{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"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":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1905.02450","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","created":"2019-05-07","cited_by_count":347},{"id":"1706.03872","title":"Six Challenges for Neural Machine Translation","created":"2017-06-12","cited_by_count":335},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"2008.00401","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","created":"2020-08-02","cited_by_count":287},{"id":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"2212.02437","title":"In-context Examples Selection for Machine Translation","created":"2022-12-05","cited_by_count":172},{"id":"2107.10821","title":"To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation","created":"2021-07-22","cited_by_count":163},{"id":"2006.06264","title":"Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics","created":"2020-06-11","cited_by_count":158},{"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":"1803.00047","title":"Analyzing Uncertainty in Neural Machine Translation","created":"2018-02-28","cited_by_count":126},{"id":"1906.02448","title":"Bridging the Gap between Training and Inference for Neural Machine Translation","created":"2019-06-06","cited_by_count":123},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123},{"id":"1808.10006","title":"Correcting Length Bias in Neural Machine Translation","created":"2018-08-29","cited_by_count":120},{"id":"2010.02650","title":"If beam search is the answer, what was the question?","created":"2020-10-06","cited_by_count":116},{"id":"1908.10090","title":"On NMT Search Errors and Model Errors: Cat Got Your Tongue?","created":"2019-08-27","cited_by_count":114},{"id":"1503.06733","title":"Yara Parser: A Fast and Accurate Dependency Parser","created":"2015-03-23","cited_by_count":111},{"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":"2010.12821","title":"Rethinking embedding coupling in pre-trained language models","created":"2020-10-24","cited_by_count":103},{"id":"1804.09849","title":"The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation","created":"2018-04-26","cited_by_count":102},{"id":"1612.02695","title":"Towards better decoding and language model integration in sequence to sequence models","created":"2016-12-08","cited_by_count":100},{"id":"1609.00150","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","created":"2016-09-01","cited_by_count":81},{"id":"1808.08866","title":"A Study of Reinforcement Learning for Neural Machine Translation","created":"2018-08-27","cited_by_count":74},{"id":"1903.00802","title":"Calibration of Encoder Decoder Models for Neural Machine Translation","created":"2019-03-03","cited_by_count":68},{"id":"2108.04718","title":"Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation","created":"2021-08-10","cited_by_count":65},{"id":"2005.00963","title":"On the Inference Calibration of Neural Machine Translation","created":"2020-05-03","cited_by_count":61},{"id":"2105.08504","title":"Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation","created":"2021-05-18","cited_by_count":56},{"id":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55},{"id":"2211.07634","title":"Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding","created":"2022-11-14","cited_by_count":54},{"id":"2005.00820","title":"Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing","created":"2020-05-02","cited_by_count":41},{"id":"2010.03737","title":"Shallow-to-Deep Training for Neural Machine Translation","created":"2020-10-08","cited_by_count":36},{"id":"1805.07591","title":"Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval","created":"2018-05-19","cited_by_count":33},{"id":"2005.07493","title":"History for Visual Dialog: Do we really need it?","created":"2020-05-08","cited_by_count":32},{"id":"1808.09582","title":"Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation","created":"2018-08-28","cited_by_count":29},{"id":"2202.11822","title":"Using natural language prompts for machine translation","created":"2022-02-23","cited_by_count":27},{"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":"1812.07807","title":"DTMT: A Novel Deep Transition Architecture for Neural Machine Translation","created":"2018-12-19","cited_by_count":13},{"id":"2010.10743","title":"Multi-Unit Transformers for Neural Machine Translation","created":"2020-10-21","cited_by_count":13},{"id":"1904.06834","title":"An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search","created":"2019-04-15","cited_by_count":12},{"id":"2108.02401","title":"WeChat Neural Machine Translation Systems for WMT21","created":"2021-08-05","cited_by_count":11},{"id":"1704.03169","title":"Later-stage Minimum Bayes-Risk Decoding for Neural Machine Translation","created":"2017-04-11","cited_by_count":8},{"id":"1708.00563","title":"Analyzing Neural MT Search and Model Performance","created":"2017-08-02","cited_by_count":2},{"id":"1803.07204","title":"Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation","created":"2018-03-20","cited_by_count":2},{"id":"2106.15217","title":"Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space","created":"2021-06-29","cited_by_count":2}],"next_cursor":null}