Related papers: Multilingual Domain Adaptation for NMT: Decoupling…

Fine-tuning a language model on a new domain is standard practice for domain adaptation. However, it can be infeasible when it comes to modern large-scale language models such as GPT-3, which can only be accessed through APIs, making it…

Recent advances in NLP are brought by a range of large-scale pretrained language models (PLMs). These PLMs have brought significant performance gains for a range of NLP tasks, circumventing the need to customize complex designs for specific…

Improving neural machine translation (NMT) systems with prompting has achieved significant progress in recent years. In this work, we focus on how to integrate multi-knowledge, multiple types of knowledge, into NMT models to enhance the…

Large Language Models (LLMs) have shown strong abilities in general language tasks, yet adapting them to specific domains remains a challenge. Current method like Domain Adaptive Pretraining (DAPT) requires costly full-parameter training…

Machine translation systems are vulnerable to domain mismatch, especially in a low-resource scenario. Out-of-domain translations are often of poor quality and prone to hallucinations, due to exposure bias and the decoder acting as a…

Log analysis represents a critical sub-domain within AI applications that facilitates automatic approaches to fault and error management of large-scaled software systems, saving labors of traditional manual methods. While existing solutions…

Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and…

Multimodal Machine Translation (MMT) enhances translation quality by incorporating visual context, helping to resolve textual ambiguities. While existing MMT methods perform well in bilingual settings, extending them to multilingual…

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…

We propose and compare methods for gradient-based domain adaptation of self-attentive neural machine translation models. We demonstrate that a large proportion of model parameters can be frozen during adaptation with minimal or no reduction…

Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription.…

Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate…

$k$NN-MT is a straightforward yet powerful approach for fast domain adaptation, which directly plugs pre-trained neural machine translation (NMT) models with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve…

In this work, we propose a flow-adapter architecture for unsupervised NMT. It leverages normalizing flows to explicitly model the distributions of sentence-level latent representations, which are subsequently used in conjunction with the…

Current Neural Machine Translation (NMT) employs a language-specific encoder to represent the source sentence and adopts a language-specific decoder to generate target translation. This language-dependent design leads to large-scale network…

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success…

Learning effective sentence representations is crucial for many Natural Language Processing (NLP) tasks, including semantic search, semantic textual similarity (STS), and clustering. While multiple transformer models have been developed for…

We consider the problem of adapting a network trained on three-channel color images to a hyperspectral domain with a large number of channels. To this end, we propose domain adaptor networks that map the input to be compatible with a…

Massively multilingual pre-trained language models (MMPLMs) are developed in recent years demonstrating superpowers and the pre-knowledge they acquire for downstream tasks. This work investigates whether MMPLMs can be applied to clinical…

Cross-lingual transfer from related high-resource languages is a well-established strategy to enhance low-resource language technologies. Prior work has shown that adapters show promise for, e.g., improving low-resource machine translation…