{"list":"other","total":187,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"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":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"1611.01734","title":"Deep Biaffine Attention for Neural Dependency Parsing","created":"2016-11-06","cited_by_count":334},{"id":"1808.09602","title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","created":"2018-08-29","cited_by_count":322},{"id":"2003.12206","title":"Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)","created":"2020-03-27","cited_by_count":322},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"1703.00955","title":"Toward Controlled Generation of Text","created":"2017-03-02","cited_by_count":272},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"1705.07120","title":"VAE with a VampPrior","created":"2017-05-19","cited_by_count":248},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"1603.06393","title":"Incorporating Copying Mechanism in Sequence-to-Sequence Learning","created":"2016-03-21","cited_by_count":218},{"id":"1703.09902","title":"Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation","created":"2017-03-29","cited_by_count":206},{"id":"1905.11006","title":"Levenshtein Transformer","created":"2019-05-27","cited_by_count":199},{"id":"1605.06069","title":"A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues","created":"2016-05-19","cited_by_count":174},{"id":"1506.08909","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","created":"2015-06-30","cited_by_count":172},{"id":"2203.06486","title":"Chart-to-Text: A Large-Scale Benchmark for Chart Summarization","created":"2022-03-12","cited_by_count":169},{"id":"1909.07940","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","created":"2019-09-17","cited_by_count":159},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139},{"id":"1703.04826","title":"Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling","created":"2017-03-14","cited_by_count":137},{"id":"1508.01745","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","created":"2015-08-07","cited_by_count":134},{"id":"2004.04487","title":"Injecting Numerical Reasoning Skills into Language Models","created":"2020-04-09","cited_by_count":133},{"id":"1904.02792","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","created":"2019-04-04","cited_by_count":127},{"id":"1904.02342","title":"Text Generation from Knowledge Graphs with Graph Transformers","created":"2019-04-04","cited_by_count":122},{"id":"1906.01081","title":"Handling Divergent Reference Texts when Evaluating Table-to-Text Generation","created":"2019-06-03","cited_by_count":119},{"id":"1805.02262","title":"Construction of the Literature Graph in Semantic Scholar","created":"2018-05-06","cited_by_count":118},{"id":"2007.08426","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","created":"2020-07-16","cited_by_count":117},{"id":"1601.04811","title":"Modeling Coverage for Neural Machine Translation","created":"2016-01-19","cited_by_count":110},{"id":"1805.04793","title":"Coarse-to-Fine Decoding for Neural Semantic Parsing","created":"2018-05-12","cited_by_count":110},{"id":"1809.00582","title":"Data-to-Text Generation with Content Selection and Planning","created":"2018-09-03","cited_by_count":106},{"id":"1701.06547","title":"Adversarial Learning for Neural Dialogue Generation","created":"2017-01-23","cited_by_count":103},{"id":"1909.01187","title":"Encode, Tag, Realize: High-Precision Text Editing","created":"2019-09-03","cited_by_count":99},{"id":"1909.10705","title":"Do Massively Pretrained Language Models Make Better Storytellers?","created":"2019-09-24","cited_by_count":90},{"id":"2004.10404","title":"Logical Natural Language Generation from Open-Domain Tables","created":"2020-04-22","cited_by_count":90},{"id":"2103.13136","title":"Representing Numbers in NLP: a Survey and a Vision","created":"2021-03-24","cited_by_count":83},{"id":"2010.09142","title":"Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model","created":"2020-10-18","cited_by_count":78},{"id":"1909.01214","title":"Better Rewards Yield Better Summaries: Learning to Summarise Without References","created":"2019-09-03","cited_by_count":77},{"id":"1904.03396","title":"Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation","created":"2019-04-06","cited_by_count":75},{"id":"1707.09861","title":"Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging","created":"2017-07-31","cited_by_count":73},{"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":"1803.05928","title":"RankME: Reliable Human Ratings for Natural Language Generation","created":"2018-03-15","cited_by_count":69},{"id":"1911.03905","title":"Semantic Noise Matters for Neural Natural Language Generation","created":"2019-11-10","cited_by_count":64},{"id":"1908.06605","title":"Long and Diverse Text Generation with Planning-based Hierarchical Variational Model","created":"2019-08-19","cited_by_count":62},{"id":"1910.08684","title":"Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation","created":"2019-10-19","cited_by_count":62},{"id":"1806.09835","title":"Graph-to-Sequence Learning using Gated Graph Neural Networks","created":"2018-06-26","cited_by_count":61},{"id":"1808.10122","title":"Learning Neural Templates for Text Generation","created":"2018-08-30","cited_by_count":61},{"id":"2109.03506","title":"Towards Natural Language Interfaces for Data Visualization: A Survey","created":"2021-09-08","cited_by_count":59},{"id":"2106.10502","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","created":"2021-06-19","cited_by_count":58},{"id":"1703.10186","title":"Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding","created":"2017-03-29","cited_by_count":57},{"id":"1704.08381","title":"Neural AMR: Sequence-to-Sequence Models for Parsing and Generation","created":"2017-04-26","cited_by_count":56},{"id":"1711.04987","title":"Unified Pragmatic Models for Generating and Following Instructions","created":"2017-11-14","cited_by_count":55}],"next_cursor":"100"}