{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1405.4053","title":"Distributed Representations of Sentences and Documents","created":"2014-05-16","cited_by_count":678},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"1605.09096","title":"Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change","created":"2016-05-30","cited_by_count":221},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"1905.07213","title":"Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language","created":"2019-05-17","cited_by_count":109},{"id":"2007.11464","title":"SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection","created":"2020-07-22","cited_by_count":108},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107},{"id":"1806.03537","title":"Diachronic word embeddings and semantic shifts: a survey","created":"2018-06-09","cited_by_count":92},{"id":"2004.14118","title":"Analysing Lexical Semantic Change with Contextualised Word Representations","created":"2020-04-29","cited_by_count":92},{"id":"1811.06278","title":"Survey of Computational Approaches to Lexical Semantic Change","created":"2018-11-15","cited_by_count":62},{"id":"2005.02590","title":"Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders","created":"2020-05-06","cited_by_count":61},{"id":"2104.08116","title":"Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media","created":"2021-04-16","cited_by_count":51},{"id":"2110.06366","title":"Time Masking for Temporal Language Models","created":"2021-10-12","cited_by_count":46},{"id":"2009.10053","title":"Latin BERT: A Contextual Language Model for Classical Philology","created":"2020-09-21","cited_by_count":43},{"id":"2104.14694","title":"Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses","created":"2021-04-29","cited_by_count":39},{"id":"1912.01072","title":"Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift","created":"2019-12-02","cited_by_count":37},{"id":"1804.06517","title":"Diachronic Usage Relatedness (DURel): A Framework for the Annotation of Lexical Semantic Change","created":"2018-04-18","cited_by_count":35},{"id":"2103.07259","title":"Explaining and Improving BERT Performance on Lexical Semantic Change Detection","created":"2021-03-12","cited_by_count":34},{"id":"1804.09692","title":"Factors Influencing the Surprising Instability of Word Embeddings","created":"2018-04-25","cited_by_count":33},{"id":"1906.01688","title":"Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change","created":"2019-06-04","cited_by_count":33},{"id":"2005.00050","title":"UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection","created":"2020-04-30","cited_by_count":32},{"id":"2104.08540","title":"DWUG: A large Resource of Diachronic Word Usage Graphs in Four Languages","created":"2021-04-17","cited_by_count":26},{"id":"1809.03169","title":"Short-Term Meaning Shift: A Distributional Exploration","created":"2018-09-10","cited_by_count":23},{"id":"2001.06629","title":"Capturing Evolution in Word Usage: Just Add More Clusters?","created":"2020-01-18","cited_by_count":22},{"id":"2112.14330","title":"Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora","created":"2021-12-28","cited_by_count":21},{"id":"2202.02093","title":"Temporal Attention for Language Models","created":"2022-02-04","cited_by_count":21},{"id":"2010.12684","title":"Dynamic Contextualized Word Embeddings","created":"2020-10-23","cited_by_count":20},{"id":"2104.08465","title":"Frequency-based Distortions in Contextualized Word Embeddings","created":"2021-04-17","cited_by_count":20},{"id":"2209.00154","title":"Contextualized language models for semantic change detection: lessons learned","created":"2022-08-31","cited_by_count":20},{"id":"2209.07216","title":"TempoWiC: An Evaluation Benchmark for Detecting Meaning Shift in Social Media","created":"2022-09-15","cited_by_count":19},{"id":"2203.12926","title":"Multitasking Framework for Unsupervised Simple Definition Generation","created":"2022-03-24","cited_by_count":18},{"id":"2101.07668","title":"Challenges for Computational Lexical Semantic Change","created":"2021-01-19","cited_by_count":16},{"id":"2203.04651","title":"Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang","created":"2022-03-09","cited_by_count":15},{"id":"1801.09872","title":"A State-of-the-Art of Semantic Change Computation","created":"2018-01-30","cited_by_count":14},{"id":"2104.03776","title":"Statistically significant detection of semantic shifts using contextual word embeddings","created":"2021-04-08","cited_by_count":14},{"id":"2106.08294","title":"Three-part diachronic semantic change dataset for Russian","created":"2021-06-15","cited_by_count":11},{"id":"2202.03612","title":"HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis","created":"2022-02-08","cited_by_count":11},{"id":"2205.06691","title":"LSCDiscovery: A shared task on semantic change discovery and detection in Spanish","created":"2022-05-13","cited_by_count":11},{"id":"2109.10397","title":"Grammatical Profiling for Semantic Change Detection","created":"2021-09-21","cited_by_count":10},{"id":"2005.06602","title":"CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations","created":"2020-04-30","cited_by_count":9},{"id":"2010.03481","title":"ELMo and BERT in semantic change detection for Russian","created":"2020-10-07","cited_by_count":8},{"id":"2101.10649","title":"Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks","created":"2021-01-26","cited_by_count":8},{"id":"2201.05123","title":"NorDiaChange: Diachronic Semantic Change Dataset for Norwegian","created":"2022-01-13","cited_by_count":7},{"id":"2204.05717","title":"Do Not Fire the Linguist: Grammatical Profiles Help Language Models Detect Semantic Change","created":"2022-04-12","cited_by_count":7},{"id":"2209.13750","title":"RuDSI: graph-based word sense induction dataset for Russian","created":"2022-09-28","cited_by_count":7},{"id":"2010.00857","title":"SST-BERT at SemEval-2020 Task 1: Semantic Shift Tracing by Clustering in BERT-based Embedding Spaces","created":"2020-10-02","cited_by_count":6},{"id":"2011.07247","title":"CL-IMS @ DIACR-Ita: Volente o Nolente: BERT does not outperform SGNS on Semantic Change Detection","created":"2020-11-14","cited_by_count":4},{"id":"2206.11865","title":"BOS at LSCDiscovery: Lexical Substitution for Interpretable Lexical Semantic Change Detection","created":"2022-06-07","cited_by_count":2},{"id":"2210.08207","title":"Temporal Word Meaning Disambiguation using TimeLMs","created":"2022-10-15","cited_by_count":1}],"next_cursor":null}