{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"1601.01280","title":"Language to Logical Form with Neural Attention","created":"2016-01-06","cited_by_count":158},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"1909.01380","title":"The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives","created":"2019-09-03","cited_by_count":139},{"id":"1906.05381","title":"Compositional generalization through meta sequence-to-sequence learning","created":"2019-06-12","cited_by_count":99},{"id":"2007.08970","title":"Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures","created":"2020-07-17","cited_by_count":95},{"id":"2009.06040","title":"Span-based Semantic Parsing for Compositional Generalization","created":"2020-09-13","cited_by_count":77},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"2011.09039","title":"Sequence-Level Mixed Sample Data Augmentation","created":"2020-11-18","cited_by_count":71},{"id":"2006.11834","title":"AdvAug: Robust Adversarial Augmentation for Neural Machine Translation","created":"2020-06-21","cited_by_count":67},{"id":"2010.03706","title":"Learning to Recombine and Resample Data for Compositional Generalization","created":"2020-10-08","cited_by_count":65},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"2108.05885","title":"The paradox of the compositionality of natural language: a neural machine translation case study","created":"2021-08-12","cited_by_count":59},{"id":"1904.09708","title":"Compositional generalization in a deep seq2seq model by separating syntax and semantics","created":"2019-04-22","cited_by_count":56},{"id":"2104.07478","title":"Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations","created":"2021-04-15","cited_by_count":55},{"id":"2006.10627","title":"Compositional Generalization by Learning Analytical Expressions","created":"2020-06-18","cited_by_count":53},{"id":"1910.02612","title":"Compositional Generalization for Primitive Substitutions","created":"2019-10-07","cited_by_count":48},{"id":"1702.03964","title":"The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations","created":"2017-02-13","cited_by_count":42},{"id":"2010.03737","title":"Shallow-to-Deep Training for Neural Machine Translation","created":"2020-10-08","cited_by_count":36},{"id":"2105.14802","title":"On Compositional Generalization of Neural Machine Translation","created":"2021-05-31","cited_by_count":34},{"id":"2010.11818","title":"Compositional Generalization via Semantic Tagging","created":"2020-10-22","cited_by_count":32},{"id":"2107.06516","title":"Learning Algebraic Recombination for Compositional Generalization","created":"2021-07-14","cited_by_count":31},{"id":"2110.04655","title":"Disentangled Sequence to Sequence Learning for Compositional Generalization","created":"2021-10-09","cited_by_count":30},{"id":"2106.03993","title":"Lexicon Learning for Few-Shot Neural Sequence Modeling","created":"2021-06-07","cited_by_count":28},{"id":"2010.07792","title":"Hierarchical Poset Decoding for Compositional Generalization in Language","created":"2020-10-15","cited_by_count":26},{"id":"2210.13050","title":"Structural generalization is hard for sequence-to-sequence models","created":"2022-10-24","cited_by_count":24},{"id":"1810.10181","title":"Exploiting Deep Representations for Neural Machine Translation","created":"2018-10-24","cited_by_count":23},{"id":"2109.15256","title":"Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks","created":"2021-09-30","cited_by_count":19},{"id":"2205.01538","title":"SUBS: Subtree Substitution for Compositional Semantic Parsing","created":"2022-05-03","cited_by_count":16},{"id":"2002.06714","title":"Multi-layer Representation Fusion for Neural Machine Translation","created":"2020-02-16","cited_by_count":15},{"id":"1911.01497","title":"On Compositionality in Neural Machine Translation","created":"2019-11-04","cited_by_count":14},{"id":"2107.01366","title":"Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN","created":"2021-07-03","cited_by_count":14},{"id":"2202.10745","title":"Improving Systematic Generalization Through Modularity and Augmentation","created":"2022-02-22","cited_by_count":13},{"id":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12},{"id":"1902.05770","title":"Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-Agreement","created":"2019-02-15","cited_by_count":11},{"id":"2104.09810","title":"Addressing the Vulnerability of NMT in Input Perturbations","created":"2021-04-20","cited_by_count":6},{"id":"1806.00722","title":"Dense Information Flow for Neural Machine Translation","created":"2018-06-03","cited_by_count":5},{"id":"2303.11750","title":"LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation","created":"2023-03-21","cited_by_count":4},{"id":"2002.08899","title":"Compositional Neural Machine Translation by Removing the Lexicon from Syntax","created":"2020-02-06","cited_by_count":3},{"id":"2210.04878","title":"Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing","created":"2022-10-10","cited_by_count":3},{"id":"2212.05982","title":"Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning","created":"2022-12-12","cited_by_count":3}],"next_cursor":null}