Related papers: Translating Pro-Drop Languages with Reconstruction…
In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge. The dependency parse tree of a source…
In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in…
The naive approach to annotation projection is not effective to project discourse annotations from one language to another because implicit discourse relations are often changed to explicit ones and vice-versa in the translation. In this…
We present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct languages and use…
Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proportion of units,…
Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content. One main challenge in learning a style transfer system is a lack of parallel data where the source…
We propose a neural machine translation architecture that models the surrounding text in addition to the source sentence. These models lead to better performance, both in terms of general translation quality and pronoun prediction, when…
Automated crash reporting systems generate large volumes of duplicate reports, overwhelming issue-tracking systems and increasing developer workload. Traditional stack trace-based deduplication methods, relying on string similarity,…
Neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy. It is…
Medical dialogue generation relies on natural language generation techniques to enable online medical consultations. Recently, the widespread adoption of large-scale models in the field of natural language processing has facilitated rapid…
With multilingual machine translation (MMT) models continuing to grow in size and number of supported languages, it is natural to reuse and upgrade existing models to save computation as data becomes available in more languages. However,…
The last decade has witnessed enormous improvements in science and technology, stimulating the growing demand for economic and cultural exchanges in various countries. Building a neural machine translation (NMT) system has become an urgent…
Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing. Recent work shows that the attention mechanism inside Transformer may not be…
Fully supervised neural approaches have achieved significant progress in the task of Chinese word segmentation (CWS). Nevertheless, the performance of supervised models tends to drop dramatically when they are applied to out-of-domain data.…
Recent literature has demonstrated the potential of multilingual Neural Machine Translation (mNMT) models. However, the most efficient models are not well suited to specialized industries. In these cases, internal data is scarce and…
Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…
Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue…
An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Recently, iterative back-translation…
Large language models (LLMs) have achieved significant success across various domains. However, training these LLMs typically involves substantial memory and computational costs during both forward and backward propagation. While…
Back-translation is an effective strategy to improve the performance of Neural Machine Translation~(NMT) by generating pseudo-parallel data. However, several recent works have found that better translation quality of the pseudo-parallel…