{"list":"other","total":157,"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":"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1905.12616","title":"Defending Against Neural Fake News","created":"2019-05-29","cited_by_count":559},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"1308.0850","title":"Generating Sequences With Recurrent Neural Networks","created":"2013-08-04","cited_by_count":554},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2010.16056","title":"Generating Radiology Reports via Memory-driven Transformer","created":"2020-10-30","cited_by_count":368},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356},{"id":"1708.01967","title":"Fake News Detection on Social Media: A Data Mining Perspective","created":"2017-08-07","cited_by_count":336},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"2005.03754","title":"FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization","created":"2020-05-07","cited_by_count":293},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287},{"id":"1605.07725","title":"Adversarial Training Methods for Semi-Supervised Text Classification","created":"2016-05-25","cited_by_count":280},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"2012.15409","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","created":"2020-12-31","cited_by_count":239},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"1704.07138","title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","created":"2017-04-24","cited_by_count":237},{"id":"2112.08542","title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","created":"2021-12-16","cited_by_count":236},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"1603.06155","title":"A Persona-Based Neural Conversation Model","created":"2016-03-19","cited_by_count":223},{"id":"1603.06393","title":"Incorporating Copying Mechanism in Sequence-to-Sequence Learning","created":"2016-03-21","cited_by_count":218},{"id":"1711.08195","title":"On the Automatic Generation of Medical Imaging Reports","created":"2017-11-22","cited_by_count":216},{"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":"1609.06038","title":"Enhanced LSTM for Natural Language Inference","created":"2016-09-20","cited_by_count":200},{"id":"1506.05869","title":"A Neural Conversational Model","created":"2015-06-19","cited_by_count":196},{"id":"1409.2329","title":"Recurrent Neural Network Regularization","created":"2014-09-08","cited_by_count":189},{"id":"1705.00106","title":"Learning to Ask: Neural Question Generation for Reading Comprehension","created":"2017-04-29","cited_by_count":186},{"id":"1804.06609","title":"Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation","created":"2018-04-18","cited_by_count":182},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"1404.2188","title":"A Convolutional Neural Network for Modelling Sentences","created":"2014-04-08","cited_by_count":163},{"id":"2104.06683","title":"The Curious Case of Hallucinations in Neural Machine Translation","created":"2021-04-14","cited_by_count":161},{"id":"2004.08728","title":"SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings","created":"2020-04-18","cited_by_count":156},{"id":"2011.02593","title":"Detecting Hallucinated Content in Conditional Neural Sequence Generation","created":"2020-11-05","cited_by_count":152},{"id":"1910.07931","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","created":"2019-10-17","cited_by_count":145},{"id":"1711.04434","title":"Faithful to the Original: Fact Aware Neural Abstractive Summarization","created":"2017-11-13","cited_by_count":141},{"id":"1805.08298","title":"Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation","created":"2018-05-21","cited_by_count":141},{"id":"2010.10042","title":"Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation","created":"2020-10-20","cited_by_count":141},{"id":"1904.02633","title":"Clinically Accurate Chest X-Ray Report Generation","created":"2019-04-04","cited_by_count":139},{"id":"1702.01932","title":"A Knowledge-Grounded Neural Conversation Model","created":"2017-02-07","cited_by_count":136},{"id":"1811.00671","title":"Dialogue Natural Language Inference","created":"2018-11-01","cited_by_count":135},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132},{"id":"2104.04302","title":"Annotating and Modeling Fine-grained Factuality in Summarization","created":"2021-04-09","cited_by_count":131},{"id":"2010.08014","title":"GSum: A General Framework for Guided Neural Abstractive Summarization","created":"2020-10-15","cited_by_count":129},{"id":"2005.03642","title":"On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation","created":"2020-05-07","cited_by_count":127},{"id":"2010.05478","title":"Evaluating Factuality in Generation with Dependency-level Entailment","created":"2020-10-12","cited_by_count":122},{"id":"2109.09209","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","created":"2021-09-19","cited_by_count":120},{"id":"1906.01081","title":"Handling Divergent Reference Texts when Evaluating Table-to-Text Generation","created":"2019-06-03","cited_by_count":119},{"id":"2102.09130","title":"Entity-level Factual Consistency of Abstractive Text Summarization","created":"2021-02-18","cited_by_count":118},{"id":"1601.04811","title":"Modeling Coverage for Neural Machine Translation","created":"2016-01-19","cited_by_count":110},{"id":"1911.03860","title":"Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training","created":"2019-11-10","cited_by_count":110},{"id":"2010.08712","title":"Factual Error Correction for Abstractive Summarization Models","created":"2020-10-17","cited_by_count":108},{"id":"1906.02443","title":"Robust Neural Machine Translation with Doubly Adversarial Inputs","created":"2019-06-06","cited_by_count":106},{"id":"2007.01162","title":"Tilted Empirical Risk Minimization","created":"2020-07-02","cited_by_count":106},{"id":"2104.08455","title":"Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding","created":"2021-04-17","cited_by_count":106},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"1905.13322","title":"Assessing The Factual Accuracy of Generated Text","created":"2019-05-30","cited_by_count":103},{"id":"1809.02922","title":"Transforming Question Answering Datasets Into Natural Language Inference Datasets","created":"2018-09-09","cited_by_count":99},{"id":"1911.02541","title":"Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports","created":"2019-11-06","cited_by_count":96},{"id":"1811.10996","title":"CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling","created":"2018-11-14","cited_by_count":94},{"id":"1712.07709","title":"Beyond News Contents: The Role of Social Context for Fake News Detection","created":"2017-12-20","cited_by_count":91},{"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":"2010.05873","title":"Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data","created":"2020-10-12","cited_by_count":84},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77},{"id":"2010.12834","title":"GO FIGURE: A Meta Evaluation of Factuality in Summarization","created":"2020-10-24","cited_by_count":76},{"id":"2104.09061","title":"Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection","created":"2021-04-19","cited_by_count":76},{"id":"1909.02074","title":"Jointly Learning to Align and Translate with Transformer Models","created":"2019-09-04","cited_by_count":75},{"id":"2004.14589","title":"Improved Natural Language Generation via Loss Truncation","created":"2020-04-30","cited_by_count":75},{"id":"2107.06963","title":"Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features","created":"2021-07-14","cited_by_count":74},{"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":"2012.13391","title":"I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling","created":"2020-12-24","cited_by_count":68},{"id":"1905.11553","title":"Target-Guided Open-Domain Conversation","created":"2019-05-28","cited_by_count":66},{"id":"2005.01159","title":"Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward","created":"2020-05-03","cited_by_count":66},{"id":"2010.02443","title":"Multi-Fact Correction in Abstractive Text Summarization","created":"2020-10-06","cited_by_count":66},{"id":"1911.03109","title":"Domain Robustness in Neural Machine Translation","created":"2019-11-08","cited_by_count":65},{"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":"2110.08222","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","created":"2021-10-15","cited_by_count":62}],"next_cursor":"100"}