This paper introduces our Diversity Advanced Actor-Critic reinforcement learning (A2C) framework (DAAC) to improve the generalization and accuracy of Natural Language Processing (NLP).
Generalising to unseen domains is under-explored and remains a challenge in neural machine translation.
Previous works mostly focus on either multilingual or multi-domain aspects of neural machine translation (NMT).
In this work, we propose a multi-armed bandit-based online optimization framework for the sequential selection of pre-training hyperparameters to optimize language model performance.
Neural Machine Translation (NMT) models are strong enough to convey semantic and syntactic information from the source language to the target language.
Complex natural language applications such as speech translation or pivot translation traditionally rely on cascaded models.
Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs.
Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement.
Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e. g., document-level translation, or having meta-information.
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i. e., source-pivot and pivot-target, leading to a significant improvement in source-target translation.
Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT).
Pre-training a model with word weights improves fine-tuning up to 1. 24% BLEU absolute and 1. 64% TER, respectively.
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data.
We empirically investigate learning from partial feedback in neural machine translation (NMT), when partial feedback is collected by asking users to highlight a correct chunk of a translation.
We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform.
In this paper, we introduce a hybrid search for attention-based neural machine translation (NMT).
In this paper, we discuss different methods which use meta information and richer context that may accompany source language input to improve machine translation quality.
We experiment graph-based Semi-Supervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data.
This new loss function yields a total of 1. 87 point improvements in terms of BLEU score in the translation quality.
In this paper, we propose an effective way for biasing the attention mechanism of a sequence-to-sequence neural machine translation (NMT) model towards the well-studied statistical word alignment models.
Achieving accurate translation, especially in multiple domain documents with statistical machine translation systems, requires more and more bilingual texts and this need becomes more critical when training such systems for language pairs with scarce training data.