Related papers: Curriculum-Based Neighborhood Sampling For Sequenc…

To improve word representation learning, we propose a probabilistic prior which can be seamlessly integrated with word embedding models. Different from previous methods, word embedding is taken as a probabilistic generative model, and it…

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…

We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective incentivises the system to learn general-purpose patterns of…

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., the language model pre-trained on static data from past years performs worse over time on emerging data. Existing…

Neural ranking models are traditionally trained on a series of random batches, sampled uniformly from the entire training set. Curriculum learning has recently been shown to improve neural models' effectiveness by sampling batches…

System combination is an important technique for combining the hypotheses of different machine translation systems to improve translation performance. Although early statistical approaches to system combination have been proven effective in…

Class-based language models (LMs) have been long devised to address context sparsity in $n$-gram LMs. In this study, we revisit this approach in the context of neural LMs. We hypothesize that class-based prediction leads to an implicit…

Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time…

Adequate sampling space coverage is the keystone to effectively train trustworthy Machine Learning models. Unfortunately, real data do carry several inherent risks due to the many potential biases they exhibit when gathered without a proper…

Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Even…

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…

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…

Spatio-temporal sequence forecasting is one of the fundamental tasks in spatio-temporal data mining. It facilitates many real world applications such as precipitation nowcasting, citywide crowd flow prediction and air pollution forecasting.…

Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is…

Nearest neighbor is a popular nonparametric method for classification and regression with many appealing properties. In the big data era, the sheer volume and spatial/temporal disparity of big data may prohibit centrally processing and…

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as data distributions…

To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and investigated in the context of large vocabulary word-based…

Learning control policies for multi-robot systems (MRS) remains a major challenge due to long-term coordination and the difficulty of obtaining realistic training data. In this work, we address both limitations within an imitation learning…

We consider the problem of sequential evaluation, in which an evaluator observes candidates in a sequence and assigns scores to these candidates in an online, irrevocable fashion. Motivated by the psychology literature that has studied…

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…