SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues

Chiu, Ssu; Li, Maolin; Chen, Yun-Nung

doi:10.18653/v1/2022.acl-long.425

Cited by 13 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…". This is beneficial for commercial dialogue systems to proactively offer or sell their task-related services [4,16] at the right time. (2) The human-machine interaction starts with task-oriented requests and eventually switches to casual chat after providing all user needed information, as the second example in Figure 1.…”

Section: Arxiv:230701664v1 [Cscl] 4 Jul 2023mentioning

confidence: 99%

“…Our work, on the other hand, leverages FusedChat to explore the proactive transitions between these two dialogue modes guided by dialogue systems rather than users. [4] recently proposed SalesBot and investigated the conversations starting from open-domain social chatting and then gradually transitioning to task-oriented purposes. However, our work not only explores the transition from chit-chat to task-oriented, but also from task-oriented to chit-chat.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues

Liu

Ultes

Minker

et al. 2023

Proceedings of the 5th International Conference on Conversational User Interfaces

View full text Add to dashboard Cite

Spoken dialogue systems (SDSs) have been separately developed under two different categories, task-oriented and chit-chat. The former focuses on achieving functional goals and the latter aims at creating engaging social conversations without special goals. Creating a unified conversational model that can engage in both chit-chat and task-oriented dialogue is a promising research topic in recent years. However, the potential "initiative" that occurs when there is a change between dialogue modes in one dialogue has rarely been explored. In this work, we investigate two kinds of dialogue scenarios, one starts from chit-chat implicitly involving task-related topics and finally switching to task-oriented requests; the other starts from task-oriented interaction and eventually changes to casual chat after all requested information is provided. We contribute two efficient prompt models which can proactively generate a transition sentence to trigger system-initiated transitions in a unified dialogue model. One is a discrete prompt model trained with two discrete tokens, the other one is a continuous prompt model using continuous prompt embeddings automatically generated by a classifier. We furthermore show that the continuous prompt model can also be used to guide the proactive transitions between particular domains in a multi-domain task-oriented setting. CCS CONCEPTS• Human-centered computing → Human computer interaction (HCI).

show abstract

Section: Arxiv:230701664v1 [Cscl] 4 Jul 2023mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues

Liu

Ultes

Minker

et al. 2023

Proceedings of the 5th International Conference on Conversational User Interfaces

View full text Add to dashboard Cite

show abstract

“…In terms of the purpose of conversation, dialog systems can be also divided into task-oriented, QA, conversational recommendation, and chit-chat [21]. Task-oriented systems aim to accomplish users' goals (e.g., online shopping or restaurant reservation) through an optimal decision-making process in multi-turn dialogs.…”

Section: Related Workmentioning

confidence: 99%

Modeling hierarchical attention interaction between contexts and triple-channel encoding networks for document-grounded dialog generation

2022

View full text Add to dashboard Cite

Dialog systems have attracted attention as they are promising in many intelligent applications. Generating fluent and informative responses is of critical importance for dialog systems. Some recent studies introduce documents as extra knowledge to improve the performance of dialog generation. However, it is hard to understand the unstructured document and extract crucial information related to dialog history and current utterance. This leads to uninformative and inflexible responses in existing studies. To address this issue, we propose a generative model of a neural network with an attention mechanism for document-grounded multi-turn dialog. This model encodes the context of utterances that contains the given document, dialog history, and the last utterance into distributed representations via a triple-channel. Then, it introduces a hierarchical attention interaction between dialog contexts and previously generated utterances into the decoder for generating an appropriate response. We compare our model with various baselines on dataset CMU_DoG in terms of the evaluation criteria. The experimental results demonstrate the state-of-the-art performance of our model as compared to previous studies. Furthermore, the results of ablation experiments show the effectiveness of the hierarchical attention interaction and the triple channel for encoding. We also conduct human judgment to evaluate the informativeness of responses and the consistency of responses with dialog history.

show abstract

“…Task-oriented dialogue systems are ubiquitous (Budzianowski et al, 2018;Chiu et al, 2022). However, they require human operators to deal with complicated intentions that are beyond their capacities.…”

Section: Introductionmentioning

confidence: 99%

SILVER: Self Data Augmentation for Out-of-Scope Detection in Dialogues

Ma,

Makino

2023

Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacifi

View full text Add to dashboard Cite

Detecting out-of-scope (OOS) utterances is crucial in task-oriented dialogue systems, but obtaining enough annotated OOS dialogues to train a binary classifier directly is difficult in practice. Existing data augmentation methods generate OOS dialogues automatically, but their performance usually depends on an external corpus. This dependence not only induces uncertainty, but also reduces the quality of generated dialogues. Specifically, all of them are out-of-domain (OOD).Herein we propose SILVER, a self data augmentation method that does not use external data. It addresses issues of previous research and improves the accuracy of OOS detection (false positive rate: 90.5% → 47.4%). Furthermore, SILVER successfully generates highquality in-domain (IND) OOS dialogues in terms of naturalness (percentage: 8% → 68%) and OOS correctness (percentage: 74% → 88%), as evaluated by human workers.

show abstract

SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues

Cited by 13 publications

References 0 publications

Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues

Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues

Modeling hierarchical attention interaction between contexts and triple-channel encoding networks for document-grounded dialog generation

SILVER: Self Data Augmentation for Out-of-Scope Detection in Dialogues

Contact Info

Product

Resources

About