{"total":172,"rows":[{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864,"area":null},{"id":"2109.04404","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","created":"2021-09-09","cited_by_count":156,"area":null},{"id":"2109.06129","title":"Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color","created":"2021-09-13","cited_by_count":119,"area":null},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2104.08027","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","created":"2021-04-16","cited_by_count":88,"area":null},{"id":"2310.13132","title":"Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries","created":"2023-10-19","cited_by_count":82,"area":null},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79,"area":null},{"id":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48,"area":null},{"id":"2104.14700","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","created":"2021-04-29","cited_by_count":47,"area":null},{"id":"2212.01488","title":"Event knowledge in large language models: the gap between the impossible and the unlikely","created":"2022-12-02","cited_by_count":45,"area":null},{"id":"2203.07893","title":"Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information","created":"2022-03-15","cited_by_count":34,"area":null},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34,"area":null},{"id":"2305.12696","title":"Learning Interpretable Style Embeddings via Prompting LLMs","created":"2023-05-22","cited_by_count":30,"area":null},{"id":"2212.11737","title":"The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations","created":"2022-12-22","cited_by_count":29,"area":null},{"id":"2212.09994","title":"Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2305.10204","title":"Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2101.09525","title":"Dictionary-based Debiasing of Pre-trained Word Embeddings","created":"2021-01-23","cited_by_count":24,"area":null},{"id":"2408.03617","title":"Is Child-Directed Speech Effective Training Data for Language Models?","created":"2024-08-07","cited_by_count":24,"area":null},{"id":"2104.05274","title":"Learning to Remove: Towards Isotropic Pre-trained BERT Embedding","created":"2021-04-12","cited_by_count":23,"area":null},{"id":"2212.13492","title":"MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing","created":"2022-12-27","cited_by_count":22,"area":null},{"id":"2211.04079","title":"COPEN: Probing Conceptual Knowledge in Pre-trained Language Models","created":"2022-11-08","cited_by_count":21,"area":null},{"id":"2203.02679","title":"Just Rank: Rethinking Evaluation with Word and Sentence Similarities","created":"2022-03-05","cited_by_count":20,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2106.04302","title":"Obtaining Better Static Word Embeddings Using Contextual Embedding Models","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2109.07971","title":"Do Language Models Know the Way to Rome?","created":"2021-09-16","cited_by_count":18,"area":null},{"id":"2101.06887","title":"Can a Fruit Fly Learn Word Embeddings?","created":"2021-01-18","cited_by_count":17,"area":null},{"id":"2212.04273","title":"Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2310.13257","title":"Visual Grounding Helps Learn Word Meanings in Low-Data Regimes","created":"2023-10-20","cited_by_count":17,"area":null},{"id":"2202.00035","title":"Learning Fair Representations via Rate-Distortion Maximization","created":"2022-01-31","cited_by_count":15,"area":null},{"id":"2305.16765","title":"Backpack Language Models","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2103.11024","title":"Conceptual similarity and communicative need shape colexification: an experimental study","created":"2021-03-19","cited_by_count":14,"area":null},{"id":"2103.16704","title":"Probabilistic Analogical Mapping with Semantic Relation Networks","created":"2021-03-30","cited_by_count":14,"area":null},{"id":"2203.07511","title":"Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations","created":"2022-03-14","cited_by_count":14,"area":null},{"id":"2101.11310","title":"Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling","created":"2021-01-27","cited_by_count":13,"area":null},{"id":"2306.01457","title":"Driving Context into Text-to-Text Privatization","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2202.03753","title":"Semantic features of object concepts generated with GPT-3","created":"2022-02-08","cited_by_count":12,"area":null},{"id":"2106.14361","title":"Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings","created":"2021-06-28","cited_by_count":11,"area":null},{"id":"2112.02650","title":"VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning","created":"2021-12-05","cited_by_count":11,"area":null},{"id":"2112.05194","title":"Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2105.13266","title":"RAW-C: Relatedness of Ambiguous Words--in Context (A New Lexical Resource for English)","created":"2021-05-27","cited_by_count":10,"area":null},{"id":"2203.07504","title":"VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models","created":"2022-03-14","cited_by_count":10,"area":null},{"id":"2205.06072","title":"SimRelUz: Similarity and Relatedness scores as a Semantic Evaluation dataset for Uzbek language","created":"2022-05-12","cited_by_count":10,"area":null},{"id":"2109.07403","title":"BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification","created":"2021-09-15","cited_by_count":9,"area":null},{"id":"2203.07860","title":"Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost","created":"2022-03-15","cited_by_count":9,"area":null},{"id":"2310.05597","title":"Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance","created":"2023-10-09","cited_by_count":9,"area":"lr"},{"id":"2104.07500","title":"Learning Zero-Shot Multifaceted Visually Grounded Word Embeddings via Multi-Task Training","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2210.02956","title":"Are word boundaries useful for unsupervised language learning?","created":"2022-10-06","cited_by_count":8,"area":null},{"id":"2101.08700","title":"Multi-sense embeddings through a word sense disambiguation process","created":"2021-01-21","cited_by_count":7,"area":null},{"id":"2104.07456","title":"Effect of Post-processing on Contextualized Word Representations","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2108.00480","title":"Realised Volatility Forecasting: Machine Learning via Financial Word Embedding","created":"2021-08-01","cited_by_count":7,"area":null},{"id":"2506.16678","title":"Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations","created":"2025-06-20","cited_by_count":7,"area":null},{"id":"2105.14668","title":"On