Related papers: $k$-Neighbor Based Curriculum Sampling for Sequenc…

Humans can infer a great deal about the meaning of a word, using the syntax and semantics of surrounding words even if it is their first time reading or hearing it. We can also generalise the learned concept of the word to new tasks.…

A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model. Surprisingly, this two-step knowledge distillation process often leads to…

Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the…

The high sample complexity of reinforcement learning challenges its use in practice. A promising approach is to quickly adapt pre-trained policies to new environments. Existing methods for this policy adaptation problem typically rely on…

Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens. We propose using k nearest neighbor (kNN) representations to identify…

Wide usage of ChatGPT has highlighted the potential of reinforcement learning from human feedback. However, its training pipeline relies on manual ranking, a resource-intensive process. To reduce labor costs, we propose a self-supervised…

Modern applications and progress in deep learning research have created renewed interest for generative models of text and of images. However, even today it is unclear what objective functions one should use to train and evaluate these…

This paper surveys and organizes research works in a new paradigm in natural language processing, which we dub "prompt-based learning". Unlike traditional supervised learning, which trains a model to take in an input x and predict an output…

Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore, which allows them to learn through explicitly memorizing the training datapoints. While effective, these models often…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

How to achieve better end-to-end speech translation (ST) by leveraging (text) machine translation (MT) data? Among various existing techniques, multi-task learning is one of the effective ways to share knowledge between ST and MT in which…

With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. A recently proposed method named Context Optimization (CoOp) introduces the…

k-Nearest Neighbors is one of the most fundamental but effective classification models. In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nearest Neighbors…

Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as…

To train neural machine translation models simultaneously on multiple tasks (languages), it is common to sample each task uniformly or in proportion to dataset sizes. As these methods offer little control over performance trade-offs, we…

Many text classification methods usually introduce external information (e.g., label descriptions and knowledge bases) to improve the classification performance. Compared to external information, some internal information generated by the…

Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Since this requires both models to share the same probability space, it becomes challenging…

We simplify sentences with an attentive neural network sequence to sequence model, dubbed S4. The model includes a novel word-copy mechanism and loss function to exploit linguistic similarities between the original and simplified sentences.…

Neural machine translation (NMT) models are usually trained with the word-level loss using the teacher forcing algorithm, which not only evaluates the translation improperly but also suffers from exposure bias. Sequence-level training under…

Grammatical error correction can be viewed as a low-resource sequence-to-sequence task, because publicly available parallel corpora are limited. To tackle this challenge, we first generate erroneous versions of large unannotated corpora…