English
Related papers

Related papers: Discourse-Aware Neural Rewards for Coherent Text G…

200 papers

Existing open-domain dialogue generation models are usually trained to mimic the gold response in the training set using cross-entropy loss on the vocabulary. However, a good response does not need to resemble the gold response, since there…

Computation and Language · Computer Science 2020-10-06 Wei-Jen Ko , Avik Ray , Yilin Shen , Hongxia Jin

Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…

Computation and Language · Computer Science 2021-06-11 Prakhar Gupta , Yulia Tsvetkov , Jeffrey P. Bigham

Deep reinforcement learning (RL) has been a commonly-used strategy for the abstractive summarization task to address both the exposure bias and non-differentiable task issues. However, the conventional reward Rouge-L simply looks for exact…

Computation and Language · Computer Science 2019-09-12 Siyao Li , Deren Lei , Pengda Qin , William Yang Wang

Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as image editing, reward models are required to capture global…

Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial for good results -- while in principle the reward only needs…

Machine Learning · Computer Science 2022-10-19 Abhishek Gupta , Aldo Pacchiano , Yuexiang Zhai , Sham M. Kakade , Sergey Levine

Reward design for reinforcement learning agents can be difficult in situations where one not only wants the agent to achieve some effect in the world but where one also cares about how that effect is achieved. For example, we might wish for…

Artificial Intelligence · Computer Science 2023-01-25 Xiangyu Peng , Christopher Cui , Wei Zhou , Renee Jia , Mark Riedl

We define a novel neuro-symbolic framework, argumentative reward learning, which combines preference-based argumentation with existing approaches to reinforcement learning from human feedback. Our method improves prior work by generalising…

Artificial Intelligence · Computer Science 2022-10-05 Francis Rhys Ward , Francesco Belardinelli , Francesca Toni

Reinforcement learning (RL) is a powerful approach to enhance task-oriented dialogue (TOD) systems. However, existing RL methods tend to mainly focus on generation tasks, such as dialogue policy learning (DPL) or response generation (RG),…

Artificial Intelligence · Computer Science 2024-06-21 Huifang Du , Shuqin Li , Minghao Wu , Xuejing Feng , Yuan-Fang Li , Haofen Wang

We show that discourse structure, as defined by Rhetorical Structure Theory and provided by an existing discourse parser, benefits text categorization. Our approach uses a recursive neural network and a newly proposed attention mechanism to…

Computation and Language · Computer Science 2017-05-09 Yangfeng Ji , Noah Smith

Sequence-to-sequence models have shown promising improvements on the temporal task of video captioning, but they optimize word-level cross-entropy loss during training. First, using policy gradient and mixed-loss methods for reinforcement…

Computation and Language · Computer Science 2017-08-09 Ramakanth Pasunuru , Mohit Bansal

The rise of personal assistants has made conversational question answering (ConvQA) a very popular mechanism for user-system interaction. State-of-the-art methods for ConvQA over knowledge graphs (KGs) can only learn from crisp…

Information Retrieval · Computer Science 2021-08-23 Magdalena Kaiser , Rishiraj Saha Roy , Gerhard Weikum

Reward design is a critical part of the application of reinforcement learning, the performance of which strongly depends on how well the reward signal frames the goal of the designer and how well the signal assesses progress in reaching…

Machine Learning · Computer Science 2022-08-01 Yixiang Wang , Yujing Hu , Feng Wu , Yingfeng Chen

Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead…

Artificial Intelligence · Computer Science 2019-08-28 Heriberto Cuayáhuitl , Donghyeon Lee , Seonghan Ryu , Sungja Choi , Inchul Hwang , Jihie Kim

Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with…

While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms…

Computation and Language · Computer Science 2022-10-11 Jin Xu , Xiaojiang Liu , Jianhao Yan , Deng Cai , Huayang Li , Jian Li

Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number independently, improving point estimates…

Machine Learning · Computer Science 2026-05-21 Jungsoo Park , Hyungjoo Chae , Ethan Mendes , Jay DeYoung , Varsha Kishore , Wei Xu , Alan Ritter

In complex real-world tasks such as robotic manipulation and autonomous driving, collecting expert demonstrations is often more straightforward than specifying precise learning objectives and task descriptions. Learning from expert data can…

Robotics · Computer Science 2025-05-05 Daulet Baimukashev , Gokhan Alcan , Kevin Sebastian Luck , Ville Kyrki

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…

Machine Learning · Computer Science 2021-12-22 Tom Bewley , Freddy Lecue

As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense…

Machine Learning · Computer Science 2023-10-23 Elizabeth Bates , Vasilios Mavroudis , Chris Hicks

Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story. LM techniques lack the ability to receive…

Computation and Language · Computer Science 2023-01-19 Pradyumna Tambwekar , Murtaza Dhuliawala , Lara J. Martin , Animesh Mehta , Brent Harrison , Mark O. Riedl