Related papers: Learning to Write with Coherence From Negative Exa…
Text generation is of great importance to many natural language processing applications. However, maximization-based decoding methods (e.g. beam search) of neural language models often lead to degenerate solutions -- the generated text is…
Natural language generation (NLG) is a critical component in spoken dialogue system, which can be divided into two phases: (1) sentence planning: deciding the overall sentence structure, (2) surface realization: determining specific word…
While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment. We propose…
Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks. Maximum-Likelihood (MLE) models trained with teacher forcing have consistently been reported as weak baselines,…
Learning depends on the ability to acquire and assimilate new information. This ability depends---somewhat counterintuitively---on the ability to forget. In particular, effective forgetting requires the ability to recognize and utilize new…
Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…
This paper studied generating natural languages at particular contexts or situations. We proposed two novel approaches which encode the contexts into a continuous semantic representation and then decode the semantic representation into text…
Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural…
Sensitivity of deep-neural models to input noise is known to be a challenging problem. In NLP, model performance often deteriorates with naturally occurring noise, such as spelling errors. To mitigate this issue, models may leverage…
Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative…
We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two…
Ensuring annotator quality in training and evaluation data is a key piece of machine learning in NLP. Tasks such as sentiment analysis and offensive speech detection are intrinsically subjective, creating a challenging scenario for…
With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data with billion-scale natural language generation (NLG) models,…
On the one hand, there has been considerable progress on neural network verification in recent years, which makes certifying neural networks a possibility. On the other hand, neural networks in practice are often re-trained over time to…
While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution but faces two critical obstacles: designing reliable reward…
In conversational question answering (CQA), the task of question rewriting~(QR) in context aims to rewrite a context-dependent question into an equivalent self-contained question that gives the same answer. In this paper, we are interested…
We address the task of assessing discourse coherence, an aspect of text quality that is essential for many NLP tasks, such as summarization and language assessment. We propose a hierarchical neural network trained in a multi-task fashion…
This paper describes our submission to the shared task on word/phrase level Quality Estimation (QE) in the First Conference on Statistical Machine Translation (WMT16). The objective of the shared task was to predict if the given word/phrase…
Natural Language Inference (NLI) is the task of determining whether a premise entails, contradicts, or is neutral with respect to a given hypothesis. The task is often framed as emulating human inferential processes, in which commonsense…
In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to…