Open-Domain Neural Conversational Agents: The Step Towards Artificial General Intelligence

Arsovski, Sasa; Wong, Sze Hui; Cheok, Adrian David

doi:10.14569/ijacsa.2018.090654

Cited by 8 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The underlying idea for this approach is to share the encoding of the question encoder to perform both tasks so that the question encoder overfit can be reduced. For example, [6] utilized binary question-answer classification as an auxiliary task (Figure 4). Binary classification refers to a classification in which an answer is classified as either correct or incorrect.…”

Section: Question Encoder Overfit Issuementioning

confidence: 99%

See 1 more Smart Citation

SEQ2SEQ++: A Multitasking-Based Seq2seq Model to Generate Meaningful and Relevant Answers

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Question Encoder Overfit Issuementioning

confidence: 99%

“…The former ones help humans perform specific tasks to achieve a specific goal, such as booking a hotel, flight, or even performing a financial transaction [5]. The latter ones act as companions for humans and can be further classified as either casual chatbots or question-answering chatbots [3], [6]- [9].…”

Section: Introductionmentioning

confidence: 99%

SEQ2SEQ++: A Multitasking-Based Seq2seq Model to Generate Meaningful and Relevant Answers

et al. 2021

View full text Add to dashboard Cite

show abstract

“…On the other hand, when the task requires a more unconstrained interaction (Arsovski, Wong, and Cheok 2018), such as answering open questions, chit‐chat, handling complaints, or where many possible situations, domains or topics must be handled, then good solutions are currently available through deep learning algorithms or hybrid approaches (combining rules, information retrieval, and deep learning models).…”

Section: General Considerationsmentioning

confidence: 99%

Considerations on creating conversational agents for multiple environments and users

Cebrián¹,

Martínez-Jiménez²,

Rodrı́guez³

et al. 2021

AI Magazine

View full text Add to dashboard Cite

Advances in artificial intelligence algorithms and expansion of straightforward cloud-based platforms have enabled the adoption of conversational assistants by both, medium and large companies, to facilitate interaction between clients and employees. The interactions are possible through the use of ubiquitous devices (e.g., Amazon Echo, Apple HomePod, Google Nest), virtual assistants (e.g., Apple Siri, Google Assistant, Samsung Bixby, or Microsoft Cortana), chat windows on the corporate website, or social network applications (e.g. Facebook Messenger, Telegram, Slack, WeChat).Creating a useful, personalized conversational agent that is also robust and popular is nonetheless challenging work. It requires picking the right algorithm, framework, and/or communication channel, but perhaps more importantly, consideration of the specific task, user needs, environment, available training data, budget, and a thoughtful design.In this paper, we will consider the elements necessary to create a conversational agent for different types of users, environments, and tasks. The elements will account for the limited amount of data available for specific tasks within a company and for non-English languages. We are confident that we can provide a useful resource for the new practitioner developing an agent. We can point out novice problems/traps to avoid, create consciousness that the development of the technology is achievable despite comprehensive and significant challenges, and raise awareness about different ethical issues that may be associated with this technology. We have compiled our experience with deploying conversational systems for daily use in multicultural, multilingual, and intergenerational settings. Additionally, we will give insight on how to scale the proposed solutions.

show abstract

“…In particular, rule-based, frame-based and agent-based approaches used in finite-state dialogue management systems and their combination were proposed in [15], [16], and [17]. Recent advanced and desirable techniques in machine learning-based methods and a drawn-out motivation in neural network model to the conversational agent development having more complexity and high efficiency were suggested in [4], [18], [19], [20], [21], and [22].…”

Section: Related Workmentioning

confidence: 99%

The Neural Network Conversation Model enables the Commonly Asked Student Query Agents

Muangnak¹,

Thasnas²,

Hengsanunkul³

et al. 2020

IJACSA

View full text Add to dashboard Cite

One of the challenges in academic counselling is to provide an automated service system for students. There several query questions asking the faculty staffs about related-academic services each semester. Offered the communication interface more convenience, the novel approach based on neural network model is introduced to investigate the automated conversational agent. The pre-defined dialogue sentences were collected manually from the student query questions and used as the training dataset. The questions have been varied and grouped by topic-categorizing queried from the registration help desk of the department. Artificial intelligence and machine learning have contributed each other to build the conversational agent so-call KUSE-ChatBOT plugged and used in the modern messenger application, LINE. The system is also included the dialogue backend management system to use in further deep learning model updating. Tensorflow, the machine learning development platform originated by Google, was performed and obtained the learning model using Python development kits. The LINE Messaging APIs is then contributed as the user interface where users could have FAQs' conversation via the LINE application. The KUSE-ChatBOT is outperformed and efficient by providing automated consultation to the students precisely with the accuracy rate over 75 percent. The system could assist the staffs to be able to lessen the workload of answering the same question repeatedly and give response to the student timely.

show abstract

Open-Domain Neural Conversational Agents: The Step Towards Artificial General Intelligence

Cited by 8 publications

References 14 publications

SEQ2SEQ++: A Multitasking-Based Seq2seq Model to Generate Meaningful and Relevant Answers

SEQ2SEQ++: A Multitasking-Based Seq2seq Model to Generate Meaningful and Relevant Answers

Considerations on creating conversational agents for multiple environments and users

The Neural Network Conversation Model enables the Commonly Asked Student Query Agents

Contact Info

Product

Resources

About