{"list":"other","total":59,"rows":[{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1608.08868","title":"Demographic Dialectal Variation in Social Media: A Case Study of African-American English","created":"2016-08-31","cited_by_count":196},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192},{"id":"2103.06678","title":"The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models","created":"2021-03-11","cited_by_count":119},{"id":"2008.06460","title":"Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model","created":"2020-08-14","cited_by_count":87},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53},{"id":"2010.11334","title":"NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task","created":"2020-10-21","cited_by_count":47},{"id":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47},{"id":"2011.12631","title":"A Panoramic Survey of Natural Language Processing in the Arab World","created":"2020-11-25","cited_by_count":45},{"id":"2105.07316","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","created":"2021-05-15","cited_by_count":43},{"id":"1804.08186","title":"Automatic Language Identification in Texts: A Survey","created":"2018-04-22","cited_by_count":41},{"id":"2310.15135","title":"Quantifying the Dialect Gap and its Correlates Across Languages","created":"2023-10-23","cited_by_count":33},{"id":"2103.08466","title":"NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task","created":"2021-03-04","cited_by_count":32},{"id":"2010.12707","title":"Learning to Recognize Dialect Features","created":"2020-10-23","cited_by_count":29},{"id":"2310.16117","title":"NADI 2023: The Fourth Nuanced Arabic Dialect Identification Shared Task","created":"2023-10-24","cited_by_count":29},{"id":"2310.13747","title":"ALDi: Quantifying the Arabic Level of Dialectness of Text","created":"2023-10-20","cited_by_count":24},{"id":"2210.09582","title":"NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task","created":"2022-10-18","cited_by_count":23},{"id":"2004.14870","title":"Mind Your Inflections! Improving NLP for Non-Standard Englishes with Base-Inflection Encoding","created":"2020-04-30","cited_by_count":22},{"id":"2212.13492","title":"MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing","created":"2022-12-27","cited_by_count":22},{"id":"2304.12026","title":"SocialDial: A Benchmark for Socially-Aware Dialogue Systems","created":"2023-04-24","cited_by_count":22},{"id":"2106.06797","title":"Machine Translation into Low-resource Language Varieties","created":"2021-06-12","cited_by_count":19},{"id":"2109.06772","title":"Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noise","created":"2021-09-14","cited_by_count":19},{"id":"2304.10158","title":"Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages","created":"2023-04-20","cited_by_count":19},{"id":"2210.00193","title":"FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation","created":"2022-10-01","cited_by_count":18},{"id":"2305.18855","title":"STT4SG-350: A Speech Corpus for All Swiss German Dialect Regions","created":"2023-05-30","cited_by_count":18},{"id":"1609.02960","title":"A Large Scale Corpus of Gulf Arabic","created":"2016-09-09","cited_by_count":17},{"id":"2007.07860","title":"Dialect Diversity in Text Summarization on Twitter","created":"2020-07-15","cited_by_count":17},{"id":"2104.07155","title":"Disentangling Representations of Text by Masking Transformers","created":"2021-04-14","cited_by_count":15},{"id":"2305.16651","title":"TADA: Task-Agnostic Dialect Adapters for English","created":"2023-05-26","cited_by_count":15},{"id":"2110.06852","title":"Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects","created":"2021-10-13","cited_by_count":14},{"id":"2211.00922","title":"Dialect-robust Evaluation of Generated Text","created":"2022-11-02","cited_by_count":14},{"id":"2305.20080","title":"Findings of the VarDial Evaluation Campaign 2023","created":"2023-05-31","cited_by_count":14},{"id":"1904.05527","title":"Modeling Global Syntactic Variation in English Using Dialect Classification","created":"2019-04-11","cited_by_count":13},{"id":"2211.12000","title":"ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English","created":"2022-11-22","cited_by_count":13},{"id":"2305.11355","title":"MD3: The Multi-Dialect Dataset of Dialogues","created":"2023-05-19","cited_by_count":13},{"id":"2305.13406","title":"DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules","created":"2023-05-22","cited_by_count":13},{"id":"1906.01830","title":"ArSentD-LEV: A Multi-Topic Corpus for Target-based Sentiment Analysis in Arabic Levantine Tweets","created":"2019-05-25","cited_by_count":11},{"id":"1705.06463","title":"Universal Dependencies Parsing for Colloquial Singaporean English","created":"2017-05-18","cited_by_count":10},{"id":"1704.07398","title":"Predicting Native Language from Gaze","created":"2017-04-24","cited_by_count":9},{"id":"1710.11035","title":"Machine Translation of Low-Resource Spoken Dialects: Strategies for Normalizing Swiss German","created":"2017-10-30","cited_by_count":9},{"id":"2305.17267","title":"CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation","created":"2023-05-26","cited_by_count":9},{"id":"2310.19567","title":"CreoleVal: Multilingual Multitask Benchmarks for Creoles","created":"2023-10-30","cited_by_count":9},{"id":"2311.00915","title":"Task-Agnostic Low-Rank Adapters for Unseen English Dialects","created":"2023-11-02","cited_by_count":9},{"id":"1307.3091","title":"Artificial Intelligence MArkup Language: A Brief Tutorial","created":"2013-07-11","cited_by_count":7},{"id":"2301.08937","title":"Exploring Methods for Building Dialects-Mandarin Code-Mixing Corpora: A Case Study in Taiwanese Hokkien","created":"2023-01-21","cited_by_count":7},{"id":"1610.00031","title":"Discriminating Similar Languages: Evaluations and Explorations","created":"2016-09-30","cited_by_count":6},{"id":"2102.11000","title":"An open access NLP dataset for Arabic dialects : Data collection, labeling, and model construction","created":"2021-02-07","cited_by_count":5},{"id":"2103.09185","title":"A Multilingual African Embedding for FAQ Chatbots","created":"2021-03-16","cited_by_count":5},{"id":"2104.04989","title":"NorDial: A Preliminary Corpus of Written Norwegian Dialect Use","created":"2021-04-11","cited_by_count":5},{"id":"2305.16598","title":"NormMark: A Weakly Supervised Markov Model for Socio-cultural Norm Discovery","created":"2023-05-26","cited_by_count":5},{"id":"2306.14866","title":"Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language","created":"2023-06-26","cited_by_count":4},{"id":"1712.06273","title":"Low Resourced Machine Translation via Morpho-syntactic Modeling: The Case of Dialectal Arabic","created":"2017-12-18","cited_by_count":3},{"id":"2301.02521","title":"SAIDS: A Novel Approach for Sentiment Analysis Informed of Dialect and Sarcasm","created":"2023-01-06","cited_by_count":3},{"id":"2210.11899","title":"A Semi-supervised Approach for a Better Translation of Sentiment in Dialectical Arabic UGT","created":"2022-10-21","cited_by_count":2},{"id":"2210.12985","title":"Maknuune: A Large Open Palestinian Arabic Lexicon","created":"2022-10-24","cited_by_count":2},{"id":"1806.00522","title":"Improving Dialogue Act Classification for Spontaneous Arabic Speech and Instant Messages at Utterance Level","created":"2018-05-30","cited_by_count":1},{"id":"1808.08392","title":"MADARi: A Web Interface for Joint Arabic Morphological Annotation and Spelling Correction","created":"2018-08-25","cited_by_count":1},{"id":"2209.09757","title":"Language Varieties of Italy: Technology Challenges and Opportunities","created":"2022-09-20","cited_by_count":1}],"next_cursor":null}