Relational Word Embeddings
This addresses a specific problem in natural language processing for researchers and practitioners by offering an incremental improvement in embedding methods.
The paper tackles the limitation of standard word embeddings in capturing relational knowledge by proposing a separate relational word embedding learned from co-occurrence statistics, which is shown to be complementary to standard embeddings without needing external knowledge bases.
While word embeddings have been shown to implicitly encode various forms of attributional knowledge, the extent to which they capture relational information is far more limited. In previous work, this limitation has been addressed by incorporating relational knowledge from external knowledge bases when learning the word embedding. Such strategies may not be optimal, however, as they are limited by the coverage of available resources and conflate similarity with other forms of relatedness. As an alternative, in this paper we propose to encode relational knowledge in a separate word embedding, which is aimed to be complementary to a given standard word embedding. This relational word embedding is still learned from co-occurrence statistics, and can thus be used even when no external knowledge base is available. Our analysis shows that relational word vectors do indeed capture information that is complementary to what is encoded in standard word embeddings.