Related papers: Natural Language Generation Using Reinforcement Le…

Natural language generation (NLG) is an important component in spoken dialogue systems. This paper presents a model called Encoder-Aggregator-Decoder which is an extension of an Recurrent Neural Network based Encoder-Decoder architecture.…

Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.…

In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics. However, RL needs to perform exploration, which can be time-consuming due to the slow…

We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC). Unlike conventional maximum likelihood estimation (MLE), the model directly optimizes towards an objective that considers a…

Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorporate language for visual understanding, most existing REC methods rely on rulebased…

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Considering a collection of RDF triples, the RDF-to-text generation task aims to generate a text description. Most previous methods solve this task using a sequence-to-sequence model or using a graph-based model to encode RDF triples and to…

Natural language understanding (NLU) and natural language generation (NLG) are both critical research topics in the NLP field. Natural language understanding is to extract the core semantic meaning from the given utterances, while natural…

Reinforcement learning (RL) algorithms assume that users specify tasks by manually writing down a reward function. However, this process can be laborious and demands considerable technical expertise. Can we devise RL algorithms that instead…

Multilingual retrieval-augmented generation (MRAG) requires models to effectively acquire and integrate beneficial external knowledge from multilingual collections. However, most existing studies employ a unitive process where queries of…

Large language models are extensively utilized in creative writing applications. Creative writing requires a balance between subjective writing quality (e.g., literariness and emotional expression) and objective constraint following (e.g.,…

Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…

We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining…

This paper presents a method for the automatic extraction of subgrammars to control and speeding-up natural language generation NLG. The method is based on explanation-based learning (EBL). The main advantage for the proposed new method for…

Traditionally, approximate dynamic programming is employed in dialogue generation with greedy policy improvement through action sampling, as the natural language action space is vast. However, this practice is inefficient for reinforcement…

Natural language generation (NLG) plays a critical role in spoken dialogue systems. This paper presents a new approach to NLG by using recurrent neural networks (RNN), in which a gating mechanism is applied before RNN computation. This…

In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the…

Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…

In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world…

Reward design in reinforcement learning (RL) is challenging since specifying human notions of desired behavior may be difficult via reward functions or require many expert demonstrations. Can we instead cheaply design rewards using a…