{"total":18,"rows":[{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2109.04593","title":"A Large-Scale Study of Machine Translation in the Turkic Languages","created":"2021-09-09","cited_by_count":21,"area":null},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"area":null},{"id":"2405.06346","title":"Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology","created":"2024-05-10","cited_by_count":17,"area":null},{"id":"2302.09685","title":"Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages","created":"2023-02-19","cited_by_count":9,"area":null},{"id":"2109.06262","title":"Evaluating Multiway Multilingual NMT in the Turkic Languages","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2312.04764","title":"First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languages","created":"2023-12-08","cited_by_count":7,"area":null},{"id":"2209.13515","title":"Assessing Digital Language Support on a Global Scale","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2110.07444","title":"Designing Language Technologies for Social Good: The Road not Taken","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2209.07351","title":"Rethinking Round-Trip Translation for Machine Translation Evaluation","created":"2022-09-15","cited_by_count":4,"area":null},{"id":"2405.01590","title":"101 Billion Arabic Words Dataset","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2106.06292","title":"A Discussion on Building Practical NLP Leaderboards: The Case of Machine Translation","created":"2021-06-11","cited_by_count":1,"area":null},{"id":"2403.19365","title":"EthioMT: Parallel Corpus for Low-resource Ethiopian Languages","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2412.00218","title":"NushuRescue: Revitalization of the Endangered Nushu Language with AI","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2211.16172","title":"Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2509.05729","title":"QCSE: A Pretrained Quantum Context-Sensitive Word Embedding for Natural Language Processing","created":"2025-09-06","cited_by_count":0,"area":null}],"next_cursor":null}