{"list":"other","total":53,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"1603.06393","title":"Incorporating Copying Mechanism in Sequence-to-Sequence Learning","created":"2016-03-21","cited_by_count":218},{"id":"1803.06535","title":"Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer","created":"2018-03-17","cited_by_count":211},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155},{"id":"1707.02633","title":"Controlling Linguistic Style Aspects in Neural Language Generation","created":"2017-07-09","cited_by_count":149},{"id":"2005.10283","title":"Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation","created":"2020-05-20","cited_by_count":138},{"id":"1904.02792","title":"Unifying Human and Statistical Evaluation for Natural Language Generation","created":"2019-04-04","cited_by_count":127},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124},{"id":"2111.09388","title":"High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics","created":"2021-11-17","cited_by_count":104},{"id":"1811.02549","title":"Language GANs Falling Short","created":"2018-11-06","cited_by_count":97},{"id":"1712.01818","title":"Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models","created":"2017-12-05","cited_by_count":68},{"id":"2205.11503","title":"Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models","created":"2022-05-23","cited_by_count":49},{"id":"2207.04043","title":"The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications","created":"2022-07-08","cited_by_count":33},{"id":"2010.04297","title":"Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task","created":"2020-10-08","cited_by_count":25},{"id":"1706.02776","title":"Optimizing expected word error rate via sampling for speech recognition","created":"2017-06-08","cited_by_count":21},{"id":"2106.02208","title":"BERTTune: Fine-Tuning Neural Machine Translation with BERTScore","created":"2021-06-04","cited_by_count":18},{"id":"1612.03791","title":"Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices","created":"2016-12-12","cited_by_count":17},{"id":"1908.06288","title":"Leveraging Sentence Similarity in Natural Language Generation: Improving Beam Search using Range Voting","created":"2019-08-17","cited_by_count":15},{"id":"1910.05298","title":"Neural Generation for Czech: Data and Baselines","created":"2019-10-11","cited_by_count":13},{"id":"1609.07561","title":"Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser","created":"2016-09-24","cited_by_count":11}],"next_cursor":null}