the Interplay Between Fine-tuning and Composition in Transformers","created":"2021-05-31","cited_by_count":6,"area":null},{"id":"2109.14039","title":"Marked Attribute Bias in Natural Language Inference","created":"2021-09-28","cited_by_count":6,"area":null},{"id":"2205.09867","title":"Gender Bias in Meta-Embeddings","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2401.06112","title":"Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings","created":"2024-01-11","cited_by_count":6,"area":null},{"id":"2402.14616","title":"The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations","created":"2024-02-22","cited_by_count":6,"area":null},{"id":"2103.06598","title":"DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces","created":"2021-03-11","cited_by_count":5,"area":null},{"id":"2111.06230","title":"Training Cross-Lingual embeddings for Setswana and Sepedi","created":"2021-11-11","cited_by_count":5,"area":null},{"id":"2206.01691","title":"Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals","created":"2022-06-03","cited_by_count":5,"area":null},{"id":"2206.08823","title":"Language with Vision: a Study on Grounded Word and Sentence Embeddings","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2406.10984","title":"Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2406.14678","title":"Evaluating Contextualized Representations of (Spanish) Ambiguous Words: A New Lexical Resource and Empirical Analysis","created":"2024-06-20","cited_by_count":5,"area":null},{"id":"2603.29552","title":"Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2102.03596","title":"Does He Wink or Does He Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models","created":"2021-02-06","cited_by_count":4,"area":null},{"id":"2107.10614","title":"Evaluation of contextual embeddings on less-resourced languages","created":"2021-07-22","cited_by_count":4,"area":null},{"id":"2109.04876","title":"Integrating Approaches to Word Representation","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2109.11763","title":"Lacking the embedding of a word? Look it up into a traditional dictionary","created":"2021-09-24","cited_by_count":4,"area":null},{"id":"2203.04366","title":"It's AI Match: A Two-Step Approach for Schema Matching Using Embeddings","created":"2022-03-08","cited_by_count":4,"area":null},{"id":"2305.07303","title":"Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2305.10438","title":"IMAGINATOR: Pre-Trained Image+Text Joint Embeddings using Word-Level Grounding of Images","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2309.10551","title":"A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2408.01961","title":"Representation Bias of Adolescents in AI: A Bilingual, Bicultural Study","created":"2024-08-04","cited_by_count":4,"area":null},{"id":"2502.05892","title":"A Distributional Perspective on Word Learning in Neural Language Models","created":"2025-02-09","cited_by_count":4,"area":null},{"id":"2502.08441","title":"Better Embeddings with Coupled Adam","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2106.01904","title":"Representing Syntax and Composition with Geometric Transformations","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2108.12941","title":"RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations","created":"2021-08-30","cited_by_count":3,"area":null},{"id":"2109.11308","title":"Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial Attack","created":"2021-09-23","cited_by_count":3,"area":null},{"id":"2110.02577","title":"Efficient Multi-Modal Embeddings from Structured Data","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2207.03086","title":"Word Embedding for Social Sciences: An Interdisciplinary Survey","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2306.16326","title":"Representation Learning via Variational Bayesian Networks","created":"2023-06-28","cited_by_count":3,"area":null},{"id":"2307.09332","title":"Company2Vec -- German Company Embeddings based on Corporate Websites","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2311.18567","title":"The Causal Influence of Grammatical Gender on Distributional Semantics","created":"2023-11-30","cited_by_count":3,"area":null},{"id":"2402.13130","title":"Are ELECTRA's Sentence Embeddings Beyond Repair? The Case of Semantic Textual Similarity","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2404.01860","title":"Self-StrAE at SemEval-2024 Task 1: Making Self-Structuring AutoEncoders Learn More With Less","created":"2024-04-02","cited_by_count":3,"area":null},{"id":"2407.17771","title":"Banyan: Improved Representation Learning with Explicit Structure","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2412.17427","title":"Measuring Contextual Informativeness in Child-Directed Text","created":"2024-12-23","cited_by_count":3,"area":null},{"id":"2504.06036","title":"Multi-Sense Embeddings for Language Models and Knowledge Distillation","created":"2025-04-08","cited_by_count":3,"area":"distill"},{"id":"2506.03994","title":"Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2507.18103","title":"A New Pair of GloVes","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2106.02954","title":"Denoising Word Embeddings by Averaging in a Shared Space","created":"2021-06-05","cited_by_count":2,"area":null},{"id":"2109.13767","title":"Identifying and Mitigating Gender Bias in Hyperbolic Word Embeddings","created":"2021-09-28","cited_by_count":2,"area":null},{"id":"2110.01804","title":"A Survey On Neural Word Embeddings","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2202.10292","title":"Seeing the advantage: visually grounding word embeddings to better capture human semantic knowledge","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2203.14996","title":"Comparing in context: Improving cosine similarity measures with a metric tensor","created":"2022-03-28","cited_by_count":2,"area":null},{"id":"2209.15197","title":"Evaluation of taxonomic and neural embedding methods for calculating semantic similarity","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2211.08447","title":"SexWEs: Domain-Aware Word Embeddings via Cross-lingual Semantic Specialisation for Chinese Sexism Detection in Social Media","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2304.06337","title":"Computational modeling of semantic change","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2305.05588","title":"StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure","created":"2023-05-09","cited_by_count":2,"area":null}],"next_cursor":"100"}