{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1803.02324","title":"Annotation Artifacts in Natural Language Inference Data","created":"2018-03-06","cited_by_count":671},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"1806.00692","title":"Stress Test Evaluation for Natural Language Inference","created":"2018-06-02","cited_by_count":213},{"id":"1903.06059","title":"Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement","created":"2019-03-14","cited_by_count":211},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"2107.05407","title":"PonderNet: Learning to Ponder","created":"2021-07-12","cited_by_count":168},{"id":"1805.02266","title":"Breaking NLI Systems with Sentences that Require Simple Lexical Inferences","created":"2018-05-06","cited_by_count":134},{"id":"1804.06028","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","created":"2018-04-17","cited_by_count":129},{"id":"1709.04057","title":"Parallelizing Linear Recurrent Neural Nets Over Sequence Length","created":"2017-09-12","cited_by_count":127},{"id":"1702.03814","title":"Bilateral Multi-Perspective Matching for Natural Language Sentences","created":"2017-02-13","cited_by_count":121},{"id":"1810.09536","title":"Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks","created":"2018-10-22","cited_by_count":101},{"id":"1702.00887","title":"Structured Attention Networks","created":"2017-02-03","cited_by_count":95},{"id":"2009.06040","title":"Span-based Semantic Parsing for Compositional Generalization","created":"2020-09-13","cited_by_count":77},{"id":"2101.07965","title":"Directed Acyclic Graph Neural Networks","created":"2021-01-20","cited_by_count":70},{"id":"1909.06639","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","created":"2019-09-14","cited_by_count":68},{"id":"1802.04223","title":"SparseMAP: Differentiable Sparse Structured Inference","created":"2018-02-12","cited_by_count":62},{"id":"2110.07732","title":"The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization","created":"2021-10-14","cited_by_count":62},{"id":"1904.02142","title":"Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders","created":"2019-04-03","cited_by_count":60},{"id":"2006.10627","title":"Compositional Generalization by Learning Analytical Expressions","created":"2020-06-18","cited_by_count":53},{"id":"1707.02786","title":"Learning to Compose Task-Specific Tree Structures","created":"2017-07-10","cited_by_count":48},{"id":"1803.03585","title":"The Importance of Being Recurrent for Modeling Hierarchical Structure","created":"2018-03-09","cited_by_count":42},{"id":"1911.04070","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","created":"2019-11-11","cited_by_count":38},{"id":"1603.06021","title":"A Fast Unified Model for Parsing and Sentence Understanding","created":"2016-03-19","cited_by_count":34},{"id":"2012.00857","title":"StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling","created":"2020-12-01","cited_by_count":33},{"id":"2107.06516","title":"Learning Algebraic Recombination for Compositional Generalization","created":"2021-07-14","cited_by_count":31},{"id":"1611.09100","title":"Learning to Compose Words into Sentences with Reinforcement Learning","created":"2016-11-28","cited_by_count":30},{"id":"2002.08046","title":"Tree-structured Attention with Hierarchical Accumulation","created":"2020-02-19","cited_by_count":30},{"id":"1902.09393","title":"Cooperative Learning of Disjoint Syntax and Semantics","created":"2019-02-25","cited_by_count":27},{"id":"2010.10418","title":"ConjNLI: Natural Language Inference Over Conjunctive Sentences","created":"2020-10-20","cited_by_count":27},{"id":"2111.05297","title":"Sliced Recursive Transformer","created":"2021-11-09","cited_by_count":26},{"id":"1705.09189","title":"Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs","created":"2017-05-25","cited_by_count":24},{"id":"1705.09207","title":"Learning Structured Text Representations","created":"2017-05-25","cited_by_count":24},{"id":"2009.07408","title":"Retrofitting Structure-aware Transformer Language Model for End Tasks","created":"2020-09-16","cited_by_count":24},{"id":"1506.04834","title":"Tree-structured composition in neural networks without tree-structured architectures","created":"2015-06-16","cited_by_count":23},{"id":"1910.13466","title":"Ordered Memory","created":"2019-10-29","cited_by_count":20},{"id":"2107.00967","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","created":"2021-07-02","cited_by_count":19},{"id":"1808.09644","title":"On Tree-Based Neural Sentence Modeling","created":"2018-08-29","cited_by_count":16},{"id":"2007.00266","title":"Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering","created":"2020-07-01","cited_by_count":16},{"id":"2109.01982","title":"Learning Hierarchical Structures with Differentiable Nondeterministic Stacks","created":"2021-09-05","cited_by_count":16},{"id":"2010.04674","title":"Learning Context-Free Languages with Nondeterministic Stack RNNs","created":"2020-10-09","cited_by_count":15},{"id":"2106.06038","title":"Modeling Hierarchical Structures with Continuous Recursive Neural Networks","created":"2021-06-10","cited_by_count":15},{"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},{"id":"2110.06865","title":"Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments","created":"2021-10-13","cited_by_count":14},{"id":"1805.04658","title":"Backpropagating through Structured Argmax using a SPIGOT","created":"2018-05-12","cited_by_count":11},{"id":"2202.08806","title":"Grammar-Based Grounded Lexicon Learning","created":"2022-02-17","cited_by_count":11},{"id":"1503.02510","title":"Compositional Distributional Semantics with Long Short Term Memory","created":"2015-03-09","cited_by_count":10},{"id":"1509.00552","title":"DAG-Recurrent Neural Networks For Scene Labeling","created":"2015-09-02","cited_by_count":10},{"id":"1607.04492","title":"Neural Tree Indexers for Text Understanding","created":"2016-07-15","cited_by_count":9},{"id":"1806.00840","title":"Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing","created":"2018-06-03","cited_by_count":7},{"id":"1906.09992","title":"Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming","created":"2019-06-24","cited_by_count":7},{"id":"2305.19999","title":"Beam Tree Recursive Cells","created":"2023-05-31","cited_by_count":6},{"id":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","cited_by_count":2}],"next_cursor":null}