Composing Distributed Representations of Relational Patterns
This work addresses semantic modeling for relational patterns in NLP, but it is incremental as it builds on existing methods and datasets.
The paper tackled the problem of learning distributed representations for relational patterns by constructing a new dataset with multiple similarity ratings and comparing encoders like additive composition, RNN, LSTM, and GRU, introducing Gated Additive Composition as an enhancement; experiments showed the dataset enables detailed encoder analyses and predicts success in relation classification tasks.
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.