Composing Distributed Representations of Relational Patterns

ACL 2016  ·  Sho Takase, Naoaki Okazaki, Kentaro Inui ·

Learning distributed representations for relation instances is a central technique in downstream NLP applications. In order to address semantic modeling of relational patterns, this paper constructs a new dataset that provides multiple similarity ratings for every pair of relational patterns on the existing dataset. In addition, we conduct a comparative study of different encoders including additive composition, RNN, LSTM, and GRU for composing distributed representations of relational patterns. We also present Gated Additive Composition, which is an enhancement of additive composition with the gating mechanism. Experiments show that the new dataset does not only enable detailed analyses of the different encoders, but also provides a gauge to predict successes of distributed representations of relational patterns in the relation classification task.

PDF Abstract ACL 2016 PDF ACL 2016 Abstract


Introduced in the Paper:

Relational Pattern Similarity Dataset

Used in the Paper:

SemEval-2010 Task-8

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.