{"total":100,"rows":[{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"area":null},{"id":"2106.01093","title":"LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations","created":"2021-06-02","cited_by_count":119,"area":null},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2102.10249","title":"Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction","created":"2021-02-20","cited_by_count":68,"area":null},{"id":"2302.01524","title":"Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing","created":"2023-02-03","cited_by_count":67,"area":null},{"id":"2103.11318","title":"Language-Agnostic Representation Learning of Source Code from Structure and Context","created":"2021-03-21","cited_by_count":63,"area":null},{"id":"2103.04350","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","created":"2021-03-07","cited_by_count":51,"area":null},{"id":"2304.06248","title":"LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model","created":"2023-04-13","cited_by_count":43,"area":null},{"id":"2108.12202","title":"A Partition Filter Network for Joint Entity and Relation Extraction","created":"2021-08-27","cited_by_count":42,"area":null},{"id":"2104.09635","title":"Refining Targeted Syntactic Evaluation of Language Models","created":"2021-04-19","cited_by_count":41,"area":null},{"id":"2203.00633","title":"Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale","created":"2022-03-01","cited_by_count":41,"area":null},{"id":"2211.01288","title":"Characterizing Intrinsic Compositionality in Transformers with Tree Projections","created":"2022-11-02","cited_by_count":41,"area":null},{"id":"2107.06516","title":"Learning Algebraic Recombination for Compositional Generalization","created":"2021-07-14","cited_by_count":31,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2104.05622","title":"Where and What? Examining Interpretable Disentangled Representations","created":"2021-04-07","cited_by_count":27,"area":null},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","cited_by_count":26,"area":null},{"id":"2103.12975","title":"VLGrammar: Grounded Grammar Induction of Vision and Language","created":"2021-03-24","cited_by_count":22,"area":null},{"id":"2104.05316","title":"Better Feature Integration for Named Entity Recognition","created":"2021-04-12","cited_by_count":22,"area":null},{"id":"2104.13727","title":"PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols","created":"2021-04-28","cited_by_count":22,"area":null},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22,"area":null},{"id":"2107.00967","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","created":"2021-07-02","cited_by_count":19,"area":null},{"id":"2109.12036","title":"Transformers Generalize Linearly","created":"2021-09-24","cited_by_count":19,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2310.19089","title":"Pushdown Layers: Encoding Recursive Structure in Transformer Language Models","created":"2023-10-29","cited_by_count":19,"area":null},{"id":"2104.04369","title":"Video-aided Unsupervised Grammar Induction","created":"2021-04-09","cited_by_count":17,"area":null},{"id":"2110.01209","title":"Learning Structural Representations for Recipe Generation and Food Retrieval","created":"2021-10-04","cited_by_count":17,"area":null},{"id":"2109.01982","title":"Learning Hierarchical Structures with Differentiable Nondeterministic Stacks","created":"2021-09-05","cited_by_count":16,"area":null},{"id":"2103.10972","title":"Learning Task Decomposition with Ordered Memory Policy Network","created":"2021-03-19","cited_by_count":15,"area":null},{"id":"2106.06038","title":"Modeling Hierarchical Structures with Continuous Recursive Neural Networks","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2203.00281","title":"Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation","created":"2022-03-01","cited_by_count":15,"area":null},{"id":"2306.04948","title":"ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis","created":"2023-06-08","cited_by_count":15,"area":null},{"id":"2103.16929","title":"Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey","created":"2021-03-31","cited_by_count":12,"area":null},{"id":"2311.04453","title":"Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2104.08685","title":"Linguistic Dependencies and Statistical Dependence","created":"2021-04-18","cited_by_count":10,"area":null},{"id":"2109.06431","title":"Exploring the Long Short-Term Dependencies to Infer Shot Influence in Badminton Matches","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2112.07874","title":"Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling","created":"2021-12-15","cited_by_count":10,"area":null},{"id":"2403.08293","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","created":"2024-03-13","cited_by_count":10,"area":null},{"id":"2101.02258","title":"Can RNNs learn Recursive Nested Subject-Verb Agreements?","created":"2021-01-06","cited_by_count":9,"area":null},{"id":"2104.07848","title":"Comparison of Grammatical Error Correction Using Back-Translation Models","created":"2021-04-16","cited_by_count":9,"area":null},{"id":"2201.02715","title":"Low-Rank Constraints for Fast Inference in Structured Models","created":"2022-01-08","cited_by_count":8,"area":null},{"id":"2208.08690","title":"A Survey on Open Information Extraction from Rule-based Model to Large Language Model","created":"2022-08-18","cited_by_count":8,"area":null},{"id":"2212.09140","title":"Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars","created":"2022-12-18","cited_by_count":7,"area":null},{"id":"2306.00645","title":"Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parsers","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2109.05112","title":"Improved Latent Tree Induction with Distant Supervision via Span Constraints","created":"2021-09-10","cited_by_count":6,"area":null},{"id":"2305.19999","title":"Beam Tree Recursive Cells","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2310.01717","title":"Ensemble Distillation for Unsupervised Constituency Parsing","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2106.01580","title":"The Limitations of Limited Context for Constituency Parsing","created":"2021-06-03","cited_by_count":5,"area":null},{"id":"2109.01238","title":"An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction","created":"2021-09-02","cited_by_count":5,"area":null},{"id":"2206.11184","title":"Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles","created":"2022-06-22","cited_by_count":5,"area":null},{"id":"2309.16319","title":"Augmenting Transformers with Recursively Composed