Implicit discourse relation classification with syntax-aware contextualized word representations

Automatically identifying implicit discourse relations requires an in-depth semantic understanding of the text fragments involved in such relations. While early work investigated the usefulness of different classes of input features, current state-of-the-art models mostly rely on standard pre-trained word embeddings to model the arguments of a discourse relation. In this paper, we introduce a method to compute contextualized representations of words, leveraging information from the sentence dependency parse, to improve argument representation. The resulting token embeddings encode the structure of the sentence from a dependency point of view in their representations. Experimental results show that the proposed representations achieve state-of-the-art results when input to standard neural network architectures, surpassing complex models that use additional data and consider the interaction between arguments.