Towards Fine-Grained Information: Identifying the Type and Location of Translation Errors
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；National University of Singapore（新加坡国立大学）；University of Science Technology of China（中国科学技术大学）；University of Macau（澳门大学）
Keqin Bao, Yu Wan, Dayiheng Liu, Baosong Yang, Wenqiang Lei, Xiangnan He, Derek F. Wong, Jun Xie
Fine-grained information on translation errors is helpful for the translation evaluation community. Existing approaches can not synchronously consider error position and type, failing to integrate the error information of both. In this paper, we propose Fine-Grained Translation Error Detection (FG-TED) task, aiming at identifying both the position and the type of translation errors on given source-hypothesis sentence pairs. Besides, we build an FG-TED model to predict the \textbf{addition} and \textbf{omission} errors -- two typical translation accuracy errors. First, we use a word-level classification paradigm to form our model and use the shortcut learning reduction to relieve the influence of monolingual features. Besides, we construct synthetic datasets for model training, and relieve the disagreement of data labeling in authoritative datasets, making the experimental benchmark concordant. Experiments show that our model can identify both error type and position concurrently, and gives state-of-the-art results on the restored dataset. Our model also delivers more reliable predictions on low-resource and transfer scenarios than existing baselines. The related datasets and the source code will be released in the future.
Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings
Instituto Superior Técnico, Universidade de Lisboa (ELLIS Unit Lisbon)（里斯本大学理工学院（ELLIS单位里斯本））；Instituto de Telecomunicações（电信研究所）；Carnegie Mellon University（卡内基梅隆大学）；TransPerfect Core contributor（TransPerfect核心贡献者）
Fine-grained Gender Control in Machine Translation with Large Language Models
LG AI Research（LG AI研究院）；Seoul National University（首尔大学）；IPAI, Seoul National University（首尔大学IPAI）；Institute of Engineering Research, Seoul National University（首尔大学工程研究所）
xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection
Instituto de Telecomunicações（电信研究所）；CentraleSupélec（巴黎中央理工-高等电力学院）；Université Paris-Saclay（巴黎萨克雷大学）；Instituto Superior Técnico（高等理工学院）；University of Lisbon（里斯本大学）；Unbabel（Unbabel公司）；INESC-ID（葡萄牙系统与计算机工程研究所）
Identifying Products in Online Cybercrime Marketplaces: A Dataset for Fine-grained Domain Adaptation
UT Austin（德克萨斯大学奥斯汀分校）；University of Michigan（密歇根大学）；Carnegie Mellon University（卡内基梅隆大学）；UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）；NYU（纽约大学）；UC San Diego（加州大学圣地亚哥分校）
Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages
Sharif University of Technology（谢里夫理工学院）；Vellore Institute of Technology（韦洛雷理工学院）；IIT Kharagpur（印度理工学院达卡分校）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Unlocking Fine-Grained Translation Quality Estimation in LRMs through Mutually Boosting Implicit and Explicit Reasoning
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；Huawei Translation Services Center, Beijing, China（北京华为翻译服务中心）
Detecting and Understanding Generalization Barriers for Neural Machine Translation
Harbin Institute of Technology（哈尔滨工业大学）；Tencent AI Lab（腾讯人工智能实验室）
泛化到不可见的实例是我们对所有数据驱动模型的永恒追求。然而，对于像机器翻译这样的实际任务，传统的方法在平均意义上衡量泛化能力提供了很好的理解细粒度的泛化能力。作为一种补救措施，本文试图识别和理解泛化障碍词在一个看不见的输入句子，\textit{cause}细粒度泛化的退化。我们提出了一个原则性的概括障碍词的定义和一个修改后的版本，这是易于计算。在此基础上，提出了三种简单的基于反事实生成的搜索感知风险估计的障碍检测方法。然后，我们进行了广泛的分析，这些检测到的泛化障碍词的Zh $\Leftrightarrow$ En NIST基准从不同的角度。还讨论了检测到的障碍词的潜在用途。
Identifying Intensity of the Structure and Content in Tweets and the Discriminative Power of Attributes in Context with Referential Translation Machines
AI Enablement（AI赋能部门）；Huawei Türkiye R&D Center（华为土耳其研发中心）
Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
Digital Twin Institute, Eastern Institute of Technology, Ningbo, China（数字孪生研究所，东部技术研究所，宁波，中国）；Saarland University（萨尔兰州大学）；Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation
AWS AI Labs（AWS人工智能实验室）
随着通用机器翻译（MT）质量的提高，对探索细粒度质量方面的有针对性的基准测试的需求也在增加。特别是，翻译中的性别准确性可能会对输出流畅性，翻译准确性和道德产生影响。在本文中，我们介绍了MT-GenEval，一个用于评估从英语翻译成八种广泛使用的语言的性别准确性的基准。MT-GenEval补充了现有的基准，以八种语言对提供现实的、性别平衡的、反事实的数据，其中个人的性别在输入部分中是明确的，包括需要跨性别协议的多句部分。我们的数据和代码在CC BY SA 3.0许可证下公开提供。
Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment
School of Informatics, Xiamen University, China（厦门大学信息学院）；Huawei Translation Services Center, Beijing, China（华为翻译服务中心）；NLP 2 CT Lab, Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系NLP 2 CT实验室）
Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization
Alibaba Digital Media and Entertainment Group（阿里巴巴数字媒体与娱乐集团）；School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）；Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University（北京交通大学交通数据挖掘与具身智能重点实验室）
