Personalization in Goal-Oriented Dialog

Joshi, Chaitanya K.; Mi, Fei; Faltings, Boi

doi:10.48550/arxiv.1706.07503

Cited by 10 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In reinforcement learning a goal that the dialog agent has to achieve is specified, and its performance can be simply measured based on the percent of cases in which it achieves the goal [Li et al, 2017, Havrylov andTitov, 2017]. Similarly for task-oriented dialog agents usually there is a clearly defined task and the accuracy of accomplishing the given task serves as a good performance metric [Joshi et al, 2017, Zhao et al, 2017a, Li et al, 2016b.…”

Section: Evaluation Methodsmentioning

confidence: 99%

“…The first one is the more traditional taskoriented dialog system, which is limited in its conversational capabilities, however it is very robust at executing task specific commands and requirements. Task-oriented models are built to accomplish specific tasks like making restaurant reservations [Joshi et al, 2017 or promoting movies , to name a few. These systems often don't have the ability to respond to arbitrary utterances since they are limited to a specific domain, thus users have to be guided by the dialog system towards the task at hand.…”

Section: Modeling Conversationsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Based Chatbot Models

Csaky

2019

Preprint

View full text Add to dashboard Cite

A conversational agent (chatbot) is a piece of software that is able to communicate with humans using natural language. Modeling conversation is an important task in natural language processing and artificial intelligence (AI). Indeed, ever since the birth of AI, creating a good chatbot remains one of the field's hardest challenges. While chatbots can be used for various tasks, in general they have to understand users' utterances and provide responses that are relevant to the problem at hand.

show abstract

Section: Evaluation Methodsmentioning

confidence: 99%

Section: Modeling Conversationsmentioning

confidence: 99%

Deep Learning Based Chatbot Models

Csaky

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…While personalization has been incorporated into single-task settings (Joshi, Mi, and Faltings 2017;Mo et al 2017;Luo et al 2019;Lu et al 2019;Pei, Ren, and de Rijke 2021), there has been no attempt for personalization in multi-task settings. This is against the background in which multi-task dialogue is rapidly becoming the standard in task-oriented dialogue evaluation (Byrne et al 2019;Rastogi et al 2019;Zang et al 2020;Shalyminov et al 2020).…”

Section: Personalization In Task-oriented Dialoguementioning

confidence: 99%

“…In particular, it allows related tasks to share information (e.g., recommending pizzerias near the stadium where a particular baseball game was played). To utilize personal attributes, task-specific APIs (e.g., Restaurant API) can request taskrelevant personal attributes (e.g., like food) from a centralized Personal Attributes API, before applying them towards personalization in a similar manner to the single-task setting (Mo et al 2017;Joshi, Mi, and Faltings 2017;Lu et al 2019).…”

Section: Datasetmentioning

confidence: 99%

“…Code at https://github.com/Zhilin123/personal attributes Personal attributes can also help task-oriented dialogue agents to provide personalized recommendations (Mo et al 2017;Joshi, Mi, and Faltings 2017;Luo et al 2019;Lu et al 2019;Pei, Ren, and de Rijke 2021). Such personalized recommendations have only been attempted for singledomain tasks with a small set of one-hot features (< 30).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extracting and Inferring Personal Attributes from Dialogue

Wang¹,

Zhou²,

Koncel-Kedziorski³

et al. 2021

Preprint

View full text Add to dashboard Cite

Personal attributes represent structured information about a person, such as their hobbies, pets, family, likes and dislikes. In this work, we introduce the tasks of extracting and inferring personal attributes from human-human dialogue. We first demonstrate the benefit of incorporating personal attributes in a social chit-chat dialogue model and task-oriented dialogue setting. Thus motivated, we propose the tasks of personal attribute extraction and inference, and then analyze the linguistic demands of these tasks. To meet these challenges, we introduce a simple and extensible model that combines an autoregressive language model utilizing constrained attribute generation with a discriminative reranker. Our model outperforms strong baselines on extracting personal attributes as well as inferring personal attributes that are not contained verbatim in utterances and instead requires commonsense reasoning and lexical inferences, which occur frequently in everyday conversation.

show abstract

AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions

Zhang

Guo

Wang

et al. 2019

2019 IEEE SmartWorld, Ubiquitous Intelligence &Amp; Computing, Advanced &Amp; Trusted Computing, Scalable Computing &Amp; Commu

View full text Add to dashboard Cite

In the last two decades, the landscape of text generation has undergone tremendous changes and is being reshaped by the success of deep learning. New technologies for text generation ranging from template-based methods to neural network-based methods emerged. Meanwhile, the research objectives have also changed from generating smooth and coherent sentences to infusing personalized traits to enrich the diversification of newly generated content. With the rapid development of text generation solutions, one comprehensive survey is urgent to summarize the achievements and track the state of the arts. In this survey paper, we present the general systematical framework, illustrate the widely utilized models and summarize the classic applications of text generation.

show abstract

Personalization in Goal-Oriented Dialog

Cited by 10 publications

References 0 publications

Deep Learning Based Chatbot Models

Deep Learning Based Chatbot Models

Extracting and Inferring Personal Attributes from Dialogue

AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions

Contact Info

Product

Resources

About