FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation

TL;DR

This paper introduces FGraDA, a dataset and benchmark for fine-grained domain adaptation in machine translation, focusing on sub-domains with limited resources and no in-domain training data, highlighting ongoing challenges.

Contribution

The paper presents a new dataset and benchmark for fine-grained domain adaptation in MT, emphasizing resource scarcity and heterogeneity in real-world scenarios.

Findings

Significant performance gaps remain in fine-grained domain adaptation.

Heterogeneous resources pose challenges for current MT models.

The dataset enables targeted evaluation of domain-specific translation issues.

Abstract

Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which is a core problem for domain adaptation in real-world scenarios. One representative of such challenging scenarios is to deploy a translation system for a conference with a specific topic, e.g., global warming or coronavirus, where there are usually extremely less resources due to the limited schedule. To motivate wider investigation in such a scenario, we present a real-world fine-grained domain adaptation task in machine translation (FGraDA). The FGraDA dataset consists of Chinese-English translation task for four sub-domains of information technology: autonomous vehicles, AI education, real-time networks, and smart phone. Each sub-domain is equipped with a development set and test set for evaluation purposes. To be closer to reality, FGraDA does not employ any in-domain bilingual training data but provides bilingual dictionaries and wiki knowledge base, which can be easier obtained within a short time. We benchmark the fine-grained domain adaptation task and present in-depth analyses showing that there are still challenging problems to further improve the performance with heterogeneous resources.