- Abstract: Domain specific goal-oriented dialogue systems typically require modeling three types of inputs, viz., (i) the knowledge-base associated with the domain, (ii) the history of the conversation, which is a sequence of utterances and (iii) the current utterance for which the response needs to be generated. While modeling these inputs, current state-of-the-art models such as Mem2Seq typically ignore the rich structure inherent in the knowledge graph and the sentences in the conversation context. Inspired by the recent success of structure-aware Graph Convolutional Networks (GCNs) for various NLP tasks such as machine translation, semantic role labeling and document dating, we propose a memory augmented GCN for goal-oriented dialogues. Our model exploits (i) the entity relation graph in a knowledge-base and (ii) the dependency graph associated with an utterance to compute richer representations for words and entities. Further, we take cognizance of the fact that in certain situations, such as, when the conversation is in a code-mixed language, dependency parsers may not be available. We show that in such situations we could use the global word co-occurrence graph and use it to enrich the representations of utterances. We experiment with the modified DSTC2 dataset and its recently released code-mixed versions in four languages and show that our method outperforms existing state-of-the-art methods, using a wide range of evaluation metrics.
- Keywords: Goal-oriented Dialogue Systems, Graph Convolutional Networks
- TL;DR: We propose a Graph Convolutional Network based encoder-decoder model with sequential attention for goal-oriented dialogue systems.