{"list":"other","total":62,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"1606.06357","title":"Complex Embeddings for Simple Link Prediction","created":"2016-06-20","cited_by_count":902},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"1911.06136","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","created":"2019-11-13","cited_by_count":356},{"id":"2010.00904","title":"Autoregressive Entity Retrieval","created":"2020-10-02","cited_by_count":334},{"id":"1909.03193","title":"KG-BERT: BERT for Knowledge Graph Completion","created":"2019-09-07","cited_by_count":324},{"id":"1909.07606","title":"K-BERT: Enabling Language Representation with Knowledge Graph","created":"2019-09-17","cited_by_count":304},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"1909.04164","title":"Knowledge Enhanced Contextual Word Representations","created":"2019-09-09","cited_by_count":296},{"id":"2010.00710","title":"Nearest Neighbor Machine Translation","created":"2020-10-01","cited_by_count":209},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"1904.10281","title":"Quaternion Knowledge Graph Embeddings","created":"2019-04-23","cited_by_count":175},{"id":"1709.04071","title":"Variational Reasoning for Question Answering with Knowledge Graph","created":"2017-09-12","cited_by_count":170},{"id":"1801.08284","title":"DKN: Deep Knowledge-Aware Network for News Recommendation","created":"2018-01-25","cited_by_count":137},{"id":"2010.11967","title":"Language Models are Open Knowledge Graphs","created":"2020-10-22","cited_by_count":95},{"id":"1611.01462","title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","created":"2016-11-04","cited_by_count":92},{"id":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85},{"id":"2102.02557","title":"Adaptive Semiparametric Language Models","created":"2021-02-04","cited_by_count":83},{"id":"1612.04426","title":"Improving Neural Language Models with a Continuous Cache","created":"2016-12-13","cited_by_count":82},{"id":"1901.08907","title":"Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation","created":"2019-01-23","cited_by_count":71},{"id":"1906.07241","title":"Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling","created":"2019-06-17","cited_by_count":71},{"id":"1609.04309","title":"Efficient softmax approximation for GPUs","created":"2016-09-14","cited_by_count":67},{"id":"1709.07432","title":"Dynamic Evaluation of Neural Sequence Models","created":"2017-09-21","cited_by_count":55},{"id":"2004.12744","title":"Augmenting Transformers with KNN-Based Composite Memory for Dialogue","created":"2020-04-27","cited_by_count":53},{"id":"2008.01766","title":"Word meaning in minds and machines","created":"2020-08-04","cited_by_count":51},{"id":"1902.09091","title":"Leveraging Knowledge Bases in LSTMs for Improving Machine Reading","created":"2019-02-25","cited_by_count":37},{"id":"1903.00058","title":"Non-Parametric Adaptation for Neural Machine Translation","created":"2019-02-28","cited_by_count":34},{"id":"2102.04643","title":"Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog","created":"2021-02-09","cited_by_count":33},{"id":"1912.10824","title":"Differentiable Reasoning on Large Knowledge Bases and Natural Language","created":"2019-12-17","cited_by_count":30},{"id":"2010.12688","title":"Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training","created":"2020-10-23","cited_by_count":24},{"id":"1904.08378","title":"Dynamic Evaluation of Transformer Language Models","created":"2019-04-17","cited_by_count":23},{"id":"2103.10518","title":"Pretraining the Noisy Channel Model for Task-Oriented Dialogue","created":"2021-03-18","cited_by_count":23},{"id":"1909.08402","title":"Enriching BERT with Knowledge Graph Embeddings for Document Classification","created":"2019-09-18","cited_by_count":22},{"id":"2107.09556","title":"WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset","created":"2021-07-20","cited_by_count":20},{"id":"1708.00781","title":"Dynamic Entity Representations in Neural Language Models","created":"2017-08-02","cited_by_count":19},{"id":"1809.01797","title":"Describing a Knowledge Base","created":"2018-09-06","cited_by_count":18},{"id":"1802.05930","title":"Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing","created":"2018-02-16","cited_by_count":15},{"id":"1805.04836","title":"Building Language Models for Text with Named Entities","created":"2018-05-13","cited_by_count":15},{"id":"1908.07690","title":"Latent Relation Language Models","created":"2019-08-21","cited_by_count":14},{"id":"1608.00318","title":"A Neural Knowledge Language Model","created":"2016-08-01","cited_by_count":13},{"id":"1706.00286","title":"Learning to Compute Word Embeddings On the Fly","created":"2017-06-01","cited_by_count":12},{"id":"1611.01628","title":"Reference-Aware Language Models","created":"2016-11-05","cited_by_count":8}],"next_cursor":null}