Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Task

Cholakov, Radostin; Kolev, Todor

doi:10.48550/arxiv.2208.07097

“…There are several choices for the base model framework, like decoder-only GPT (Yang, Li, and Quan 2021;Peng et al 2021), encoder-decoder T5 (Su et al 2021;Bang, Lee, and Koo 2023), UniLM-based models (He et al 2022b,a), encoder-2decoders based models (Lee 2021; Cholakov and Kolev 2022). Considering that the belief generation depends more on understanding and summarization ability, while the policy and response generation relies more on generative ability to maintain contextual coherence.…”

Section: Model Frameworkmentioning

confidence: 99%

TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling

Liu,

Li,

Feng

2024

AAAI

0

View full text Add to dashboard Cite

Task-oriented dialog systems have witnessed substantial progress due to conversational pre-training techniques. Yet, two significant challenges persist. First, most systems primarily utilize the latest turn's state label for the generator. This practice overlooks the comprehensive value of state labels in boosting the model's understanding for future generations. Second, an overreliance on generated policy often leads to error accumulation, resulting in suboptimal responses when adhering to incorrect actions. To combat these challenges, we propose turn-level multi-task objectives for the encoder. With the guidance of essential information from labeled intermediate states, we establish a more robust representation for both understanding and generation. For the decoder, we introduce an action tree-based scheduled sampling technique. Specifically, we model the hierarchical policy as trees and utilize the similarity between trees to sample negative policy based on scheduled sampling, hoping the model to generate invariant responses under perturbations. This method simulates potential pitfalls by sampling similar negative policy, bridging the gap between task-oriented dialog training and inference. Among methods without continual pre-training, our approach achieved state-of-the-art (SOTA) performance on the MultiWOZ dataset series and was also competitive with pre-trained SOTA methods.

show abstract

“…We evaluate both end-to-end and policy optimization settings. This includes UBAR (Nekvinda and Dusek, 2021), PPTOD (Su et 2022), RSTOD (Cholakov and Kolev, 2022), BORT (Sun et al, 2022a), MTTOD (Lee, 2021), HDNO (Wang et al, 2020a), GALAXY , MarCO (Wang et al, 2020b), Mars (Sun et al, 2022b), and KRLS . To obtain database search results in the end-to-end setting, we use MTTOD's dialogue state tracker, which is trained jointly during fine-tuning.…”

Section: Experiments Setupmentioning

confidence: 99%

DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems

Wu,

Gung,

Shu

et al. 2023

Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue

0

View full text Add to dashboard Cite

Dialogue act annotations are important to improve response generation quality in taskoriented dialogue systems. However, it can be challenging to use dialogue acts to control response generation in a generalizable way because different datasets and tasks may have incompatible annotations. While alternative methods that utilize latent action spaces or reinforcement learning do not require explicit annotations, they may lack interpretability or face difficulties defining task-specific rewards. In this work, we present a novel end-to-end latent dialogue act model (DiactTOD) that represents dialogue acts in a latent space. Diact-TOD, when pre-trained on a large corpus, is able to predict and control dialogue acts to generate controllable responses using these latent representations in a zero-shot fashion. Our approach demonstrates state-of-the-art performance across a wide range of experimental settings on the MultiWOZ dataset, including zeroshot, few-shot, and full data fine-tuning with both end-to-end and policy optimization configurations.

show abstract

“…We evaluate both end-to-end and policy optimization settings. This includes UBAR (Nekvinda and Dusek, 2021), PPTOD (Su et 2022), RSTOD (Cholakov and Kolev, 2022), BORT (Sun et al, 2022a), MTTOD (Lee, 2021), HDNO (Wang et al, 2020a), GALAXY , MarCO (Wang et al, 2020b), Mars (Sun et al, 2022b), and KRLS . To obtain database search results in the end-to-end setting, we use MTTOD's dialogue state tracker, which is trained jointly during fine-tuning.…”

Section: Experiments Setupmentioning

confidence: 99%

Learning to memorize in neural task-oriented dialogue systems

Wu¹

View full text Add to dashboard Cite

Dialogue act annotations are important to improve response generation quality in taskoriented dialogue systems. However, it can be challenging to use dialogue acts to control response generation in a generalizable way because different datasets and tasks may have incompatible annotations. While alternative methods that utilize latent action spaces or reinforcement learning do not require explicit annotations, they may lack interpretability or face difficulties defining task-specific rewards. In this work, we present a novel end-to-end latent dialogue act model (DiactTOD) that represents dialogue acts in a latent space. Diact-TOD, when pre-trained on a large corpus, is able to predict and control dialogue acts to generate controllable responses using these latent representations in a zero-shot fashion. Our approach demonstrates state-of-the-art performance across a wide range of experimental settings on the MultiWOZ dataset, including zeroshot, few-shot, and full data fine-tuning with both end-to-end and policy optimization configurations.

show abstract

Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Task

Cited by 4 publications

References 0 publications

TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling

TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling

DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems

Learning to memorize in neural task-oriented dialogue systems

Contact Info

Product

Resources

About