Jointly Predicting Dialog Act and Named Entity for Spoken Language Understanding

Abstract

Spoken language understanding (SLU) addresses the problem of mapping natural language speech into semantic frame for structure encoding of its meaning. Most of the SLU systems separate out the dialog act (DA) identification from the named entity (NE) recognition to generate the semantic frames. In previous works, these two subtasks are treated by independent or cascaded approaches. In the cascaded systems, however, DA and NE influence only to one side, rather than to both sides. In this paper, we develop a new joint SLU model with a triangular-chain conditional random field (CRF) to encode inter-dependence between DA and NE. On four real dialog data, we show that our joint approach outperforms both independent and cascaded approaches.

Machine Learning Approaches to Spoken Language Understanding for Ambient Intelligence

“…For example, in joint prediction of DAs and NEs [13], x may be a word sequence, y may be an NE sequence, and z may be a DA (or the speaker's intent). Let a random vector x be a sequence of input observations, a random vector y be a sequence of output labels that we wish to predict, and a random variable z be an output variable that indicates a topic or meta-sequence information.…”

“…He and Young [13] described an approach using a hidden vector state model that extends the basic hidden Markov model for encoding 8.8 Conclusion and Future Direction 221 hierarchical structures. He and Young [13] described an approach using a hidden vector state model that extends the basic hidden Markov model for encoding 8.8 Conclusion and Future Direction 221 hierarchical structures.…”

DialogStudio: A workbench for data-driven spoken dialog system development and management

“…The SLU module was implemented using the method of Jeong and Lee (2006). The DM module was implemented using the example-based dialog management (EBDM) method (Lee et al, 2005).…”

Attention-Based End-to-End Named Entity Recognition from Speech

“…Named entities are heavily used in spoken language understanding (SLU) [4] [16] [10], where the goal is to understand what has been spoken. For example, SLU is an essential part of personal assistants in home automation and smartphone devices.…”