Related papers: Action State Update Approach to Dialogue Managemen…
Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems. However, collecting a large amount of turn-by-turn annotated dialogue data is costly and inefficient. In this paper, we propose a novel turn-level…
User Satisfaction Estimation (USE) is an important yet challenging task in goal-oriented conversational systems. Whether the user is satisfied with the system largely depends on the fulfillment of the user's needs, which can be implicitly…
Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services in diminishing performance on previously learnt services. Motivated by the insight that…
We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the…
Intelligent dialogue systems are expected as a new interface between humans and machines. Such an intelligent dialogue system should estimate the user's internal state (UIS) in dialogues and change its response appropriately according to…
The purpose of this paper is to present a method for automatic classification of dialogue utterances and the results of applying that method to a corpus. Superficial features of a set of training utterances (which we will call cues) are…
Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases.…
Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within…
Automatic Speech Understanding (ASU) aims at human-like speech interpretation, providing nuanced intent, emotion, sentiment, and content understanding from speech and language (text) content conveyed in speech. Typically, training a robust…
This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers…
Reinforcement learning has been applied to train the dialog systems in many works. Previous approaches divide the dialog system into multiple modules including DST (dialog state tracking) and DP (dialog policy), and train these modules…
The ability to model and automatically detect dialogue act is an important step toward understanding spontaneous speech and Instant Messages. However, it has been difficult to infer a dialogue act from a surface utterance because it highly…
In this paper, we study the task of selecting the optimal response given a user and system utterance history in retrieval-based multi-turn dialog systems. Recently, pre-trained language models (e.g., BERT, RoBERTa, and ELECTRA) showed…
Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for DA…
The recent abundance of conversational data on the Web and elsewhere calls for effective NLP systems for dialog understanding. Complete utterance-level understanding often requires context understanding, defined by nearby utterances. In…
Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to…
In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's requests (\textit{a.k.a} dialogue state tracking) is key to a smooth interaction. Traditionally, TOD systems perform this update in three…
Dialogue policy optimization often obtains feedback until task completion in task-oriented dialogue systems. This is insufficient for training intermediate dialogue turns since supervision signals (or rewards) are only provided at the end…
Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…
The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e.g., hotel booking). The dialogue management is a core part of SDS. There are two main missions in dialogue management: dialogue…