Historical Text Normalization with Delayed Rewards
Training neural sequence-to-sequence models with simple token-level log-likelihood is now a standard approach to historical text normalization, albeit often outperformed by phrase-based models. Policy gradient training enables direct optimization for exact matches, and while the small datasets in historical text normalization are prohibitive of from-scratch reinforcement learning, we show that policy gradient fine-tuning leads to significant improvements across the board. Policy gradient training, in particular, leads to more accurate normalizations for long or unseen words.
Code (0)
등록된 구현이 없습니다.
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Text NormalizationSimilar Papers 제목 키워드 기반
Bandit Learning with Delayed Impact of Actions
We consider a stochastic multi-armed bandit (MAB) problem with delayed impact of actions. In our setting, actions taken in the past impact the arm rewards in the subsequent future. This delayed impact of actions is preva…
FairnessMulti-Armed BanditsBeyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning
Reinforcement Learning (RL) empowers agents to acquire various skills by learning from reward signals. Unfortunately, designing high-quality instance-level rewards often demands significant effort. An emerging alternativ…
Reinforcement Learning (RL)Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents
Optimizing large language models (LLMs) for long-horizon caregiver agents requires balancing delayed task objectives with immediate environment dynamics, such as patient distress and resistance. In dementia care, this ba…
Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks
Large Language Models (LLMs) increasingly rely on external tools such as search engines to solve complex agentic tasks that require reasoning and external knowledge retrieval. Recently, reinforcement learning with verifi…
Reinforcement LearningRUDDER: Return Decomposition for Delayed Rewards
We propose RUDDER, a novel reinforcement learning approach for delayed rewards in finite Markov decision processes (MDPs). In MDPs the Q-values are equal to the expected immediate reward plus the expected future rewards.…
Atari Gamesreinforcement-learningReinforcement LearningReinforcement Learning (RL)