Related papers: Learning and Analyzing Generation Order for Undire…

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck,…

The encoder-decoder model is widely used in natural language generation tasks. However, the model sometimes suffers from repeated redundant generation, misses important phrases, and includes irrelevant entities. Toward solving these…

Autoregressive sequence models achieve state-of-the-art performance in domains like machine translation. However, due to the autoregressive factorization nature, these models suffer from heavy latency during inference. Recently,…

We build a multi-source machine translation model and train it to maximize the probability of a target English string given French and German sources. Using the neural encoder-decoder framework, we explore several combination methods and…

We propose $\textit{iterative inversion}$ -- an algorithm for learning an inverse function without input-output pairs, but only with samples from the desired output distribution and access to the forward function. The key challenge is a…

Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically on the generation order. Prior work either hard-codes an ordering (e.g., blockwise…

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive…

Conditional graph generation tasks involve training a model to generate a graph given a set of input conditions. Many previous studies employ autoregressive models to incrementally generate graph components such as nodes and edges. However,…

Prior work on generating explanations in a planning and decision-making context has focused on providing the rationale behind an AI agent's decision making. While these methods provide the right explanations from the explainer's…

Pre-trained models (PTMs) have lead to great improvements in natural language generation (NLG). However, it is still unclear how much commonsense knowledge they possess. With the goal of evaluating commonsense knowledge of NLG models,…

Test-time thinking (that is, generating explicit intermediate reasoning chains) is known to boost performance in large language models and has recently shown strong gains for large vision language models (LVLMs). However, despite these…

Brains construct not only "first-order" representations of the environment but also "higher-order" representations about those representations -- including higher-order uncertainty estimates that guide learning and adaptive behavior.…

Many sequence-to-sequence generation tasks, including machine translation and text-to-speech, can be posed as estimating the density of the output y given the input x: p(y|x). Given this interpretation, it is natural to evaluate…

Back-translation is widely known for its effectiveness in neural machine translation when there is little to no parallel data. In this approach, a source-to-target model is coupled with a target-to-source model trained in parallel. The…

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…

Recent years has witnessed dramatic progress of neural machine translation (NMT), however, the method of manually guiding the translation procedure remains to be better explored. Previous works proposed to handle such problem through…

Two popular types of machine translation (MT) are phrase-based and neural machine translation systems. Both of these types of systems are composed of multiple complex models or layers. Each of these models and layers learns different…

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to…

Knowledge Grounded Conversation Models (KGCM) are usually based on a selection/retrieval module and a generation module, trained separately or simultaneously, with or without having access to a gold knowledge option. With the introduction…

In recent years, masked diffusion models (MDMs) have emerged as a promising alternative approach for generative modeling over discrete domains. Compared to autoregressive models (ARMs), MDMs trade off complexity at training time with…