Recursive Template-based Frame Generation for Task Oriented Dialog

The Natural Language Understanding (NLU) component in task oriented dialog systems processes a user’s request and converts it into structured information that can be consumed by downstream components such as the Dialog State Tracker (DST). This information is typically represented as a semantic frame that captures the intent and slot-labels provided by the user. We first show that such a shallow representation is insufficient for complex dialog scenarios, because it does not capture the recursive nature inherent in many domains. We propose a recursive, hierarchical frame-based representation and show how to learn it from data. We formulate the frame generation task as a template-based tree decoding task, where the decoder recursively generates a template and then fills slot values into the template. We extend local tree-based loss functions with terms that provide global supervision and show how to optimize them end-to-end. We achieve a small improvement on the widely used ATIS dataset and a much larger improvement on a more complex dataset we describe here.

• Publication year

  2020

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2020-07-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.18653/V1/2020.ACL-MAIN.186
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019cited by this paper
• BERT for Joint Intent Classification and Slot Filling

  2019influential reference
• Joint Multiple Intent Detection and Slot Labeling for Goal-Oriented Dialog

  2019cited by this paper
• What we need to learn if we want to do and not just talk

  2018cited by this paper
• Coarse-to-Fine Decoding for Neural Semantic Parsing

  2018cited by this paper
• Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

  2018cited by this paper
• Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

  2018cited by this paper
• Two-stage multi-intent detection for spoken language understanding

  2017cited by this paper
• Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM

  2016cited by this paper
• Data Recombination for Neural Semantic Parsing

  2016cited by this paper
• Pointer Networks

  2015cited by this paper
• The Second Dialog State Tracking Challenge

  2014cited by this paper
• Optimal Thresholding of Classifiers to Maximize F1 Measure

  2014cited by this paper
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• Exploiting shared information for multi-intent natural language sentence classification

  2013cited by this paper
• Parsing Natural Scenes and Natural Language with Recursive Neural Networks

  2011cited by this paper
• What is left to be understood in ATIS?

  2010cited by this paper
• Long Short-Term Memory

  1997cited by this paper

• Interpreting open-domain dialogue generation by disentangling latent feature representations

  2023cites this paper
• Mitigating Societal Harms in Large Language Models

  2023cites this paper
• Recent Advances in Neural Text Generation: A Task-Agnostic Survey

  2022cites this paper
• Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation

  2022cites this paper
• Recent advances in deep learning based dialogue systems: a systematic survey

  2021cites this paper
• Automatic Document Sketching: Generating Drafts from Analogous Texts

  2021cites this paper