{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1902.10197","title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","created":"2019-02-26","cited_by_count":898},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1905.07129","title":"ERNIE: Enhanced Language Representation with Informative Entities","created":"2019-05-17","cited_by_count":528},{"id":"1906.05317","title":"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction","created":"2019-06-12","cited_by_count":450},{"id":"1911.03082","title":"Composition-based Multi-Relational Graph Convolutional Networks","created":"2019-11-08","cited_by_count":396},{"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":"1911.06136","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","created":"2019-11-13","cited_by_count":356},{"id":"2010.01057","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","created":"2020-10-02","cited_by_count":326},{"id":"2002.01808","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","created":"2020-02-05","cited_by_count":319},{"id":"1909.04164","title":"Knowledge Enhanced Contextual Word Representations","created":"2019-09-09","cited_by_count":296},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231},{"id":"2110.08387","title":"Generated Knowledge Prompting for Commonsense Reasoning","created":"2021-10-15","cited_by_count":214},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"id":"2201.08860","title":"GreaseLM: Graph REASoning Enhanced Language Models for Question Answering","created":"2022-01-21","cited_by_count":171},{"id":"2009.12677","title":"KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning","created":"2020-09-26","cited_by_count":106},{"id":"2010.00309","title":"CoLAKE: Contextualized Language and Knowledge Embedding","created":"2020-10-01","cited_by_count":86},{"id":"2010.00796","title":"JAKET: Joint Pre-training of Knowledge Graph and Language Understanding","created":"2020-10-02","cited_by_count":73},{"id":"2110.04330","title":"KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering","created":"2021-10-08","cited_by_count":67},{"id":"2012.14610","title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","created":"2020-12-29","cited_by_count":61},{"id":"2012.11490","title":"CSKG: The CommonSense Knowledge Graph","created":"2020-12-21","cited_by_count":45},{"id":"2110.06176","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","created":"2021-10-12","cited_by_count":43},{"id":"2112.02732","title":"JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering","created":"2021-12-06","cited_by_count":40},{"id":"1911.06192","title":"Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering","created":"2019-11-07","cited_by_count":39},{"id":"2110.08417","title":"Open Domain Question Answering with A Unified Knowledge Interface","created":"2021-10-16","cited_by_count":32},{"id":"2103.11320","title":"Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources","created":"2021-03-21","cited_by_count":30},{"id":"2205.08184","title":"SKILL: Structured Knowledge Infusion for Large Language Models","created":"2022-05-17","cited_by_count":27},{"id":"2006.13774","title":"Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings","created":"2020-06-24","cited_by_count":21},{"id":"2204.10555","title":"KALA: Knowledge-Augmented Language Model Adaptation","created":"2022-04-22","cited_by_count":21},{"id":"2112.08544","title":"NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge","created":"2021-12-16","cited_by_count":20},{"id":"2204.04046","title":"KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News Media","created":"2022-04-08","cited_by_count":20},{"id":"2109.04223","title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","created":"2021-09-09","cited_by_count":19},{"id":"2204.09149","title":"DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation","created":"2022-04-19","cited_by_count":19},{"id":"1912.02761","title":"Measuring Social Bias in Knowledge Graph Embeddings","created":"2019-12-05","cited_by_count":17},{"id":"2004.12006","title":"Contextualized Representations Using Textual Encyclopedic Knowledge","created":"2020-04-24","cited_by_count":17},{"id":"2209.14464","title":"Neural Methods for Logical Reasoning Over Knowledge Graphs","created":"2022-09-28","cited_by_count":17},{"id":"2204.10448","title":"Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering","created":"2022-04-22","cited_by_count":15},{"id":"2108.03861","title":"KGAP: Knowledge Graph Augmented Political Perspective Detection in News Media","created":"2021-08-09","cited_by_count":14},{"id":"2109.04810","title":"Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT","created":"2021-09-10","cited_by_count":14},{"id":"1712.09783","title":"Topic Compositional Neural Language Model","created":"2017-12-28","cited_by_count":11},{"id":"2208.07622","title":"KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion","created":"2022-08-16","cited_by_count":10},{"id":"2207.08982","title":"Selection Bias Induced Spurious Correlations in Large Language Models","created":"2022-07-18","cited_by_count":9},{"id":"2204.02549","title":"C3KG: A Chinese Commonsense Conversation Knowledge Graph","created":"2022-04-06","cited_by_count":8},{"id":"2208.06458","title":"LM-CORE: Language Models with Contextually Relevant External Knowledge","created":"2022-08-12","cited_by_count":8},{"id":"2203.02985","title":"Dynamic Key-value Memory Enhanced Multi-step Graph Reasoning for Knowledge-based Visual Question Answering","created":"2022-03-06","cited_by_count":7},{"id":"2109.10697","title":"Towards Automatic Bias Detection in Knowledge Graphs","created":"2021-09-19","cited_by_count":6},{"id":"2203.08979","title":"Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching","created":"2022-03-16","cited_by_count":6},{"id":"1810.03947","title":"textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior","created":"2018-10-09","cited_by_count":5},{"id":"2206.03715","title":"Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning","created":"2022-06-08","cited_by_count":5},{"id":"2006.10632","title":"Explainable and Discourse Topic-aware Neural Language Understanding","created":"2020-06-18","cited_by_count":4},{"id":"2108.03881","title":"Legislator Representation Learning with Social Context and Expert Knowledge","created":"2021-08-09","cited_by_count":3}],"next_cursor":null}