Related papers: Contrastive Learning with Adversarial Perturbation…

Generative Adversarial Networks (GANs) for text generation have recently received many criticisms, as they perform worse than their MLE counterparts. We suspect previous text GANs' inferior performance is due to the lack of a reliable…

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…

Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…

We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is…

To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations. Under this…

We study the problem of active learning with the added twist that the learner is assisted by a helpful teacher. We consider the following natural interaction protocol: At each round, the learner proposes a query asking for the label of an…

Conditional Generative Adversarial Networks (cGANs) extend the standard unconditional GAN framework to learning joint data-label distributions from samples, and have been established as powerful generative models capable of generating…

Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech…

Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones. Taking the former text as positive and the latter as negative samples, the PLM can be trained effectively for…

In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via…

We introduce a novel data generation method for contradiction detection, which leverages the generative power of large language models as well as linguistic rules. Our vision is to provide a condensed corpus of prototypical contradictions,…

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

This paper studies constrained text generation, which is to generate sentences under certain pre-conditions. We focus on CommonGen, the task of generating text based on a set of concepts, as a representative task of constrained text…

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…

We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well…

Machine translation and other NLP systems often contain significant biases regarding sensitive attributes, such as gender or race, that worsen system performance and perpetuate harmful stereotypes. Recent preliminary research suggests that…

In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated dialogue…

Neural language models are often trained with maximum likelihood estimation (MLE), where the next word is generated conditioned on the ground-truth word tokens. During testing, however, the model is instead conditioned on previously…

Visual contrastive learning aims to learn representations by contrasting similar (positive) and dissimilar (negative) pairs of data samples. The design of these pairs significantly impacts representation quality, training efficiency, and…

Negative sampling is a limiting factor w.r.t. the generalization of metric-learned neural networks. We show that uniform negative sampling provides little information about the class boundaries and thus propose three novel techniques for…