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors},
  abstract = {<p>Motivations like domain adaptation, transfer learning, and feature learning have fueled interest in inducing embeddings for rare or unseen words, n-grams, synsets, and other textual features. This paper introduces a la carte embedding, a simple and general alternative to the usual word2vec-based approaches for building such representations that is based upon recent theoretical results for GloVe-like embeddings. Our method relies mainly on a linear transformation that is efficiently learnable using pretrained word vectors and linear regression. This transform is applicable on the fly in the future when a new text feature or rare word is encountered, even if only a single usage example is available. We introduce a new dataset showing how the a la carte method requires fewer examples of words in context to learn high-quality embeddings and we obtain state-of-the-art results on a nonce task and some unsupervised document classification tasks.</p>
},
  year = {2018},
  journal = {Proceedings of the Association of Computational Linguistics},
  language = {eng},
}