Language difference is one of the factors that hinder the acquisition of second language skills. In this article, we introduce a novel solution that leverages the strength of deep neural networks to measure the semantic dissimilarity between languages based on their word distributions in the embedding space of the multilingual pre-trained language model (e.g.,BERT). Then, we empirically examine the effectiveness of the proposed semantic language distance (SLD) in explaining the consistent variation in English ability of countries, which is proxied by their performance in the Internet-Based Test of English as Foreign Language (TOEFL iBT). The experimental results show that the language distance demonstrates negative influence on a country's average English ability. Interestingly, the effect is more significant on speaking and writing subskills, which pertain to the productive aspects of language learning. Besides, we provide specific recommendations for future research directions.
Colombian Waitresses y Jueces canadienses: Gender and Country Biases in Occupation Recommendations from LLMs
Erasmus Mundus Master in Language and Communication Technologies（埃拉斯谟 Mundus 语言与沟通技术硕士项目）；HiTZ Center - Ixa, University of the Basque Country (UPV/EHU)（巴斯克国家大学（UPV/EHU）HiTZ中心 - Ixa）；Cohere（Cohere公司）；Saarland University（萨尔兰州大学）
Recent work has shown that Pre-trained Language Models (PLMs) store the relational knowledge learned from data and utilize it for performing downstream tasks. However, commonsense knowledge across different regions may vary. For instance, the color of bridal dress is white in American weddings whereas it is red in Chinese weddings. In this paper, we introduce a benchmark dataset, Geo-Diverse Commonsense Multilingual Language Models Analysis (GeoMLAMA), for probing the diversity of the relational knowledge in multilingual PLMs. GeoMLAMA contains 3,125 prompts in English, Chinese, Hindi, Persian…
Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学信息与语言处理中心（CIS））
Recently, it has been found that monolingual English language models can be used as knowledge bases. Instead of structural knowledge base queries, masked sentences such as "Paris is the capital of [MASK]" are used as probes. We translate the established benchmarks TREx and GoogleRE into 53 languages. Working with mBERT, we investigate three questions. (i) Can mBERT be used as a multilingual knowledge base? Most prior work only considers English. Extending research to multiple languages is important for diversity and accessibility. (ii) Is mBERT's performance as knowledge base language-independ…
Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
Institute for Logic, Language and Computation, University of Amsterdam（逻辑、语言与计算研究所，阿姆斯特丹大学）；Center for Language and Cognition, University of Groningen（语言与认知中心，格罗宁根大学）
CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understanding
Instituto Politécnico Nacional（墨西哥国立理工学院）；Haverford College（哈弗福德学院）；Wollo University（沃尔洛大学）；Pennsylvania State University（宾夕法尼亚州立大学）；University of Hamburg（汉堡大学）
Extrapolating Large Language Models to Non-English by Aligning Languages
Nanjing University（南京大学）；Peking University（北京大学）；Shanghai AI Lab（上海人工智能实验室）；The University of Hong Kong（香港大学）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing
Department of Linguistics & Institute for Advanced Computational Science, Stony Brook University（语言学系与高级计算科学研究所，石溪大学）；Department of Linguistics, University of Saskatchewan（语言学系，萨斯喀彻温大学）
Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs
Mila - Quebec AI Institute McGill University, Canada（魁北克AI研究所麦吉尔大学，加拿大）；LT3, IDLab, Universiteit Gent（LT3，IDLab，根特大学）；Bloomberg（彭博）；University of Trento（特伦托大学）
Multilingual LLMs Struggle to Link Orthography and Semantics in Bilingual Word Processing
Department of Electrical Engineering, Indian Institute of Technology Delhi（印度理工学院德里电气工程系）；Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi（印度理工学院德里人工智能学院）
Large Language Model-Driven Dynamic Assessment of Grammatical Accuracy in English Language Learner Writing
National Institute of Standards（国家标准 institute）；Department of Physics, Colorado State University（物理系，科罗拉多州立大学）；Electrical Engineering Department, University of Colorado（电气工程系，科罗拉多大学）
Wiktionary as a Crowdsourced Lexicon for English Dialects
Centre for Sustainability Research, University of Otago（奥塔哥大学可持续性研究中心）；Te Pūnaha Matatini Centre for Research Excellence in Complex Systems（Te Pūnaha Matatini复杂系统卓越研究中心）
Past research has identified discriminatory automatic speech recognition (ASR) performance as a function of the racial group and nationality of the speaker. In this paper, we expand the discussion beyond bias as a function of the individual national origin of the speaker to look for bias as a function of the geopolitical orientation of their nation of origin. We audit some of the most popular English language ASR services using a large and global data set of speech from The Speech Accent Archive, which includes over 2,700 speakers of English born in 171 different countries. We show that, even …
University of Warwick（华威大学）；University of St Andrews（圣安德鲁斯大学）
In contrast to much previous work that has focused on location classification of tweets restricted to a specific country, here we undertake the task in a broader context by classifying global tweets at the country level, which is so far unexplored in a real-time scenario. We analyse the extent to which a tweet's country of origin can be determined by making use of eight tweet-inherent features for classification. Furthermore, we use two datasets, collected a year apart from each other, to analyse the extent to which a model trained from historical tweets can still be leveraged for classificati…
National University of Ireland Galway（爱尔兰国立大学戈尔韦分校）；ULTRA Arts and Science College（ULTRA艺术与科学学院）；Cardiff University（卡迪夫大学）；Indian Institute of Information Technology and Management-Kerala（印度喀拉拉邦信息技术与管理学院）
This paper describes the development of a multilingual, manually annotated dataset for three under-resourced Dravidian languages generated from social media comments. The dataset was annotated for sentiment analysis and offensive language identification for a total of more than 60,000 YouTube comments. The dataset consists of around 44,000 comments in Tamil-English, around 7,000 comments in Kannada-English, and around 20,000 comments in Malayalam-English. The data was manually annotated by volunteer annotators and has a high inter-annotator agreement in Krippendorff's alpha. The dataset contai…
Recent efforts to consolidate guidelines and treebanks in the Universal Dependencies project raise the expectation that joint training and dataset comparison is increasingly possible for high-resource languages such as English, which have multiple corpora. Focusing on the two largest UD English treebanks, we examine progress in data consolidation and answer several questions: Are UD English treebanks becoming more internally consistent? Are they becoming more like each other and to what extent? Is joint training a good idea, and if so, since which UD version? Our results indicate that while co…
