{"total":48,"rows":[{"id":"2210.04185","title":"Controllable Dialogue Simulation with In-Context Learning","created":"2022-10-09","cited_by_count":42,"area":null},{"id":"2107.11904","title":"Transferable Dialogue Systems and User Simulators","created":"2021-07-25","cited_by_count":36,"area":null},{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2212.09072","title":"Let's Negotiate! A Survey of Negotiation Dialogue Systems","created":"2022-12-18","cited_by_count":31,"area":null},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30,"area":null},{"id":"2103.10518","title":"Pretraining the Noisy Channel Model for Task-Oriented Dialogue","created":"2021-03-18","cited_by_count":23,"area":null},{"id":"2405.13003","title":"A Survey on Recent Advances in Conversational Data Generation","created":"2024-05-12","cited_by_count":23,"area":null},{"id":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22,"area":null},{"id":"2109.04919","title":"EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems","created":"2021-09-10","cited_by_count":20,"area":null},{"id":"2205.02471","title":"BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog","created":"2022-05-05","cited_by_count":20,"area":null},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2311.09008","title":"End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions","created":"2023-11-15","cited_by_count":17,"area":null},{"id":"2109.12761","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2108.13679","title":"Task-Oriented Dialogue System as Natural Language Generation","created":"2021-08-31","cited_by_count":14,"area":null},{"id":"2109.04314","title":"Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems","created":"2021-09-09","cited_by_count":13,"area":null},{"id":"2211.16773","title":"KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning","created":"2022-11-30","cited_by_count":9,"area":null},{"id":"2106.02317","title":"Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory","created":"2021-06-04","cited_by_count":8,"area":null},{"id":"2203.00073","title":"Structure Extraction in Task-Oriented Dialogues with Slot Clustering","created":"2022-02-28","cited_by_count":8,"area":null},{"id":"2208.02294","title":"Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2210.08692","title":"A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems","created":"2022-10-17","cited_by_count":6,"area":null},{"id":"2308.00878","title":"DiactTOD: Learning Generalizable Latent Dialogue Acts for Controllable Task-Oriented Dialogue Systems","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2207.12185","title":"Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning","created":"2022-07-25","cited_by_count":5,"area":null},{"id":"2103.06370","title":"Causal-aware Safe Policy Improvement for Task-oriented dialogue","created":"2021-03-10","cited_by_count":4,"area":null},{"id":"2205.14748","title":"Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition","created":"2022-05-29","cited_by_count":4,"area":null},{"id":"2209.04595","title":"OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue","created":"2022-09-10","cited_by_count":4,"area":null},{"id":"2102.04506","title":"A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining","created":"2021-02-08","cited_by_count":3,"area":null},{"id":"2106.07728","title":"Targeted Data Acquisition for Evolving Negotiation Agents","created":"2021-06-14","cited_by_count":3,"area":null},{"id":"2109.07779","title":"Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2205.12590","title":"RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2207.12235","title":"Advancing Semi-Supervised Task Oriented Dialog Systems by JSA Learning of Discrete Latent Variable Models","created":"2022-07-25","cited_by_count":3,"area":null},{"id":"2209.00876","title":"Dialogue Evaluation with Offline Reinforcement Learning","created":"2022-09-02","cited_by_count":3,"area":null},{"id":"2209.11128","title":"Learning Interpretable Latent Dialogue Actions With Less Supervision","created":"2022-09-22","cited_by_count":3,"area":null},{"id":"2309.04739","title":"Data Augmentation for Conversational AI","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2103.05434","title":"When is it permissible for artificial intelligence to lie? A trust-based approach","created":"2021-03-09","cited_by_count":2,"area":null},{"id":"2107.03286","title":"DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2209.07873","title":"Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2106.04835","title":"Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2205.07633","title":"Taming Continuous Posteriors for Latent Variational Dialogue Policies","created":"2022-05-16","cited_by_count":1,"area":null},{"id":"2205.10558","title":"CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models","created":"2022-05-21","cited_by_count":1,"area":null},{"id":"2303.13465","title":"Deep RL with Hierarchical Action Exploration for Dialogue Generation","created":"2023-03-22","cited_by_count":1,"area":null},{"id":"2305.03262","title":"Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2411.16305","title":"Learning from Relevant Subgoals in Successful Dialogs using Iterative Training for Task-oriented Dialog Systems","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2110.13213","title":"Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users","created":"2021-10-25","cited_by_count":0,"area":null},{"id":"2210.06706","title":"Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2308.02903","title":"LaDA: Latent Dialogue Action For Zero-shot Cross-lingual Neural Network Language Modeling","created":"2023-08-05","cited_by_count":0,"area":null},{"id":"2402.01097","title":"Let's Negotiate! A Survey of Negotiation Dialogue Systems","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2604.18354","title":"PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues","created":"2026-04-20","cited_by_count":0,"area":null}],"next_cursor":null}