{"total":51,"rows":[{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471,"area":null},{"id":"2102.11417","title":"Parallelizing Legendre Memory Unit Training","created":"2021-02-22","cited_by_count":23,"area":null},{"id":"2102.10864","title":"Subword Pooling Makes a Difference","created":"2021-02-22","cited_by_count":18,"area":null},{"id":"2109.03777","title":"Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP","created":"2021-09-08","cited_by_count":17,"area":null},{"id":"2112.06386","title":"Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification","created":"2021-12-13","cited_by_count":15,"area":null},{"id":"2106.04133","title":"Efficient Speech Emotion Recognition Using Multi-Scale CNN and Attention","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2105.00388","title":"Billion-scale Pre-trained E-commerce Product Knowledge Graph Model","created":"2021-05-02","cited_by_count":13,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2108.08041","title":"DeepCVA: Automated Commit-level Vulnerability Assessment with Deep Multi-task Learning","created":"2021-08-18","cited_by_count":11,"area":null},{"id":"2207.12759","title":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","created":"2022-07-26","cited_by_count":11,"area":null},{"id":"2506.01435","title":"Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2104.06901","title":"Enhancing Interpretable Clauses Semantically using Pretrained Word Representation","created":"2021-04-14","cited_by_count":10,"area":null},{"id":"2105.14403","title":"Re-evaluating Word Mover's Distance","created":"2021-05-30","cited_by_count":10,"area":null},{"id":"2210.07661","title":"CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling","created":"2022-10-14","cited_by_count":10,"area":null},{"id":"2101.04197","title":"Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa -- A Large Romanian Sentiment Data Set","created":"2021-01-11","cited_by_count":8,"area":null},{"id":"2104.04828","title":"FreSaDa: A French Satire Data Set for Cross-Domain Satire Detection","created":"2021-04-10","cited_by_count":8,"area":null},{"id":"2212.09410","title":"Less is More: Parameter-Free Text Classification with Gzip","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2112.14921","title":"Retrieving Black-box Optimal Images from External Databases","created":"2021-12-30","cited_by_count":6,"area":null},{"id":"2305.18824","title":"Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2107.00079","title":"Using AntiPatterns to avoid MLOps Mistakes","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2203.08417","title":"On the Use of Fine-grained Vulnerable Code Statements for Software Vulnerability Assessment Models","created":"2022-03-16","cited_by_count":5,"area":null},{"id":"2211.08451","title":"kogito: A Commonsense Knowledge Inference Toolkit","created":"2022-11-15","cited_by_count":4,"area":null},{"id":"2312.17253","title":"Deep Learning-based Sentiment Classification: A Comparative Survey","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2107.05151","title":"Document Embedding for Scientific Articles: Efficacy of Word Embeddings vs TFIDF","created":"2021-07-11","cited_by_count":3,"area":null},{"id":"2205.06618","title":"The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2212.05189","title":"Expanding Knowledge Graphs with Humans in the Loop","created":"2022-12-10","cited_by_count":3,"area":null},{"id":"2110.02047","title":"Hierarchical information matters: Text classification via tree based graph neural network","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2604.27398","title":"Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2103.05638","title":"Beyond Nystr\\\"omformer -- Approximation of self-attention by Spectral Shifting","created":"2021-03-09","cited_by_count":1,"area":null},{"id":"2107.11666","title":"Graph Convolutional Network with Generalized Factorized Bilinear Aggregation","created":"2021-07-24","cited_by_count":1,"area":null},{"id":"2203.10482","title":"DEIM: An effective deep encoding and interaction model for sentence matching","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2204.03954","title":"Are We Really Making Much Progress in Text Classification? A Comparative Review","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2205.01954","title":"Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem","created":"2022-05-04","cited_by_count":1,"area":null},{"id":"2205.03695","title":"AKI-BERT: a Pre-trained Clinical Language Model for Early Prediction of Acute Kidney Injury","created":"2022-05-07","cited_by_count":1,"area":null},{"id":"2306.16299","title":"Social World Knowledge: Modeling and Applications","created":"2023-06-28","cited_by_count":1,"area":null},{"id":"2308.01413","title":"LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning","created":"2023-07-30","cited_by_count":1,"area":null},{"id":"2411.08244","title":"NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs","created":"2024-11-12","cited_by_count":1,"area":null},{"id":"2503.15469","title":"A Dual-Directional Context-Aware Test-Time Learning for Text Classification","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2101.06880","title":"Abstractive Opinion Tagging","created":"2021-01-18","cited_by_count":0,"area":null},{"id":"2111.03514","title":"SocialVec: Social Entity Embeddings","created":"2021-11-05","cited_by_count":0,"area":null},{"id":"2203.00964","title":"PKGM: A Pre-trained Knowledge Graph Model for E-commerce Application","created":"2022-03-02","cited_by_count":0,"area":null},{"id":"2205.08740","title":"A reproducible experimental survey on biomedical sentence similarity: a string-based method sets the state of the art","created":"2022-05-18","cited_by_count":0,"area":null},{"id":"2305.05162","title":"Effective Medical Code Prediction via Label Internal Alignment","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2308.06235","title":"KETM:A Knowledge-Enhanced Text Matching method","created":"2023-08-11","cited_by_count":0,"area":null},{"id":"2404.18942","title":"GuideWalk: A Novel Graph-Based Word Embedding for Enhanced Text Classification","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2408.09158","title":"Linear Attention is Enough in Spatial-Temporal Forecasting","created":"2024-08-17","cited_by_count":0,"area":null},{"id":"2508.08942","title":"Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2511.22977","title":"Pooling Attention: Evaluating Pretrained Transformer Embeddings for Deception Classification","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2603.10148","title":"Social Knowledge for Cross-Domain User Preference Modeling","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2607.05416","title":"Text Distance from Nested and Hierarchical Repetitions: A Compression-Based Perspective","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.15246","title":"CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}