Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue

@inproceedings{Kang2019RecommendationAA,
  title={Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue},
  author={Dongyeop Kang and Anusha Balakrishnan and Pararth Shah and Paul A. Crook and Y-Lan Boureau and Jason Weston},
  booktitle={EMNLP},
  year={2019}
}
Traditional recommendation systems produce static rather than interactive recommendations invariant to a user’s specific requests, clarifications, or current mood, and can suffer from the cold-start problem if their tastes are unknown. These issues can be alleviated by treating recommendation as an interactive dialogue task instead, where an expert recommender can sequentially ask about someone’s preferences, react to their requests, and recommend more appropriate items. In this work, we… 

Figures and Tables from this paper

Self-Supervised Bot Play for Conversational Recommendation with Justifications
TLDR
A new two-part framework for training conversational recommender systems is developed, which can be applied to different recommendation models across diverse domains to achieve superior performance in conversational recommendation compared to state-of-the-art methods.
Popcorn: Human-in-the-loop Popularity Debiasing in Conversational Recommender Systems
TLDR
This paper proposes a human-in-the-loop popularity debiasing framework that integrates real-time semantic understanding of open-ended user utterances as well as historical records, while also effectively managing the dialogue with the user.
DEUX: An Attribute-Guided Framework for Sociable Recommendation Dialog Systems
TLDR
DUX is proposed, a novel attribute-guided framework to create better user experiences while accomplishing a movie recommendation task and outperforms all the baselines on being more consistent, fitting the user preferences better, and providing a more engaging chat experience.
Towards Conversational Recommendation over Multi-Type Dialogs
TLDR
This work creates a human-to-human Chinese dialog dataset DuRecDial, where there are multiple sequential dialogs for a pair of a recommendation seeker and a recommender, where the recommender proactively leads a multi-type dialog to approach recommendation targets and then makes multiple recommendations with rich interaction behavior.
E-ConvRec: A Large-Scale Conversational Recommendation Dataset for E-Commerce Customer Service
TLDR
E-ConvRec is constructed, an authentic Chinese dialogue dataset consisting of over 25k dialogues and 770k utterances, which contains user profile, product knowledge base (KB), and multiple sequential real conversations between users and recommenders to explore conversational recommendation in a real scene from multiple facets based on the dataset.
Learning Neural Templates for Recommender Dialogue System
TLDR
This work introduces a novel framework called NTRD for recommender dialogue system that can decouple the dialogue generation from the item recommendation and has the unique advantage to produce novel items that do not appear in the training set of dialogue corpus.
Bridging the Gap between Conversational Reasoning and Interactive Recommendation
TLDR
A novel recommender dialog model that walks on a large-scale knowledge graph to form a reasoning tree at each turn, then mapped to dialog acts to guide response generation and maximizes the mutual benefit between two systems.
Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy
TLDR
A new solution named I-Pro is proposed that can learn Proactive policy in the Interactive setting via a learned goal weight, which consists of four factors (dialogue turn, goal completion difficulty, user satisfaction estimation, and cooperative degree).
Target-guided Knowledge-aware Recommendation Dialogue System: An Empirical Investigation (Long paper)
TLDR
This paper designs a dialogue generation system that employs pre-trained language models with multi-task learning to jointly learn response generation and goal prediction towards the target and presents a knowledge-preserving encoding strategy to maintain the facts in background knowledge.
INSPIRED: Toward Sociable Recommendation Dialog Systems
TLDR
This work designs an annotation scheme related to recommendation strategies based on social science theories and annotate these dialogs, and shows that sociable recommendation strategies, such as sharing personal opinions or communicating with encouragement, more frequently lead to successful recommendations.
...
...

References

SHOWING 1-10 OF 31 REFERENCES
Towards Deep Conversational Recommendations
TLDR
This paper collects ReDial, a data set consisting of over 10,000 conversations centered around the theme of providing movie recommendations and uses this dataset to explore new neural architectures, mechanisms and methods suitable for composing conversational recommendation systems.
Deal or No Deal? End-to-End Learning of Negotiation Dialogues
TLDR
For the first time, it is shown it is possible to train end-to-end models for negotiation, which must learn both linguistic and reasoning skills with no annotated dialogue states, and this technique dramatically improves performance.
Learning End-to-End Goal-Oriented Dialog
TLDR
It is shown that an end-to-end dialog system based on Memory Networks can reach promising, yet imperfect, performance and learn to perform non-trivial operations and be compared to a hand-crafted slot-filling baseline on data from the second Dialog State Tracking Challenge.
Decoupling Strategy and Generation in Negotiation Dialogues
TLDR
A modular approach based on coarse dialogue acts (e.g., propose(price=50)) that decouples strategy and generation that can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy is proposed.
Modeling a Dialogue Strategy for Personalized Movie Recommendations
This paper addresses conversational interaction in user-adaptive recommender systems. By collecting and analyzing a movie recommendation dialogue corpus, two initiative types that need to be
Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings
TLDR
A neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses is proposed, which is both more effective at achieving the goal and more human-like than baseline neural and rule-based models.
Personalizing Dialogue Agents: I have a dog, do you have pets too?
TLDR
This work collects data and train models tocondition on their given profile information; and information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction.
Hierarchical Text Generation and Planning for Strategic Dialogue
TLDR
An approach to learning representations of messages in dialogues by maximizing the likelihood of subsequent sentences and actions, which decouples the semantics of the dialogue utterance from its linguistic realization, which outperforms previous work both linguistically and strategically.
Recommender systems with social regularization
TLDR
This paper proposes a matrix factorization framework with social regularization, which can be easily extended to incorporate other contextual information, like social tags, etc, and demonstrates that the approaches outperform other state-of-the-art methods.
Mastering the game of Go without human knowledge
TLDR
An algorithm based solely on reinforcement learning is introduced, without human data, guidance or domain knowledge beyond game rules, that achieves superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.
...
...