research area Methods and Algorithms, research area Speech and Natural Language Processingconference EMNLP
content type paperpublished November 2020

Conversational Semantic Parsing for Dialog State Tracking

AuthorsJianpeng Cheng, Devang Agrawal, Hector Martinez Alonso, Shruti Bhargava, Joris Driesen Federico Flego, Dain Kaplan, Dimitri Kartsaklis, Lin Li, Dhivya Piraviperumal, Jason D Williams, Hong Yu, Diarmuid O Seaghdha, Anders Johannsen

View publication

We consider a new perspective on dialog state tracking (DST), the task of estimating a user's goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositionality, cross-domain knowledge sharing and co-reference. We present TreeDST, a dataset of 27 thousand conversations annotated with tree-structured dialog states and system acts. We describe an encoder-decoder framework for DST with hierarchical representations, which leads to 20 percent improvement over state-of-the-art DST approaches that operate on a flat meaning space of slot-value pairs.

Related readings and updates.

SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking

March 4, 2024research area Data Science and Annotation, research area Speech and Natural Language Processingconference EACL

In-context learning with Large Language Models (LLMs) has emerged as a promising avenue of research in Dialog State Tracking (DST). However, the best-performing in-context learning methods involve retrieving and adding similar examples to the prompt, requiring access to labeled training data. Procuring such training data for a wide range of domains and applications is time-consuming, expensive, and, at times, infeasible. While zero-shot learning…
Read more

EMNLP 2020

November 8, 2020research area Speech and Natural Language Processingconference EMNLP

Apple sponsored the Empirical Methods in Natural Language Processing (EMNLP) conference, which was held virtually from November 16 to 20. EMNLP is a leading conference focused on natural language processing.

Read more