Dangyang Chen


pdf bib
Reinforcement Learning with Token-level Feedback for Controllable Text Generation
Wendi Li | Wei Wei | Kaihe Xu | Wenfeng Xie | Dangyang Chen | Yu Cheng
Findings of the Association for Computational Linguistics: NAACL 2024

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most existing methods suffer from overfitting issues (finetuning-based methods) or semantic collapse (post-processing methods). However, current RL methods are generally guided by coarse-grained (sentence/paragraph-level) feedback, which may lead to suboptimal performance owing to semantic twists or progressions within sentences. To tackle that, we propose a novel reinforcement learning algorithm named TOLE which formulates TOken-LEvel rewards for controllable text generation, and employs a “first-quantize-then-noise” paradigm to enhance the robustness of the RL algorithm. Furthermore, TOLE can be flexibly extended to multiple constraints with little computational expense. Experimental results show that our algorithm can achieve superior performance on both single-attribute and multi-attribute control tasks. We have released our codes at https://github.com/WindyLee0822/CTG.


pdf bib
Miracle: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control
Zhenyi Lu | Wei Wei | Xiaoye Qu | Xian-Ling Mao | Dangyang Chen | Jixiong Chen
Findings of the Association for Computational Linguistics: EMNLP 2023

Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions. Previous approaches have explored explicitly user profile modeling using text descriptions, implicit derivation of user embeddings, or utilizing handicraft prompts for ChatGPT-like models. However, textual personas are limited in describing multi-faceted attributes (e.g., language style, inner character nuances), implicit embedding suffers from personality sparsity, and handicraft prompts lack fine-grained and stable controllability. Hence, these approaches may struggle with complex personalized dialogue generation tasks that require generating controllable responses with multiple personal attributes. To this end, we propose Miracle, a novel personalized dialogue generation method through MultIple PeRsonal Attributes Control within Latent-Space Energy-based Models. ttributes Control within Latent-Space Energy-based Models. Specifically, our approach first disentangles complex personality into multi-faceted attributes. Subsequently, we employ a conditional variational auto-encoder to align with the dense personalized responses within a latent joint attribute space. We have also tailored a dedicated energy function and customized the ordinary differential equations sampling method to offer flexible attribute composition and precise attribute control. Extensive experiments demonstrate that Miracle outperforms several strong baselines in terms of personality controllability and response generation quality. Our dataset and code are available at https://github.com/LZY-the-boys/MIRACLE

pdf bib
TREA: Tree-Structure Reasoning Schema for Conversational Recommendation
Wendi Li | Wei Wei | Xiaoye Qu | Xian-Ling Mao | Ye Yuan | Wenfeng Xie | Dangyang Chen
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Conversational recommender systems (CRS) aim to timely trace the dynamic interests of users through dialogues and generate relevant responses for item recommendations. Recently, various external knowledge bases (especially knowledge graphs) are incorporated into CRS to enhance the understanding of conversation contexts. However, recent reasoning-based models heavily rely on simplified structures such as linear structures or fixed-hierarchical structures for causality reasoning, hence they cannot fully figure out sophisticated relationships among utterances with external knowledge. To address this, we propose a novel Tree structure Reasoning schEmA named TREA. TREA constructs a multi-hierarchical scalable tree as the reasoning structure to clarify the causal relationships between mentioned entities, and fully utilizes historical conversations to generate more reasonable and suitable responses for recommended results. Extensive experiments on two public CRS datasets have demonstrated the effectiveness of our approach.


pdf bib
HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold
Ruihan Zhang | Wei Wei | Xian-Ling Mao | Rui Fang | Dangyang Chen
Findings of the Association for Computational Linguistics: EMNLP 2022

Event detection has been suffering from constantly emerging event types with lack of sufficient data. Existing works formulate the new problem as few-shot event detection (FSED), and employ two-stage or unified models based on meta-learning to address the problem. However, these methods fall far short of expectations due to: (i) insufficient learning of discriminative representations in low-resource scenarios, and (ii) representation overlap between triggers and non-triggers. To resolve the above issues, in this paper, we propose a novel Hybrid Contrastive Learning method with a Task-Adaptive Threshold (abbreviated as HCL-TAT), which enables discriminative representation learning with a two-view contrastive loss (support-support and prototype-query), and devises an easily-adapted threshold to alleviate misidentification of triggers. Extensive experiments on the benchmark dataset FewEvent demonstrate the superiority of our method to achieve better results compared to the state-of-the-arts. All the data and codes will be available to facilitate future research.