{"list":"other","total":80,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"1709.03815","title":"OpenNMT: Open-source Toolkit for Neural Machine Translation","created":"2017-09-12","cited_by_count":251},{"id":"1907.04907","title":"Topic Modeling in Embedding Spaces","created":"2019-07-08","cited_by_count":224},{"id":"1603.06393","title":"Incorporating Copying Mechanism in Sequence-to-Sequence Learning","created":"2016-03-21","cited_by_count":218},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"2010.12725","title":"Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?","created":"2020-10-24","cited_by_count":147},{"id":"2108.12284","title":"The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers","created":"2021-08-26","cited_by_count":117},{"id":"1606.03622","title":"Data Recombination for Neural Semantic Parsing","created":"2016-06-11","cited_by_count":111},{"id":"1602.07776","title":"Recurrent Neural Network Grammars","created":"2016-02-25","cited_by_count":109},{"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":"1802.03691","title":"Tree-to-tree Neural Networks for Program Translation","created":"2018-02-11","cited_by_count":93},{"id":"1704.07535","title":"Abstract Syntax Networks for Code Generation and Semantic Parsing","created":"2017-04-25","cited_by_count":92},{"id":"1704.00784","title":"Online and Linear-Time Attention by Enforcing Monotonic Alignments","created":"2017-04-03","cited_by_count":85},{"id":"2008.06662","title":"Compositional Generalization via Neural-Symbolic Stack Machines","created":"2020-08-15","cited_by_count":80},{"id":"1706.00359","title":"Discovering Discrete Latent Topics with Neural Variational Inference","created":"2017-06-01","cited_by_count":79},{"id":"2009.06040","title":"Span-based Semantic Parsing for Compositional Generalization","created":"2020-09-13","cited_by_count":77},{"id":"1906.10225","title":"Compound Probabilistic Context-Free Grammars for Grammar Induction","created":"2019-06-24","cited_by_count":76},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"1603.06744","title":"Latent Predictor Networks for Code Generation","created":"2016-03-22","cited_by_count":73},{"id":"1812.01194","title":"A Retrieve-and-Edit Framework for Predicting Structured Outputs","created":"2018-12-04","cited_by_count":73},{"id":"2001.03632","title":"Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks","created":"2020-01-10","cited_by_count":72},{"id":"2011.09039","title":"Sequence-Level Mixed Sample Data Augmentation","created":"2020-11-18","cited_by_count":71},{"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":"1808.10122","title":"Learning Neural Templates for Text Generation","created":"2018-08-30","cited_by_count":61},{"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":"2010.11939","title":"Limitations of Autoregressive Models and Their Alternatives","created":"2020-10-22","cited_by_count":55},{"id":"2006.10627","title":"Compositional Generalization by Learning Analytical Expressions","created":"2020-06-18","cited_by_count":53},{"id":"1906.02890","title":"Visually Grounded Neural Syntax Acquisition","created":"2019-06-07","cited_by_count":48},{"id":"1910.02612","title":"Compositional Generalization for Primitive Substitutions","created":"2019-10-07","cited_by_count":48},{"id":"1603.08148","title":"Pointing the Unknown Words","created":"2016-03-26","cited_by_count":43},{"id":"2005.10213","title":"Applying the Transformer to Character-level Transduction","created":"2020-05-20","cited_by_count":43},{"id":"2010.05647","title":"Improving Compositional Generalization in Semantic Parsing","created":"2020-10-12","cited_by_count":42},{"id":"1907.05545","title":"The Dynamic Embedded Topic Model","created":"2019-07-12","cited_by_count":41},{"id":"2002.00876","title":"Torch-Struct: Deep Structured Prediction Library","created":"2020-02-03","cited_by_count":40},{"id":"1807.03756","title":"Latent Alignment and Variational Attention","created":"2018-07-10","cited_by_count":36},{"id":"2009.12404","title":"Visually Grounded Compound PCFGs","created":"2020-09-25","cited_by_count":34},{"id":"2104.05196","title":"StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer","created":"2021-04-12","cited_by_count":34},{"id":"1609.04186","title":"Neural Machine Translation with Supervised Attention","created":"2016-09-14","cited_by_count":31},{"id":"2005.01096","title":"Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence","created":"2020-05-03","cited_by_count":25},{"id":"1907.10739","title":"Visual Interaction with Deep Learning Models through Collaborative Semantic Inference","created":"2019-07-24","cited_by_count":24},{"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":"2011.04640","title":"Scaling Hidden Markov Language Models","created":"2020-11-09","cited_by_count":22},{"id":"2103.12975","title":"VLGrammar: Grounded Grammar Induction of Vision and Language","created":"2021-03-24","cited_by_count":22},{"id":"2104.13727","title":"PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols","created":"2021-04-28","cited_by_count":22},{"id":"1609.09007","title":"Unsupervised Neural Hidden Markov Models","created":"2016-09-28","cited_by_count":19},{"id":"1704.04743","title":"Towards String-to-Tree Neural Machine Translation","created":"2017-04-16","cited_by_count":19},{"id":"2007.15135","title":"The Return of Lexical Dependencies: Neural Lexicalized PCFGs","created":"2020-07-29","cited_by_count":19},{"id":"2012.04276","title":"Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization","created":"2020-12-08","cited_by_count":19},{"id":"2105.15021","title":"Neural Bi-Lexicalized PCFG Induction","created":"2021-05-31","cited_by_count":18},{"id":"1511.06018","title":"Segmental Recurrent Neural Networks","created":"2015-11-18","cited_by_count":17},{"id":"2104.04369","title":"Video-aided Unsupervised Grammar Induction","created":"2021-04-09","cited_by_count":17},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17},{"id":"1601.01085","title":"Incorporating Structural Alignment Biases into an Attentional Neural Translation Model","created":"2016-01-06","cited_by_count":16},{"id":"1702.03525","title":"Learning to Parse and Translate Improves Neural Machine Translation","created":"2017-02-12","cited_by_count":16},{"id":"2005.04560","title":"Posterior Control of Blackbox Generation","created":"2020-05-10","cited_by_count":16},{"id":"1609.08194","title":"Online Segment to Segment Neural Transduction","created":"2016-09-26","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":"2006.04771","title":"Copy that! Editing Sequences by Copying Spans","created":"2020-06-08","cited_by_count":13},{"id":"1808.10024","title":"Hard Non-Monotonic Attention for Character-Level Transduction","created":"2018-08-29","cited_by_count":12},{"id":"1807.02301","title":"Sequential Copying Networks","created":"2018-07-06","cited_by_count":10},{"id":"2010.14720","title":"Second-Order Unsupervised Neural Dependency Parsing","created":"2020-10-28","cited_by_count":10},{"id":"1708.00801","title":"Dependency Grammar Induction with Neural Lexicalization and Big Training Data","created":"2017-08-02","cited_by_count":7},{"id":"2103.02298","title":"An Empirical Study of Compound PCFGs","created":"2021-03-03","cited_by_count":6},{"id":"1401.5693","title":"Sentence Compression as Tree Transduction","created":"2014-01-15","cited_by_count":5},{"id":"1809.01854","title":"Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing","created":"2018-09-06","cited_by_count":5},{"id":"1503.04881","title":"Long Short-Term Memory Over Tree Structures","created":"2015-03-16","cited_by_count":4},{"id":"2010.04704","title":"Recursive Top-Down Production for Sentence Generation with Latent Trees","created":"2020-10-09","cited_by_count":2}],"next_cursor":null}