Related papers: Multi-Reference Training with Pseudo-References fo…

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when…

There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter…

Applying Reinforcement learning (RL) following maximum likelihood estimation (MLE) pre-training is a versatile method for enhancing neural machine translation (NMT) performance. However, recent work has argued that the gains produced by RL…

Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification…

Neural Machine Translation (NMT) has drawn much attention due to its promising translation performance recently. However, several studies indicate that NMT often generates fluent but unfaithful translations. In this paper, we propose a…

Video captioning which automatically translates video clips into natural language sentences is a very important task in computer vision. By virtue of recent deep learning technologies, e.g., convolutional neural networks (CNNs) and…

We present a novel framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework,…

Despite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be straightforwardly incorporated…

As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other. However, the dominant methods for…

Captioning models are typically trained using the cross-entropy loss. However, their performance is evaluated on other metrics designed to better correlate with human assessments. Recently, it has been shown that reinforcement learning (RL)…

Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. Different from previous works that make use of mutually similar but redundant translation memories~(TMs), we propose a new…

This paper proposes a novel method to inject custom terminology into neural machine translation at run time. Previous works have mainly proposed modifications to the decoding algorithm in order to constrain the output to include…

An all-too-present bottleneck for text classification model development is the need to annotate training data and this need is multiplied for multilingual classifiers. Fortunately, contemporary machine translation models are both easily…

We consider the problem of making efficient use of heterogeneous training data in neural machine translation (NMT). Specifically, given a training dataset with a sentence-level feature such as noise, we seek an optimal curriculum, or order…

We study the problem of generating inferential texts of events for a variety of commonsense like \textit{if-else} relations. Existing approaches typically use limited evidence from training examples and learn for each relation individually.…

Neural Image Captioning (NIC) or neural caption generation has attracted a lot of attention over the last few years. Describing an image with a natural language has been an emerging challenge in both fields of computer vision and language…

In this paper, we address a fundamental gap between pre-training and fine-tuning of deep neural networks: while pre-training has shifted from unimodal to multimodal learning with enhanced visual understanding, fine-tuning predominantly…

A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT…

For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally…

Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly sampled from…