Related papers: A Better Variant of Self-Critical Sequence Trainin…

Self-training is one of the earliest and simplest semi-supervised methods. The key idea is to augment the original labeled dataset with unlabeled data paired with the model's prediction (i.e. the pseudo-parallel data). While self-training…

Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot…

Recently it has been shown that policy-gradient methods for reinforcement learning can be utilized to train deep end-to-end systems directly on non-differentiable metrics for the task at hand. In this paper we consider the problem of…

Reranking methods in machine translation aim to close the gap between common evaluation metrics (e.g. BLEU) and maximum likelihood learning and decoding algorithms. Prior works address this challenge by training models to rerank beam search…

In this study, we propose a self-supervised video denoising method called "restore-from-restored." This method fine-tunes a pre-trained network by using a pseudo clean video during the test phase. The pseudo clean video is obtained by…

Self-training is a useful strategy for semi-supervised learning, leveraging raw texts for enhancing model performances. Traditional self-training methods depend on heuristics such as model confidence for instance selection, the manual…

Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.…

We propose a new strategy to improve the accuracy and robustness of image classification. First, we train a baseline CNN model. Then, we identify challenging regions in the feature space by identifying all misclassified samples, and…

Although existing neural retrieval models reveal promising results when training data is abundant and the performance keeps improving as training data increases, collecting high-quality annotated data is prohibitively costly. To this end,…

In this work, we explore whether modeling recurrence into the Transformer architecture can both be beneficial and efficient, by building an extremely simple recurrent module into the Transformer. We compare our model to baselines following…

We propose reCSE, a self supervised contrastive learning sentence representation framework based on feature reshaping. This framework is different from the current advanced models that use discrete data augmentation methods, but instead…

In this paper, we generalize text infilling (e.g., masked language models) by proposing Sequence Span Rewriting (SSR) as a self-supervised sequence-to-sequence (seq2seq) pre-training objective. SSR provides more fine-grained learning…

This paper provides a new way to improve the efficiency of the REINFORCE training process. We apply it to the task of instance selection in distant supervision. Modeling the instance selection in one bag as a sequential decision process, a…

We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing.…

Discrete biological sequence optimization requires iterative refinement under strict syntactic constraints. Diffusion models offer progressive refinement but do not naturally expose controllable discrete edit operations, while…

In this study, we propose a simple and effective fine-tuning algorithm called "restore-from-restored", which can greatly enhance the performance of fully pre-trained image denoising networks. Many supervised denoising approaches can produce…

Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existing algorithms face a tradeoff between computational efficiency and sample efficiency in value…

In this work, we develop a simple algorithm for semi-supervised regression. The key idea is to use the top eigenfunctions of integral operator derived from both labeled and unlabeled examples as the basis functions and learn the prediction…

This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights…

Existing approaches for grammatical error correction (GEC) largely rely on supervised learning with manually created GEC datasets. However, there has been little focus on verifying and ensuring the quality of the datasets, and on how…