CLASSY: A Conversational Aware Suggestion System

Abstract. In this paper we give an overview of the participation of the IRIT lab, University of Toulouse, France, in the TREC 2012 Contextual Suggestion Track. We present our personalized contextual retrieval framework, an approach for context processing, and two approaches for user preference processing. The official evaluations of our two submitted runs are reported and compared to the four baselines defined for the track. Evaluation results show that one of our submitted run was ranked 1st among the 27 runs of the 14 ...

Journal of Artificial Intelligence …, 2004

Searching for and making decisions about information is becoming increasingly difficult as the amount of information and number of choices increases. Recommendation systems help users find items of interest of a particular type, such as movies or restaurants, but are still somewhat awkward to use. Our solution is to take advantage of the complementary strengths of personalized recommendation systems and dialogue systems, creating personalized aides. We present a system -the Adaptive Place Advisor -that treats item selection as an interactive, conversational process, with the program inquiring about item attributes and the user responding. Individual, long-term user preferences are unobtrusively obtained in the course of normal recommendation dialogues and used to direct future conversations with the same user. We present a novel user model that influences both item search and the questions asked during a conversation. We demonstrate the effectiveness of our system in significantly reducing the time and number of interactions required to find a satisfactory item, as compared to a control group of users interacting with a non-adaptive version of the system.

Context-awarenessisanessentialrequirementincraftingrec- ommender systems that provide serendipity, i.e. “pleasant surprises”, in- dependently of human command. These solutions must be able to infer interactions based on data from sensors and recognised activities in order to infer what is useful information and when to deliver it. For that, we are devising advanced models of context inference based on the analysis of users’ signals during everyday activities. In this paper, we present a proof-of-concept platform that allows for the application of techniques of deep learning and context analytics to derive patterns in spatio-temporal context signals. We call this composition Big Context. We argue that by understanding how people and things are connected, one can devise novel forms of interactions that provide a more pleasant user experience. In this work, we introduce our method and platform, and illustrate some of the possible techniques using a prototype application that provides serendipitous recommendations.

ICCBR Workshop Proceedings, 2010

Abstract. In this paper, we describe a Conversational Interaction framework as an innovative and natural approach to facilitate easier information access by combining web search and recommendations. This framework includes an intelligent information agent (Cobot) in the conversation that provides contextually relevant social and web search recommendations. This setup leverages the information discovery process by integrating web information retrieval along with proactive connections to relevant users who can participate in real ...

Proceedings of the 2nd International Conference on Pervasive Embedded Computing and Communication Systems, 2012

Services relevance is strictly connected to the environment in which they are provided and one service that is highly relevant in a particular environment can be a completely inappropriate service in a different context or in a different environment. To provide relevant and appropriate services, the systems should be aware of their environment, the needs and interests of users and should adapt their behaviour to the specific needs of each particular place and each particular set of users' current interests. The combination of users' personal interactions to build the social context of a public place represents an important support to allow services adaptiveness and thus adjust systems behaviour to best fit users' needs and space characteristics. This paper provides an overview of some aspects that involve the combination of personal interactions to build socially-aware systems. It also describes two experiments, where social context was used to improve services usefulness. Results indicate that this combination can represent an important aspect to be considered in the way to provide users with novel, relevant and suitable services.

Proceedings of the 28th International Conference on Computational Linguistics, 2020

Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. To develop an effective CRS, the support of high-quality datasets is essential. Existing CRS datasets mainly focus on immediate requests from users, while lack proactive guidance to the recommendation scenario. In this paper, we contribute a new CRS dataset named TG-ReDial (Recommendation through Topic-Guided Dialog). Our dataset has two major features. First, it incorporates topic threads to enforce natural semantic transitions towards the recommendation scenario. Second, it is created in a semi-automatic way, hence human annotation is more reasonable and controllable. Based on TG-ReDial, we present the task of topic-guided conversational recommendation, and propose an effective approach to this task. Extensive experiments have demonstrated the effectiveness of our approach on three sub-tasks, namely topic prediction, item recommendation and response generation. TG-ReDial is available at https://github.com/RUCAIBox/TG-ReDial.

Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)

Conversational recommendation systems (CRS) aim to recommend suitable items to users through natural language conversation. However, most CRS approaches do not effectively utilize the signal provided by these conversations. They rely heavily on explicit external knowledge e.g., knowledge graphs to augment the models' understanding of the items and attributes, which is quite hard to scale. To alleviate this, we propose an alternative information retrieval (IR)-styled approach to the CRS item recommendation task, where we represent conversations as queries and items as documents to be retrieved. We expand the document representation used for retrieval with conversations from the training set. With a simple BM25-based retriever, we show that our task formulation compares favorably with much more complex baselines using complex external knowledge on a popular CRS benchmark. We demonstrate further improvements using user-centric modeling and data augmentation to counter the cold start problem for CRSs.

2003

In ongoing discussions participants tend to pick up their smart phones to retrieve relevant information for clarification, severely hampering the flow of the discussion. We introduce ambient search as a variant of information retrieval where a system unobtrusively provides relevant information snippets in the background without the need to steer devices actively. In this demo paper, we describe a first prototype of our ongoing research activities towards such a system.

Striking up a good conversation with new acquaintances is often difficult. In this paper we introduce a system that uses a ranking recommendation algorithm to generate real-time personalized topic suggestions during a conversation. The system then delivers the suggestions via Google Glass. We conducted a study with 38 pairs of strangers, who received such suggestions while conversing with a person they met for the first time. Participants found the suggestions to be helpful, but only at the right moments, and for certain types of speakers. Our results contribute to the understanding of how communication interventions influence people's experience and behaviors, and enhance interpersonal interactions. Our study also presents design implications for applications on wearable devices to facilitate conversations between strangers.