Inducing Embeddings for Rare and Unseen Words by Leveraging Lexical Resources

We put forward an approach that exploits the knowledge encoded in lexical resources in order to induce representations for words that were not encountered frequently during training. Our approach provides an advantage over the past work in that it enables vocabulary expansion not only for morphological variations, but also for infrequent domain specific terms. We performed evaluations in different settings, showing that the technique can provide consistent improvements on multiple benchmarks across domains.The authors gratefully acknowledge the support of the MRC grant No. MR/M025160/1 for PheneBank