TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking

By Michael Heck, Carel van Niekerk, Nurul Lubis, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, Milica Gavsi'c. 2020

240 citations recorded by the source corpus.

Task-oriented dialog systems rely on dialog state tracking (DST) to monitor the user’s goal during the course of an interaction. Multi-domain and open-vocabulary settings complicate the task considerably and demand scalable solutions. In this paper we present a new approach to DST which makes use of various copy mechanisms to fill slots with values. Our model has no need to maintain a list of candidate values. Instead, all values are extracted from the dialog context on-the-fly. A slot is filled by one of three copy mechanisms: (1) Span prediction may extract values directly from the user input; (2) a value may be copied from a system inform memory that keeps track of the system’s inform operations (3) a value may be copied over from a different slot that is already contained in the dialog state to resolve coreferences within and across domains. Our approach combines the advantages of span-based slot filling methods with memory methods to avoid the use of value picklists altogether. We argue that our strategy simplifies the DST task while at the same time achieving state of the art performance on various popular evaluation sets including Multiwoz 2.1, where we achieve a joint goal accuracy beyond 55%.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Simple Language Model for Task-Oriented Dialogue (2020, background): “TripPy apply their own format normalization, typo corrections, and process for accounting for label variations.”
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking (2021, methodology): “The two closest baselines 2 , Con-vBERT (Mehri et al., 2020) and CoCoAug (Li et al., 2021), are also built upon TripPy, where Con-vBERT enhances its performance by using exter-nal large-scale conversational corpora to pre-train a BERT base and CoCoAug leverages a delicate counter-factual augmentatio”
Dialogue State Tracking with a Language Model using Schema-Driven Prompting (2021, methodology): “, 2020), TripPy (Heck et al., 2020), Simple-TOD (Hosseini-Asl et al.”
Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance (2021, background): “Nevertheless, the state-of-the-art goal accuracy on the popular MultiWOZ (Budzianowski et al., 2018) multi-domain benchmark is currently only at 60% (Heck et al., 2020; Li et al., 2020a).”
DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue (2020, methodology): “…on large natural language corpora, these models gain generalized language understanding capabilities that transfer effectively to downstream tasks (Wang et al., 2018), including intent prediction (Chen et al., 2019; Castellucci et al., 2019) and dialogue state tracking (Heck et al., 2020).”
Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking (2021, background): “Current state-of-the-art models (Chen et al., 2020; Lin et al., 2020; Heck et al., 2020; Hosseini-Asl et al., 2020; Ye et al., 2021; Li et al., 2020) trained with extensive annotated data have been shown promising performance in complex multi-domain conversations (Budzianowski et al.”