<div dir="ltr"><div dir="ltr"><div>Hohoho... you don't know if you want to ask Santa for a wooden train or a quadcopter drone? Despair no more, you can have the best of both worlds:<br></div><div><br></div><div><span class="gmail-im" style="color:rgb(80,0,80)"><h1 dir="ltr" style="line-height:1.38;margin-top:20pt;margin-bottom:6pt;text-align:center"><span style="font-size:20pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Deep Learning and Formal Languages:</span></h1><h1 dir="ltr" style="line-height:1.38;margin-top:20pt;margin-bottom:6pt;text-align:center"><span style="font-size:20pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"> Building Bridges </span></h1><h1 dir="ltr" style="line-height:1.38;margin-top:20pt;margin-bottom:6pt;text-align:center"><span class="gmail-im" style="font-size:small;font-weight:400;text-align:start"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Deep Learning and Formal Languages: Building Bridges -- ACL 2019 Workshop </span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Florence, Italy</span></p></span><p dir="ltr" style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Website: <a href="https://sites.google.com/view/delfol-workshop-acl19" target="_blank">https://sites.google.com/view/delfol-workshop-acl19</a></span></p><span class="gmail-im" style="font-size:small;font-weight:400;text-align:start"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">SUBMISSION DEADLINE: 26 April 2019</span></p><br><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">While deep learning and neural networks have revolutionized the field of natural language processing, changed the habits of its practitioners and opened up new research directions,  many aspects of the inner workings of deep neural networks remain unknown. </span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">At the same time, we have access to many decades of accumulated knowledge on formal languages, grammar, and transductions, both weighted and unweighted and for strings as well as trees: closure properties, computational complexity of various operations, relationships between various classes of them, and many empirical and theoretical results on their learnability.</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">The goal of this workshop is to bring researchers together who are interested in how our understanding of formal languages can contribute to the understanding and design of neural network architectures for natural language processing. For example, fundamental work on neural nets has examined whether they could learn different classes of formal languages, and reciprocally whether formal grammars or automata could closely approximate neural networks. Recently we have seen new research directions on what each formalism can bring to understand or improve the other. Topics which fall within the purview of the workshop include, but are not limited to</span></p><br><ul style="margin-top:0pt;margin-bottom:0pt"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Learnability of formal languages with neural nets (both strong and weak learning)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Relationship between deep learning models and linguistically inspired formalisms</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Connections between neural network architectures and classical computational models</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Traditional formal grammars augmented through non-linearity</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Hybrid models combining neural networks and finite state machines</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">The use of formal grammars to analyze and interpret the behavior of neural networks </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Approximating neural networks with weighted automata and grammars</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Including formal grammar constraints as symbolic priors in neural networks</span></p></li></ul><br></span><p dir="ltr" style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">We call for three types of papers:</span></p><p dir="ltr" style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-size:11pt;white-space:pre-wrap;color:rgb(0,0,0);font-family:Arial">    (1) Regular workshop paper</span></p><p dir="ltr" style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-size:11pt;white-space:pre-wrap;color:rgb(0,0,0);font-family:Arial">    (2) </span><span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial;font-size:11pt;white-space:pre-wrap">Extended abstracts</span></p><p dir="ltr" style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-size:11pt;white-space:pre-wrap;color:rgb(0,0,0);font-family:Arial">    (3) Cross-submissions</span></p><p dir="ltr" style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start;line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Only (1) will be included in the workshop proceedings</span></p><span class="gmail-im" style="font-size:small;font-weight:400;text-align:start"><br><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Some recent work which falls within the scope of this call include:</span></p><br></span><ul style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start;margin-top:0pt;margin-bottom:0pt"><span class="gmail-im" style="color:rgb(80,0,80)"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Bridging CNNs, RNNs, and Weighted Finite-State Machines. Roy Schwartz, Sam Thomson,and Noah A Smith. (ACL 2018)</span></p></li></span><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Rational Recurrences. Hao Peng, Roy Schwartz, Sam Thomson, Noah A. Smith. (ENMLP 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Recurrent Neural Networks as Weighted Language Recognizers. Y. Chen, S. Gilroy, A. Maletti, J. May, and K. Knight.  (NAACL 2018)</span></p></li><span class="gmail-im" style="color:rgb(80,0,80)"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Using Regular Languages to Explore the Representational Capacity of Recurrent Neural Architectures. Abhijit Mahalunkar and John D. Kelleher. (ICANN 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Explaining black boxes on sequential data using weighted automata. Stéphane Ayache, </span><a href="http://www.lif.univ-mrs.fr/~reyraud" target="_blank" style="text-decoration-line:none"><span style="font-size:9pt;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Rémi Eyraud</span></a><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline"> and Noé Goudian. (ICGI 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.2;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples. Gail Weiss, Yoav Goldberg, and Eran Yahav. (ICML 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.2;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction. Siyuan Qi, Baoxiong Jia, and Song-Chun Zhu. (ICML 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses. Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Dmitry Storcheus, Scott Yang (NIPS 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text. Oiwi Parker Jones and Brendan Shillingford (IRASL workshop at NIPS 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Verification of Recurrent Neural Networks Through Rule Extraction. Q Wang, K Zhang, X Liu, and CL Giles (<a href="http://arxiv.org/" target="_blank">arxiv.org</a> 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">A Comparison of Rule Extraction for Different Recurrent Neural Network Models and Grammatical Complexity. Q Wang, K Zhang, II Ororbia, G Alexander, X Xing, X Liu, CL Giles (<a href="http://arxiv.org/" target="_blank">arxiv.org</a> 2018)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Grammar Variational Autoencoder. Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato. (ICML 2017)</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Subregular Complexity and Deep Learning. Enes Avcu, Chihiro Shibata, and Jeffrey Heinz. (LAML 2017)</span></p></li></span><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Recurrent Neural Network Grammars.  Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, and Noah A. Smith. (NAACL 2016).</span></p></li><span class="gmail-im" style="color:rgb(80,0,80)"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:9pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:9pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Weighting finite-state transductions with neural context. Pushpendre Rastogi, Ryan Cotterell, and Jason Eisner (NAACL 2016)</span></p></li></span></ul></h1><h1 dir="ltr" style="line-height:1.38;margin-top:20pt;margin-bottom:6pt"><span style="font-size:20pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Programme Committee </span></h1><h1 dir="ltr" style="line-height:1.38;margin-top:20pt;margin-bottom:6pt;text-align:center"><div class="gmail-adL" style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start"><span class="gmail-im" style="color:rgb(80,0,80)"><ul style="margin-top:0pt;margin-bottom:0pt"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="background-color:transparent;font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;font-weight:700;vertical-align:baseline">Borja Balle</span><span style="background-color:transparent;font-size:11pt;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, Amazon</span><br></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Xavier Carreras</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, dMetrics </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Shay B. Cohen</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, University of Edinburgh </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Alex Clark</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, University of London</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Ewan Dunbar</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, Université Paris Diderot</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Marc Dymetman</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, Naver Labs Europe</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Kyle Gorman</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, City University of New York</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Hadrien Glaude</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, Amazon </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">John Hale</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, University of Georgia </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Mans Hulden</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, University of Colorado </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Franco Luque</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, University of Córdoba</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Chihiro Shibata</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, Tokyo University of Technology </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Adina Williams</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, FAIR</span></p></li></ul><br><br></span></div></h1><h1 dir="ltr" style="line-height:1.38;margin-top:20pt;margin-bottom:6pt"><span style="font-size:20pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:400;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Organizers</span></h1><h1 dir="ltr" style="line-height:1.38;margin-top:20pt;margin-bottom:6pt;text-align:center"><div class="gmail-adL" style="color:rgb(34,34,34);font-size:small;font-weight:400;text-align:start"><span class="gmail-im" style="color:rgb(80,0,80)"><ul style="margin-top:0pt;margin-bottom:0pt"><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Jason Eisner</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, Johns Hopkins University </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Matthias Gallé</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, Naver Labs Europe</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Jeffrey Heinz</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, Stony Brook University </span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Ariadna Quattoni</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">, dMetrics</span></p></li><li dir="ltr" style="margin-left:15px;list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:11pt;background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline">Guillaume Rabusseau,</span><span style="font-size:11pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline"> Université de Montréal / Mila</span></p></li></ul></span></div></h1></span></div></div></div>