{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"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":"1606.03622","title":"Data Recombination for Neural Semantic Parsing","created":"2016-06-11","cited_by_count":111},{"id":"2006.10369","title":"Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation","created":"2020-06-18","cited_by_count":105},{"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":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","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":"2112.07610","title":"Improving Compositional Generalization with Latent Structure and Data Augmentation","created":"2021-12-14","cited_by_count":46},{"id":"1808.07561","title":"Training Deeper Neural Machine Translation Models with Transparent Attention","created":"2018-08-22","cited_by_count":38},{"id":"2010.03737","title":"Shallow-to-Deep Training for Neural Machine Translation","created":"2020-10-08","cited_by_count":36},{"id":"1805.06130","title":"Towards Robust Neural Machine Translation","created":"2018-05-16","cited_by_count":35},{"id":"1911.00317","title":"On the Linguistic Representational Power of Neural Machine Translation Models","created":"2019-11-01","cited_by_count":34},{"id":"2105.14802","title":"On Compositional Generalization of Neural Machine Translation","created":"2021-05-31","cited_by_count":34},{"id":"1606.02006","title":"Incorporating Discrete Translation Lexicons into Neural Machine Translation","created":"2016-06-07","cited_by_count":33},{"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":"2109.02575","title":"Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization","created":"2021-09-06","cited_by_count":27},{"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":"1905.08527","title":"CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks","created":"2019-05-21","cited_by_count":22},{"id":"2109.15256","title":"Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks","created":"2021-09-30","cited_by_count":19},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17},{"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":"1906.01234","title":"Transcoding compositionally: using attention to find more generalizable solutions","created":"2019-06-04","cited_by_count":14},{"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":"2110.09419","title":"Compositional Attention: Disentangling Search and Retrieval","created":"2021-10-18","cited_by_count":12},{"id":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12},{"id":"1805.09657","title":"Learning compositionally through attentive guidance","created":"2018-05-20","cited_by_count":11},{"id":"2306.02840","title":"Learning to Substitute Spans towards Improving Compositional Generalization","created":"2023-06-05","cited_by_count":8},{"id":"2104.09810","title":"Addressing the Vulnerability of NMT in Input Perturbations","created":"2021-04-20","cited_by_count":6},{"id":"1908.06259","title":"Hard but Robust, Easy but Sensitive: How Encoder and Decoder Perform in Neural Machine Translation","created":"2019-08-17","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":"2305.12169","title":"Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization","created":"2023-05-20","cited_by_count":3},{"id":"2210.06709","title":"Categorizing Semantic Representations for Neural Machine Translation","created":"2022-10-13","cited_by_count":2}],"next_cursor":null}