Conversational Semantic Parsing using Dynamic Context Graphs
This addresses the problem of interactive querying in conversational AI for users needing to extract information from large-scale knowledge graphs, representing an incremental advance in context modeling.
The paper tackles conversational semantic parsing over large knowledge graphs by dynamically creating context subgraphs for each utterance and encoding them with graph neural networks, achieving performance improvements across simple and complex questions compared to static approaches.
In this paper we consider the task of conversational semantic parsing over general purpose knowledge graphs (KGs) with millions of entities, and thousands of relation-types. We focus on models which are capable of interactively mapping user utterances into executable logical forms (e.g., Sparql) in the context of the conversational history. Our key idea is to represent information about an utterance and its context via a subgraph which is created dynamically, i.e., the number of nodes varies per utterance. Rather than treating the subgraph as a sequence, we exploit its underlying structure and encode it with a graph neural network which further allows us to represent a large number of (unseen) nodes. Experimental results show that dynamic context modeling is superior to static approaches, delivering performance improvements across the board (i.e., for simple and complex questions). Our results further confirm that modeling the structure of context is better at processing discourse information, (i.e., at handling ellipsis and resolving coreference) and longer interactions.