Dialogue management for an automated multilingual call center

Hardy, Hilda; Strzalkowski, Tomek; Wu, Min

doi:10.3115/1118927.1118931

Cited by 10 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The financial domain corpus currently stands at 1000 dialogues, comprising some 30 000 utterances and a vocabulary size of around 8000 words. This corpus forms the basis of our initial multilingual triaging application, implemented for English, French and German (Hardy et al, 2003a); as well as our prototype automatic financial services system, presented in this paper, which completes a variety of tasks in English (Hardy et al, 2004). The much larger software support corpus (10 000 calls in English and French) is still being collected and processed and will be used to develop the next AMITIÉ S prototype.…”

Section: Amitié S Corpusmentioning

confidence: 97%

“…For our initial tri-lingual triaging application (Hardy et al, 2003a), response generator servers were implemented in English, French and German within the Galaxy Communicator Software Infrastructure. Our automatic telephone-banking demonstrator expands the functionality of the English response generator in order to handle selected tasks in full.…”

Section: Response Generationmentioning

confidence: 99%

See 1 more Smart Citation

The Amitiés system: Data-driven techniques for automated dialogue

Hardy

Biermann

Inouye

et al. 2006

Speech Communication

Self Cite

View full text Add to dashboard Cite

Section: Amitié S Corpusmentioning

confidence: 97%

Section: Response Generationmentioning

confidence: 99%

The Amitiés system: Data-driven techniques for automated dialogue

Hardy

Biermann

Inouye

et al. 2006

Speech Communication

Self Cite

View full text Add to dashboard Cite

“…In the past few years, there has been a rising interest in incorporating Spoken Dialogue Systems [1,2,3] in real-life applications. Many industries, like social robots [4], tourist information [5], banks [6], navigation [7], health care [8] and calling centers [9], have already incorporated Spoken Dialogue Systems to improve performance and offer better services. At its core, a Dialogue System utilizes a Dialogue Manager (DM) [10], which keeps track of the dialogue's state and predicts an action based on that state.…”

Section: Introductionmentioning

confidence: 99%

Robust Belief State Space Representation for Statistical Dialogue Managers Using Deep Autoencoders

Lygerakis

Diakoloulas

Lagoudakis

et al. 2019

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

View full text Add to dashboard Cite

Statistical Dialogue Systems (SDS) have proved their humongous potential over the past few years. However, the lack of efficient and robust representations of the belief state (BS) space refrains them from revealing their full potential. There is a great need for automatic BS representations, which will replace the old hand-crafted, variable-length ones. To tackle those problems, we introduce a novel use of Autoencoders (AEs). Our goal is to obtain a low-dimensional, fixed-length, and compact, yet robust representation of the BS space. We investigate the use of dense AE, Denoising AE (DAE) and Variational Denoising AE (VDAE), which we combine with GP-SARSA to learn dialogue policies in the PyDial toolkit. In this framework, the BS is normally represented in a relatively compact, but still redundant summary space which is obtained through a heuristic mapping of the original master space. We show that all the proposed AE-based representations consistently outperform the summary BS representation. Especially, as the Semantic Error Rate (SER) increases, the DAE/VDAE-based representations obtain state-of-the-art and sample efficient performance.

show abstract

“…Conversational systems is a thriving research area with numerous real-world applications, such as call-centers [1], tourist information [2], car navigation [3], education [4], social robots [5], banking [6], health services [7], and games and entertainment [8]. Many commercial applications are also emerging, such as intelligent personal assistants, e.g.…”

Section: Introductionmentioning

confidence: 99%

A Case Study on the Importance of Belief State Representation for Dialogue Policy Management

Kotti¹,

Diakoloukas²,

Papangelis³

et al. 2018

Interspeech 2018

View full text Add to dashboard Cite

A key component of task-oriented dialogue systems is the belief state representation, since it directly affects the policy learning efficiency. In this paper, we propose a novel, binary, compact, yet scalable belief state representation. We compare the standard verbose belief state representation (268 dimensions) with the domain-independent representation (57 dimensions) and the proposed representation (13 or 4 dimensions). To test those representations, the recently introduced Advantage Actor Critic (A2C) algorithm is exploited. The latter has not been tested before for any representation apart from the verbose one. We study the effect of the belief state representation within A2C under 0%, 15%, 30%, and 45% semantic error rate and conclude that the novel binary representation in general outperforms both the domain-independent and the verbose belief state representation. Further, the robustness of the binary representation is tested under more realistic scenarios with mismatched semantic error rates, within the A2C and DQN algorithms. The results indicate that the proposed compact, binary representation performs better or similarly to the other representations, being an efficient and promising alternative to the full belief.

show abstract

Dialogue management for an automated multilingual call center

Cited by 10 publications

References 5 publications

The Amitiés system: Data-driven techniques for automated dialogue

The Amitiés system: Data-driven techniques for automated dialogue

Robust Belief State Space Representation for Statistical Dialogue Managers Using Deep Autoencoders

A Case Study on the Importance of Belief State Representation for Dialogue Policy Management

Contact Info

Product

Resources

About