Strategy of the Negative Sampling for Training Retrieval-Based Dialogue Systems

Nugmanova, Aigul; Smirnov, Alexander; Lavrentyeva, Galina; Chernykh, Irina

doi:10.1109/percomw.2019.8730665

Cited by 5 publications

(3 citation statements)

References 9 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Outside of that work, the use of negative training in dialogue retrieval, rather than generation, has been previously extensively studied, see e.g. (Humeau et al, 2019;Nugmanova et al, 2019). In the area of generative dialogue, a number of works have focused on improving the standard likelihood training approach.…”

Section: Related Workmentioning

confidence: 99%

Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training

Li¹,

Roller²,

Kulikov³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions within utterances, (iii) overuse frequent words, and (iv) at a deeper level, contain logical flaws. In this work we show how all of these problems can be addressed by extending the recently introduced unlikelihood loss (Welleck et al., 2019a) to these cases. We show that appropriate loss functions which regularize generated outputs to match human distributions are effective for the first three issues. For the last important general issue, we show applying unlikelihood to collected data of what a model should not do is effective for improving logical consistency, potentially paving the way to generative models with greater reasoning ability. We demonstrate the efficacy of our approach across several dialogue tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training

Li¹,

Roller²,

Kulikov³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Negative Training for Dialogue Learning Negative training for retrieval-based dialogue learning has been previously extensively studied (Humeau et al, 2020;Nugmanova et al, 2019), while we focus on the dialogue generation in this work. He and Glass (2020)…”

Section: Related Workmentioning

confidence: 99%

Diversifying Neural Dialogue Generation via Negative Distillation

Li¹,

Feng²,

Sun³

et al. 2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Generative dialogue models suffer badly from the generic response problem, limiting their applications to a few toy scenarios. Recently, an interesting approach, namely negative training, has been proposed to alleviate this problem by reminding the model not to generate high-frequency responses during training. However, its performance is hindered by two issues, ignoring low-frequency but generic responses and bringing low-frequency but meaningless responses. In this paper, we propose a novel negative training paradigm, called negative distillation, to keep the model away from the undesirable generic responses while avoiding the above problems. First, we introduce a negative teacher model that can produce querywise generic responses, and then the student model is required to maximize the distance with multi-level negative knowledge. Empirical results show that our method outperforms previous negative training methods significantly. 1

show abstract

“…We argue that the dual-or poly-encoder models are not practical for the task-oriented settings as their performance depends on the way negative examples are sampled during training (Nugmanova et al, 2019). Choosing appropriate negative examples is difficult in task-oriented datasets as system responses are often very similar to each other (with the conversations being in a narrow domain and following similar patterns).…”

Section: Action-aware Response Selectionmentioning

confidence: 99%

AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog

Nekvinda,

Dušek

2022

Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue

View full text Add to dashboard Cite

We introduce AARGH, an end-to-end taskoriented dialog system combining retrieval and generative approaches in a single model, aiming at improving dialog management and lexical diversity of outputs. The model features a new response selection method based on an action-aware training objective and a simplified single-encoder retrieval architecture which allow us to build an end-to-end retrievalenhanced generation model where retrieval and generation share most of the parameters.On the MultiWOZ dataset, we show that our approach produces more diverse outputs while maintaining or improving state tracking and context-to-response generation performance, compared to state-of-the-art baselines.

show abstract

Strategy of the Negative Sampling for Training Retrieval-Based Dialogue Systems

Cited by 5 publications

References 9 publications

Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training

Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training

Diversifying Neural Dialogue Generation via Negative Distillation

AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog

Contact Info

Product

Resources

About