The paper describes a transformer-based system designed for SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis. The purpose of the task was to predict the intimacy of tweets in a range from 1 (not intimate at all) to 5 (very intimate). The official training set for the competition consisted of tweets in six languages (English, Spanish, Italian, Portuguese, French, and Chinese). The test set included the given six languages as well as external data with four languages not presented in the training set (Hindi, Arabic, Dutch, and Korean). We presented a solution based on an ensemble of XLM-T, a multilingual RoBERTa model adapted to the Twitter domain. To improve the performance of unseen languages, each tweet was supplemented by its English translation. We explored the effectiveness of translated data for the languages seen in fine-tuning compared to unseen languages and estimated strategies for using translated data in transformer-based models. Our solution ranked 4th on the leaderboard while achieving an overall Pearson's r of 0.599 over the test set. The proposed system improves up to 0.088 Pearson's r over a score averaged across all 45 submissions.

翻译：本文描述了一个基于Transformer的系统，用于SemEval-2023任务9：多语言推文亲密度分析。该任务旨在预测推文的亲密度，评分范围为1（完全不亲密）到5（非常亲密）。官方竞赛训练集包含六种语言的推文（英语、西班牙语、意大利语、葡萄牙语、法语和中文）。测试集不仅涵盖上述六种语言，还包含训练集中未出现的四种语言（印地语、阿拉伯语、荷兰语和韩语）的外部数据。我们提出了一种基于XLM-T集成学习的解决方案，XLM-T是一个针对推特领域优化的多语言RoBERTa模型。为提升未见语言的性能，每条推文均补充了其英文翻译。我们研究了翻译数据在微调过程中对可见语言与不可见语言的有效性差异，并评估了在基于Transformer的模型中使用翻译数据的策略。我们的解决方案在排行榜上位列第四，在测试集上实现了总体皮尔逊相关系数0.599。与全部45个提交方案的平均得分相比，所提系统的皮尔逊相关系数提升了0.088。