Structured Fusion Networks for Dialog

By Shikib Mehri, Tejas Srinivasan, Maxine Eskénazi. 2019

94 citations recorded by the source corpus.

Neural dialog models have exhibited strong performance, however their end-to-end nature lacks a representation of the explicit structure of dialog. This results in a loss of generalizability, controllability and a data-hungry nature. Conversely, more traditional dialog systems do have strong models of explicit structure. This paper introduces several approaches for explicitly incorporating structure into neural models of dialog. Structured Fusion Networks first learn neural dialog modules corresponding to the structured components of traditional dialog systems and then incorporate these modules in a higher-level generative model. Structured Fusion Networks obtain strong results on the MultiWOZ dataset, both with and without reinforcement learning. Structured Fusion Networks are shown to have several valuable properties, including better domain generalizability, improved performance in reduced data scenarios and robustness to divergence during reinforcement learning.

Subfields: Artificial Intelligence

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

Citations in the corpus

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context (2019, background): “5 + BLEU as an overall quality measure suggested in Mehri et al. (2019).”
SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model (2020, methodology): “To tackle this, several models were proposed to handle the multi-domain dialog response generation (Pei et al., 2019; Budzianowski and Vuli´c, 2019; Mehri et al., 2019; Zhao et al., 2019; Wu et al., 2019; Zhang et al., 2019a).”
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems (2020, background): “, 2019a), Structured Fusion (Mehri et al., 2019), HDSA (Chen et al.”
End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2 (2020, background): “…the dialogue state (the composite function of NLU and DST), and the Word-level POL (Budzianowski et al., 2018; Pei et al., 2019; Chen et al., 2019; Mehri et al., 2019; Zhao et al., 2019) which maps the previous utterance and dialogue state to the system response (the composite function of POL and…”
Paraphrase Augmented Task-Oriented Dialog Generation (2020, background): “5 + BLEU for overall quality measure as suggested in (Mehri et al., 2019).”
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems (2020, methodology): “Following previous work (Mehri et al., 2019), we also report the combined score, i.e., Combined = (Inform + Success) × 0 .”
GODEL: Large-Scale Pre-Training for Goal-Directed Dialog (2022, methodology): “• The Combined score (Mehri et al., 2019) defined as (Inform + Success) * 0.”