{"list":"other","total":61,"rows":[{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"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":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"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":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"1909.05855","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","created":"2019-09-12","cited_by_count":434},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"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":"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":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"2204.01075","title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","created":"2022-04-03","cited_by_count":171},{"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":"2010.03093","title":"WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization","created":"2020-10-07","cited_by_count":154},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"1909.05358","title":"Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset","created":"2019-09-01","cited_by_count":140},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136},{"id":"2004.14900","title":"MLSUM: The Multilingual Summarization Corpus","created":"2020-04-30","cited_by_count":121},{"id":"2005.02324","title":"Neural CRF Model for Sentence Alignment in Text Simplification","created":"2020-05-05","cited_by_count":106},{"id":"2005.10433","title":"Text-to-Text Pre-Training for Data-to-Text Tasks","created":"2020-05-21","cited_by_count":104},{"id":"2005.00481","title":"ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations","created":"2020-05-01","cited_by_count":101},{"id":"1901.07931","title":"Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge","created":"2019-01-23","cited_by_count":86},{"id":"2203.13947","title":"Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension","created":"2022-03-26","cited_by_count":80},{"id":"1810.05995","title":"BLEU is Not Suitable for the Evaluation of Text Simplification","created":"2018-10-14","cited_by_count":78},{"id":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73},{"id":"2002.11893","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","created":"2020-02-27","cited_by_count":66},{"id":"1911.03905","title":"Semantic Noise Matters for Neural Natural Language Generation","created":"2019-11-10","cited_by_count":64},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57},{"id":"2104.05767","title":"Paragraph-level Simplification of Medical Texts","created":"2021-04-12","cited_by_count":53},{"id":"2105.03664","title":"D2S: Document-to-Slide Generation Via Query-Based Text Summarization","created":"2021-05-08","cited_by_count":50},{"id":"2205.11465","title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","created":"2022-05-23","cited_by_count":50},{"id":"1906.03221","title":"Data-to-text Generation with Entity Modeling","created":"2019-06-07","cited_by_count":45},{"id":"2010.08738","title":"RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling","created":"2020-10-17","cited_by_count":41},{"id":"2010.12321","title":"BARThez: a Skilled Pretrained French Sequence-to-Sequence Model","created":"2020-10-23","cited_by_count":40},{"id":"2202.09583","title":"Models and Datasets for Cross-Lingual Summarisation","created":"2022-02-19","cited_by_count":36},{"id":"1906.07220","title":"Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue","created":"2019-06-17","cited_by_count":35},{"id":"2102.02723","title":"Data-to-text Generation with Macro Planning","created":"2021-02-04","cited_by_count":34},{"id":"2103.07929","title":"A Systematic Review of Reproducibility Research in Natural Language Processing","created":"2021-03-14","cited_by_count":34},{"id":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32},{"id":"1910.12129","title":"ViGGO: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation","created":"2019-10-26","cited_by_count":31},{"id":"2109.13489","title":"\"How Robust r u?\": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations","created":"2021-09-28","cited_by_count":30},{"id":"1809.06142","title":"Open Subtitles Paraphrase Corpus for Six Languages","created":"2018-09-17","cited_by_count":24},{"id":"2108.07374","title":"Reusable Templates and Guides For Documenting Datasets and Models for Natural Language Processing and Generation: A Case Study of the HuggingFace and GEM Data and Model Cards","created":"2021-08-16","cited_by_count":24},{"id":"1906.04687","title":"Generating Summaries with Topic Templates and Structured Convolutional Decoders","created":"2019-06-11","cited_by_count":20},{"id":"2012.12458","title":"TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems","created":"2020-12-23","cited_by_count":18},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18},{"id":"2109.05006","title":"BiSECT: Learning to Split and Rephrase Sentences with Bitexts","created":"2021-09-10","cited_by_count":18},{"id":"2109.09195","title":"Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries","created":"2021-09-19","cited_by_count":15},{"id":"1910.05298","title":"Neural Generation for Czech: Data and Baselines","created":"2019-10-11","cited_by_count":13},{"id":"2103.13103","title":"Finnish Paraphrase Corpus","created":"2021-03-24","cited_by_count":10},{"id":"1910.01863","title":"Template-free Data-to-Text Generation of Finnish Sports News","created":"2019-10-04","cited_by_count":9},{"id":"1910.13299","title":"Findings of the Third Workshop on Neural Generation and Translation","created":"2019-10-29","cited_by_count":8},{"id":"2009.08560","title":"Small but Mighty: New Benchmarks for Split and Rephrase","created":"2020-09-17","cited_by_count":8},{"id":"1910.14539","title":"Naver Labs Europe's Systems for the Document-Level Generation and Translation Task at WNGT 2019","created":"2019-10-31","cited_by_count":5},{"id":"2204.13848","title":"Repro: An Open-Source Library for Improving the Reproducibility and Usability of Publicly Available Research Code","created":"2022-04-29","cited_by_count":2}],"next_cursor":null}