Related papers: Tailoring Domain Adaptation for Machine Translatio…
Keeping the performance of language technologies optimal as time passes is of great practical interest. We study temporal effects on model performance on downstream language tasks, establishing a nuanced terminology for such discussion and…
We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained to perform decoding in an iterative manner, a Levenshtein…
Synthesizing QA pairs with a question generator (QG) on the target domain has become a popular approach for domain adaptation of question answering (QA) models. Since synthetic questions are often noisy in practice, existing work adapts…
Measuring the similarity between two different sentential arguments is an important task in argument mining. However, one of the challenges in this field is that the dataset must be annotated using expertise in a variety of topics, making…
In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the learned knowledge from a separate, labeled source domain to…
Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline. However, the underlying supervised models require a large number of labeled pairs, and these pairs are hard…
The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…
Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.…
Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…
We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain. Samples are grouped by their similarities to the domain of interest and each group is fed to the training algorithm with a…
Most previous unsupervised domain adaptation (UDA) methods for question answering(QA) require access to source domain data while fine-tuning the model for the target domain. Source domain data may, however, contain sensitive information and…
We investigate the problem of cross-dataset adaptation for visual question answering (Visual QA). Our goal is to train a Visual QA model on a source dataset but apply it to another target one. Analogous to domain adaptation for visual…
Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain transfer often operate on data on which the modes of the…
Automatic Post-Editing (APE) systems often struggle with over-correction, where unnecessary modifications are made to a translation, diverging from the principle of minimal editing. In this paper, we propose a novel technique to mitigate…
This work connects language model adaptation with concepts of machine learning theory. We consider a training setup with a large out-of-domain set and a small in-domain set. We derive how the benefit of training a model on either set…
Translation Quality Estimation is critical to reducing post-editing efforts in machine translation and to cross-lingual corpus cleaning. As a research problem, quality estimation (QE) aims to directly estimate the quality of translation in…
In many practical applications, it is often difficult and expensive to obtain enough large-scale labeled data to train deep neural networks to their full capability. Therefore, transferring the learned knowledge from a separate, labeled…
When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from…
The performance of automatic speech recognition models often degenerates on domains not covered by the training data. Domain adaptation can address this issue, assuming the availability of the target domain data in the target language.…
A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a…