A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots

Abstract

A slot value might be provided segment by segment over multiple-turn interactions in a dialog, especially for some important information such as phone numbers and names. It is a common phenomenon in daily life, but little attention has been paid to it in previous work. To fill the gap, this paper defines a new task named Sub-Slot based Task-Oriented Dialog (SSTOD) and builds a Chinese dialog dataset SSD for boosting research on SSTOD. The dataset includes a total of 40K dialogs and 500K utterances from four different domains: Chinese names, phone numbers, ID numbers and license plate numbers. The data is well annotated with sub-slot values, slot values, dialog states and actions. We find some new linguistic phenomena and interactive manners in SSTOD which raise critical challenges of building dialog agents for the task. We test three state-of-the-art dialog models on SSTOD and find they cannot handle the task well on any of the four domains. We also investigate an improved model by involving slot knowledge in a plug-in manner. More work should be done to meet the new challenges raised from SSTOD which widely exists in real-life applications. The dataset and code are publicly available via https://github.com/shunjiu/SSTOD.

UniSA: Unified Generative Framework for Sentiment Analysis

“…Early research focused on context modeling using GRU [6] models to extract context information and judge the emotion category of the utterance based on the context information [9,12,17,40,49]. More recent research has introduced GCN models [11] into conversation scene modeling, where each utterance in the conversation [32,80] is regarded as a node in the graph, and the relationship between utterances constitutes the edge connecting the nodes [10,19,25,59]. The most recent works in this area employ Transformer architecture and self-attention mechanisms to capture contextual information of utterances and achieve state-of-the-art performance in emotion recognition in conversations [20,27,30,41,58].…”

Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue System

“…Traditional dialogue systems [17,33] usually consist of three components: natural language understanding (NLU) [28,30,58,59], dialogue management (DM) [6,7,18], and natural language generation (NLG) [50,63,65,66] modules. Empirically, NLU plays the most important role in task-oriented dialogue systems, including tasks such as intent detection [12,13,29,57], slot filling [61], and semantic parsing [19? , 20].…”

Empathetic Response Generation via Emotion Cause Transition Graph

“…We first manually annotate a span-level emotion cause dataset and exploit a pre-trained model fine-tuned on this dataset to identify emotion cause spans. Since human dialogue [16,17,18] naturally centers on key concepts [19,20], we extract keywords in emotion cause spans as key concepts, which are vertices of the graph. And edges in the graph represent natural transitions between emotion causes in the dialog.…”