# Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond Source: [Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:20:37.043Z Authors: Xin Li, Lidong Bing, Wenxuan Zhang, Zheng Li, Wai Lam Published: 2020-10-23T13:47:01.000Z ## Abstract Cross-lingual adaptation with multilingual pre-trained language models (mPTLMs) mainly consists of two lines of works: zero-shot approach and translation-based approach, which have been studied extensively on the sequence-level tasks. We further verify the efficacy of these cross-lingual adaptation approaches by evaluating their performances on more fine-grained sequence tagging tasks. After re-examining their strengths and drawbacks, we propose a novel framework to consolidate the zero-shot approach and the translation-based approach for better adaptation performance. Instead of simply augmenting the source data with the machine-translated data, we tailor-make a warm-up mechanism to quickly update the mPTLMs with the gradients estimated on a few translated data. Then, the adaptation approach is applied to the refined parameters and the cross-lingual transfer is performed in a warm-start way. The experimental results on nine target languages demonstrate that our method is beneficial to the cross-lingual adaptation of various sequence tagging tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Cross-lingual Aspect-Based Sentiment Analysis on SemEval 2016](): Cross-lingual Aspect-Based Sentiment Analysis; SemEval 2016; FR Score: 49.34. ## Original sources and implementation [Original paper]() [PDF]()