Sequential Dialogue Context Modeling for Spoken Language Understanding
This work addresses contextual ambiguities in goal-oriented dialogue systems for improved SLU, though it appears incremental as it builds on existing RNN and memory network approaches.
The paper tackled the problem of modeling dialogue history in spoken language understanding by proposing a Sequential Dialogue Encoder Network, which encodes context in chronological order using an RNN, and demonstrated reduced semantic frame error rates in experiments on a multi-domain dataset.
Spoken Language Understanding (SLU) is a key component of goal oriented dialogue systems that would parse user utterances into semantic frame representations. Traditionally SLU does not utilize the dialogue history beyond the previous system turn and contextual ambiguities are resolved by the downstream components. In this paper, we explore novel approaches for modeling dialogue context in a recurrent neural network (RNN) based language understanding system. We propose the Sequential Dialogue Encoder Network, that allows encoding context from the dialogue history in chronological order. We compare the performance of our proposed architecture with two context models, one that uses just the previous turn context and another that encodes dialogue context in a memory network, but loses the order of utterances in the dialogue history. Experiments with a multi-domain dialogue dataset demonstrate that the proposed architecture results in reduced semantic frame error rates.