Multi-grained Representations","created":"2023-09-28","cited_by_count":5,"area":null},{"id":"2405.02350","title":"What makes Models Compositional? A Theoretical View: With Supplement","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2104.13933","title":"Learning Syntax from Naturally-Occurring Bracketings","created":"2021-04-28","cited_by_count":4,"area":null},{"id":"2105.10193","title":"Rule Augmented Unsupervised Constituency Parsing","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2303.02860","title":"A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification","created":"2023-03-06","cited_by_count":4,"area":null},{"id":"2307.10779","title":"Efficient Beam Tree Recursion","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2402.12691","title":"Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2402.14393","title":"Graph Parsing Networks","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2110.02283","title":"Co-training an Unsupervised Constituency Parser with Weak Supervision","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2205.05943","title":"Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs","created":"2022-05-12","cited_by_count":3,"area":null},{"id":"2205.12590","title":"RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2210.12309","title":"Learning a Grammar Inducer from Massive Uncurated Instructional Videos","created":"2022-10-22","cited_by_count":3,"area":null},{"id":"2310.14997","title":"Simple Hardware-Efficient PCFGs with Independent Left and Right Productions","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2409.13738","title":"NLP4PBM: A Systematic Review on Process Extraction using Natural Language Processing with Rule-based, Machine and Deep Learning Methods","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2411.16993","title":"Tree Transformers are an Ineffective Model of Syntactic Constituency","created":"2024-11-25","cited_by_count":3,"area":null},{"id":"2411.18885","title":"Sneaking Syntax into Transformer Language Models with Tree Regularization","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2210.01338","title":"Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning","created":"2022-10-04","cited_by_count":2,"area":null},{"id":"2212.10564","title":"Re-evaluating the Need for Multimodal Signals in Unsupervised Grammar Induction","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2303.08809","title":"Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2309.04919","title":"The Emergence of Chunking Structures with Hierarchical RNN","created":"2023-09-10","cited_by_count":2,"area":null},{"id":"2310.16240","title":"Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2507.04793","title":"A Survey of Pun Generation: Datasets, Evaluations and Methodologies","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2106.07047","title":"Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models","created":"2021-06-13","cited_by_count":1,"area":null},{"id":"2111.14034","title":"ORCHARD: A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2201.04227","title":"A Feature Extraction based Model for Hate Speech Identification","created":"2022-01-11","cited_by_count":1,"area":null},{"id":"2203.10256","title":"Dependency-based Mixture Language Models","created":"2022-03-19","cited_by_count":1,"area":null},{"id":"2211.00479","title":"Revisiting the Practical Effectiveness of Constituency Parse Extraction from Pre-trained Language Models","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2301.06862","title":"Algorithms for Acyclic Weighted Finite-State Automata with Failure Arcs","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2407.16181","title":"Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2506.23146","title":"Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2511.03547","title":"Bearing Syntactic Fruit with Stack-Augmented Neural Networks","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2103.06198","title":"Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling","created":"2021-03-10","cited_by_count":0,"area":null},{"id":"2104.07454","title":"Memory Capacity of Recurrent Neural Networks with Matrix Representation","created":"2021-04-11","cited_by_count":0,"area":null},{"id":"2110.15931","title":"Unsupervised Full Constituency Parsing with Neighboring Distribution Divergence","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2111.14031","title":"FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding","created":"2021-11-28","cited_by_count":0,"area":null},{"id":"2204.08115","title":"HFT-ONLSTM: Hierarchical and Fine-Tuning Multi-label Text Classification","created":"2022-04-18","cited_by_count":0,"area":null},{"id":"2206.04806","title":"Syntactic Inductive Biases for Deep Learning Methods","created":"2022-06-08","cited_by_count":0,"area":null},{"id":"2206.04980","title":"Unsupervised and Few-shot Parsing from Pretrained Language Models","created":"2022-06-10","cited_by_count":0,"area":null},{"id":"2210.03985","title":"Bird-Eye Transformers for Text Generation Models","created":"2022-10-08","cited_by_count":0,"area":null},{"id":"2302.06451","title":"Ordered Memory Baselines","created":"2023-02-08","cited_by_count":0,"area":null},{"id":"2305.11034","title":"Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2305.16043","title":"Ordered and Binary Speaker Embedding","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2312.10097","title":"Arithmetics-Based Decomposition of Numeral Words -- Arithmetic Conditions give the Unpacking Strategy","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2403.00143","title":"Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2410.04074","title":"On Eliciting Syntax from Language Models via Hashing","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2411.05806","title":"SkipSNN: Efficiently Classifying Spike Trains with Event-attention","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2508.07969","title":"Understanding Syntactic Generalization in Structure-inducing Language Models","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.20734","title":"Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2511.01950","title":"EchoLSTM: A Self-Reflective Recurrent Network for Stabilizing Long-Range Memory","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2512.23145","title":"Reservoir Computing inspired Matrix Multiplication-free Language Model","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2607.08063","title":"Holographic Neural PCFG for Unsupervised Parsing","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":null}