Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context

Zhang, Yichi; Ou, Zhijian; Yu, Zhou

doi:10.48550/arxiv.1911.10484

Cited by 16 publications

(40 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many recent work attempt to use end-to-end neural models, such as sequence-to-sequence and GPT-2, to solve taskoriented dialog problems and achieve remarkable results (Wen et al 2016b;Budzianowski et al 2018;Zhang, Ou, and Yu 2019;Peng et al 2020;Ham et al 2020a). In our work, we follow the finetuning strategy of Peng et al (2020) where we concatenate the dialog history and annotations and flatten them into a string, and then use a combination of three objectives to fine-tune GPT-2.…”

Section: Multi-task Fine-tuningmentioning

confidence: 99%

“…Wen et al (2017); Yang et al (2017); Ham et al (2020b) demonstrate that end-to-end systems outperform the traditional pipeline approaches in task-oriented dialog scenarios. Zhang, Ou, and Yu (2019); Peng et al (2020) focus on the benchmarks of the MultiWoz dataset and achieve top performance.…”

Section: Introductionmentioning

confidence: 99%

“…• Domain-Aware Data Pre/Post-processing Although the backbone of the proposed method is an end-to-end model, it is important to apply proper data pre-processing and post-processing because the input and the output of the model are not free-form natural language. As the Multi-Woz dataset is human-human conversation based, we follow Wen et al (2017); Zhang, Ou, and Yu (2019) It simplifies the training data and makes the model to only predict the templates. To encourage knowledge sharing through semantically similar slots in different domains, we apply domain-adaptive delexicalization (Zhang, Ou, and Yu 2019) and compute the domain at each dialog turn to replace the placeholders with slots in the right domain.…”

Section: Introductionmentioning

confidence: 99%

“…As the Multi-Woz dataset is human-human conversation based, we follow Wen et al (2017); Zhang, Ou, and Yu (2019) It simplifies the training data and makes the model to only predict the templates. To encourage knowledge sharing through semantically similar slots in different domains, we apply domain-adaptive delexicalization (Zhang, Ou, and Yu 2019) and compute the domain at each dialog turn to replace the placeholders with slots in the right domain.…”

Section: Introductionmentioning

confidence: 99%

“…To address this problem, we apply the domain-adaptive delexicalization(Zhang, Ou, and Yu 2019) that uses an identical placeholder [value name] to encourage knowledge sharing through semantically similar slots in different domains. Since our model could predict domain for each turn, there is no ambiguity in the post-processing stage for the placeholder replacement.• Turn Domain Computing Turn domain is referred as the domain involved in the current dialog turn.…”

mentioning

confidence: 99%

See 4 more Smart Citations

A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining

Zhang¹,

Lyu²,

Ding³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants in the shared task build an end-to-end task completion dialog system which is evaluated by human evaluation and a user simulator based automatic evaluation. Different from traditional pipelined approaches where modules are optimized individually and suffer from cascading failure, we propose an end-to-end dialog system that 1) uses Generative Pretraining 2 (GPT-2) as the backbone to jointly solve Natural Language Understanding, Dialog State Tracking, and Natural Language Generation tasks, 2) adopts Domain and Task Adaptive Pretraining to tailor GPT-2 to the dialog domain before finetuning, 3) utilizes heuristic pre/post-processing rules that greatly simplify the prediction tasks and improve generalizability, and 4) equips a fault tolerance module to correct errors and inappropriate responses. Our proposed method significantly outperforms baselines and ties for first place in the official evaluation. We make our source code publicly available.* Boliang Zhang and Ying Lyu contributed equally to this work.

show abstract

Section: Multi-task Fine-tuningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining

Zhang¹,

Lyu²,

Ding³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

A Student-Teacher Architecture for Dialog Domain Adaptation Under the Meta-Learning Setting

Qian

Wei

2021

AAAI

Self Cite

View full text Add to dashboard Cite

Numerous new dialog domains are being created every day while collecting data for these domains is extremely costly since it involves human interactions. Therefore, it is essential to develop algorithms that can adapt to different domains efficiently when building data-driven dialog models. Most recent research on domain adaption focuses on giving the model a better initialization, rather than optimizing the adaptation process. We propose an efficient domain adaptive task-oriented dialog system model, which incorporates a meta-teacher model to emphasize the different impacts between generated tokens with respect to the context. We first train our base dialog model and meta-teacher model adversarially in a meta-learning setting on rich-resource domains. The meta-teacher learns to quantify the importance of tokens under different contexts across different domains. During adaptation, the meta-teacher guides the dialog model to focus on important tokens in order to achieve better adaptation efficiency. We evaluate our model on two multi-domain datasets, MultiWOZ and Google Schema-Guided Dialogue, and achieve state-of-the-art performance.

show abstract

[CASPI] Causal-aware Safe Policy Improvement for Task-oriented Dialogue

Ramachandran¹,

Hashimoto²,

Xiong³

2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

The recent success of reinforcement learning (RL) in solving complex tasks is often attributed to its capacity to explore and exploit an environment. Sample efficiency is usually not an issue for tasks with cheap simulators to sample data online. On the other hand, Taskoriented Dialogues (ToD) are usually learnt from offline data collected using human demonstrations. Collecting diverse demonstrations and annotating them is expensive. Unfortunately, RL policy trained on off-policy data are prone to issues of bias and generalization, which are further exacerbated by stochasticity in human response and non-markovian nature of annotated belief state of a dialogue management system. To this end, we propose a batch-RL framework for ToD policy learning: Causal-aware Safe Policy Improvement (CASPI). CASPI includes a mechanism to learn fine-grained reward that captures intention behind human response and also offers guarantee on dialogue policy's performance against a baseline. We demonstrate the effectiveness of this framework on end-to-end dialogue task of the Multiwoz2.0 dataset. The proposed method outperforms the current state of the art. Further more we demonstrate sample efficiency, where our method trained only on 20% of the data, are comparable to current state of the art method trained on 100% data on two out of there evaluation metrics.

show abstract

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context

Cited by 16 publications

References 29 publications

A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining

A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining

A Student-Teacher Architecture for Dialog Domain Adaptation Under the Meta-Learning Setting

[CASPI] Causal-aware Safe Policy Improvement for Task-oriented Dialogue

Contact Info

Product

Resources

About