DeepAI AI Chat
Log In Sign Up

Speaker-Sensitive Dual Memory Networks for Multi-Turn Slot Tagging

by   Young-Bum Kim, et al.

In multi-turn dialogs, natural language understanding models can introduce obvious errors by being blind to contextual information. To incorporate dialog history, we present a neural architecture with Speaker-Sensitive Dual Memory Networks which encode utterances differently depending on the speaker. This addresses the different extents of information available to the system - the system knows only the surface form of user utterances while it has the exact semantics of system output. We performed experiments on real user data from Microsoft Cortana, a commercial personal assistant. The result showed a significant performance improvement over the state-of-the-art slot tagging models using contextual information.


page 1

page 2

page 3

page 4


CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots

Natural Language Understanding (NLU) is a core component of dialog syste...

Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding

Spoken language understanding (SLU) is an essential component in convers...

Modeling Inter-Speaker Relationship in XLNet for Contextual Spoken Language Understanding

We propose two methods to capture relevant history information in a mult...

Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding

To capture salient contextual information for spoken language understand...

Adapting Long Context NLM for ASR Rescoring in Conversational Agents

Neural Language Models (NLM), when trained and evaluated with context sp...

SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking

In goal-oriented dialog systems, belief trackers estimate the probabilit...

GCT: Gated Contextual Transformer for Sequential Audio Tagging

Audio tagging aims to assign predefined tags to audio clips to indicate ...