Understanding Learning Dynamics Of Language Models with SVCCA
暂无分享,去创建一个
[1] Jeffrey Dean,et al. Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.
[2] Michael Carbin,et al. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks , 2018, ICLR.
[3] Alfred O. Hero,et al. Scalable Mutual Information Estimation Using Dependence Graphs , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[4] Johan Bos,et al. The Groningen Meaning Bank , 2013, JSSP.
[5] Naftali Tishby,et al. Opening the Black Box of Deep Neural Networks via Information , 2017, ArXiv.
[6] Omer Levy,et al. LSTMs Exploit Linguistic Attributes of Data , 2018, Rep4NLP@ACL.
[7] Grzegorz Chrupala,et al. Encoding of phonology in a recurrent neural model of grounded speech , 2017, CoNLL.
[8] Sara Veldhoen,et al. Visualisation and 'Diagnostic Classifiers' Reveal How Recurrent and Recursive Neural Networks Process Hierarchical Structure , 2018, J. Artif. Intell. Res..
[9] Ryan Cotterell,et al. Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate , 2018, TACL.
[10] Samuel R. Bowman,et al. Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis , 2018, BlackboxNLP@EMNLP.
[11] Johan Bos,et al. Semantic Tagging with Deep Residual Networks , 2016, COLING.
[12] Omer Levy,et al. Deep RNNs Encode Soft Hierarchical Syntax , 2018, ACL.
[13] Yulia Tsvetkov,et al. Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning , 2016, ACL.
[14] Bin Yu,et al. Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs , 2018, ICLR.
[15] Samy Bengio,et al. Understanding deep learning requires rethinking generalization , 2016, ICLR.
[16] Michael Carbin,et al. The Lottery Ticket Hypothesis: Training Pruned Neural Networks , 2018, ArXiv.
[17] Edouard Grave,et al. Colorless Green Recurrent Networks Dream Hierarchically , 2018, NAACL.
[18] Florian Mohnert,et al. Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information , 2018, BlackboxNLP@EMNLP.
[19] Guillaume Lample,et al. What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties , 2018, ACL.
[20] Hod Lipson,et al. Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.
[21] Daniel Jurafsky,et al. Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context , 2018, ACL.
[22] Douwe Kiela,et al. No Training Required: Exploring Random Encoders for Sentence Classification , 2019, ICLR.
[23] Luke S. Zettlemoyer,et al. Deep Contextualized Word Representations , 2018, NAACL.
[24] Andy Way,et al. Investigating ‘Aspect’ in NMT and SMT: Translating the English Simple Past and Present Perfect , 2017 .
[25] Emmanuel Dupoux,et al. Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies , 2016, TACL.
[26] Grzegorz Chrupala,et al. Representation of Linguistic Form and Function in Recurrent Neural Networks , 2016, CL.
[27] Yoshua Bengio,et al. On the Learning Dynamics of Deep Neural Networks , 2018, ArXiv.
[28] Ondrej Bojar,et al. Are BLEU and Meaning Representation in Opposition? , 2018, ACL.
[29] Anders Søgaard,et al. Deep multi-task learning with low level tasks supervised at lower layers , 2016, ACL.
[30] Rob Fergus,et al. Visualizing and Understanding Convolutional Networks , 2013, ECCV.
[31] Jascha Sohl-Dickstein,et al. SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability , 2017, NIPS.
[32] Samy Bengio,et al. Insights on representational similarity in neural networks with canonical correlation , 2018, NeurIPS.
[33] Adam Lopez,et al. Indicatements that character language models learn English morpho-syntactic units and regularities , 2018, BlackboxNLP@EMNLP.
[34] Yonatan Belinkov,et al. What do Neural Machine Translation Models Learn about Morphology? , 2017, ACL.
[35] Yonatan Belinkov,et al. Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks , 2017, IJCNLP.