Contextual Intent Tracking for Personal Assistants

Sun, Yu; Yuan, Nicholas Jing; Wang, Yingzi; Xie, Xing; McDonald, Kieran; Zhang, Rui

doi:10.1145/2939672.2939676

Cited by 51 publications

(19 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Task-oriented dialogue system has been a longstanding studied topic (Williams and Young, 2007;Lee et al, 2009;Huang et al, 2020b) and can be integrated into many practical applications such as virtual assistant (Sun et al, 2016(Sun et al, , 2017. Traditionally, task-oriented dialogue systems are built in the pipeline approach, which consists of four essential components: natural language understanding (Chen et al, 2016), dialogue state tracking (Lee and Stent, 2016;Zhong et al, 2018;Wu et al, 2019a), policy learning (Su et al, 2016;Peng et al, 2018;Su et al, 2018) and natural language generation (Sharma et al, 2017;Chen et al, 2019;Huang et al, 2020a).…”

Section: Related Workmentioning

confidence: 99%

GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems

Yang¹,

Zhang²,

Erfani³

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs. There are two challenges for such systems: one is how to effectively incorporate external knowledge bases (KBs) into the learning framework; the other is how to accurately capture the semantics of dialogue history. In this paper, we address these two challenges by exploiting the graph structural information in the knowledge base and in the dependency parsing tree of the dialogue. To effectively leverage the structural information in dialogue history, we propose a new recurrent cell architecture which allows representation learning on graphs. To exploit the relations between entities in KBs, the model combines multi-hop reasoning ability based on the graph structure. Experimental results show that the proposed model achieves consistent improvement over state-of-the-art models on two different task-oriented dialogue datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems

Yang¹,

Zhang²,

Erfani³

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…We can also see that although the context by LTM or LTR approaches is of relative low relevance (measured by nDCG@10), our model can still achieve comparable quality of the generated SERP. Besides contextual ranking list, various types of information (e.g., users activities [31] [32]) can be considered into context in the future.…”

Section: ) Effect Of Contextmentioning

confidence: 99%

CARL: Aggregated Search with Context-Aware Module Embedding Learning

Huang

Sun

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Aggregated search aims to construct search result pages (SERPs) from blue-links and heterogeneous modules (such as news, images, and videos). Existing studies have largely ignored the correlations between blue-links and heterogeneous modules when selecting the heterogeneous modules to be presented. We observe that the top ranked blue-links, which we refer to as the context, can provide important information about query intent and helps identify the relevant heterogeneous modules. For example, informative terms like "streamed" and "recorded" in the context imply that a video module may better satisfy the query. To model and utilize the context information for aggregated search, we propose a model with context attention and representation learning (CARL). Our model applies a recurrent neural network with attention mechanism to encode the context, and incorporates the encoded context information into module embeddings. The context-aware module embeddings together with the ranking policy are jointly optimized under the Markov decision process (MDP) formulation. To achieve a more effective joint learning, we further propose an optimization function with self-supervision loss to provide auxiliary supervision signals. Experimental results based on two public datasets demonstrate the superiority of CARL over multiple baseline approaches, and confirm the effectiveness of the proposed optimization function in boosting the joint learning process.Index Terms-information retrieval, reinforcement learning, attention mechanism * Corresponding author Fig. 1. Contextual ranking list (upper left) and aggregated SERP (upper right). Correlations are observed between the blue-links and modules marked by the same color, and the detailed informative terms are listed.Conventional aggregated search frameworks use a pipeline with two sequential subtasks: module selection and module presentation. The first subtask selects relevant modules from

show abstract

“…Sun et al [13] are interested in contextual intent. Contextual intent attaches importance to context with a particular emphasis on external physical environment, and complex context-intent relationships are modeled.…”

Section: Related Workmentioning

confidence: 99%

User Interests Clustering in Business Intelligence Interactions

Drushku

Aligon

Labroche

et al. 2017

Advanced Information Systems Engineering

View full text Add to dashboard Cite

Abstract. It is quite common these days for experts, casual analysts, executives or data enthusiasts, to analyze large datasets using userfriendly interfaces on top of Business Intelligence (BI) systems. However, current BI systems do not adequately detect and characterize user interests, which may lead to tedious and unproductive interactions. In this paper, we propose to identify such user interests by characterizing the intent of the interaction with the BI system. With an eye on user modeling for proactive search systems, we identify a set of features for an adequate description of intents, and a similarity measure for grouping intents into coherent interests. We validate experimentally our approach with a user study, where we analyze traces of BI navigation. We show that our similarity measure outperforms a state-of-the-art query similarity measure and yields a very good precision with respect to expressed user interests.

show abstract

Contextual Intent Tracking for Personal Assistants

Cited by 51 publications

References 20 publications

GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems

GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems

CARL: Aggregated Search with Context-Aware Module Embedding Learning

User Interests Clustering in Business Intelligence Interactions

Contact Info

Product

Resources

About