**Abstr
act**

Recent advances in data-driven approaches have demons trated appealing results in generating natural languages in applications l ike machine translation and summarization. However\, when the generation t asks are open-ended and the content is under-specified\, existing techniqu es struggle to generate coherent and creative passages. This happens becau se the generation models are trained to capture the surface form (i.e. seq uences of words)\, rather than the underlying semantics and discourse stru ctures. Moreover\, composing creative pieces such as puns\, poems\, and st ories require deviating from the norm\, whereas existing generation approa ches seek to mimic the norm and thus are unlikely to lead to truly novel\, creative composition. In this talk\, I will present several of our recent works related to creative story and figurative language generation\, emph asizing the importance of understanding and control for creative generatio n.

\n**Biography**

Nanyun (Violet) Peng is an Assistant Professor of Computer Science at the University of Cali fornia\, Los Angeles. Prior to that\, she spent three years at the Univers ity of Southern California’s Information Sciences Institute. She received her Ph.D. in Computer Science from Johns Hopkins University\, Center for L anguage and Speech Processing advised by Dr. Mark Dredze. Her research foc uses on creative language generation\, and the robustness and generalizabi lity of natural language understanding\, with works being featured in majo r tech media such as Wired and The Register.

\n X-TAGS;LANGUAGE=en-US:2020\,Peng\,September END:VEVENT BEGIN:VEVENT UID:ai1ec-20117@www.clsp.jhu.edu DTSTAMP:20230326T000034Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract\nNeural sequence generation systems oftentimes generat e sequences by searching for the most likely sequence under the learnt pro bability distribution. This assumes that the most likely sequence\, i.e. t he mode\, under such a model must also be the best sequence it has to offe r (often in a given context\, e.g. conditioned on a source sentence in tra nslation). Recent findings in neural machine translation (NMT) show that t he true most likely sequence oftentimes is empty under many state-of-the-a rt NMT models. This follows a large list of other pathologies and biases o bserved in NMT and other sequence generation models: a length bias\, large r beams degrading performance\, exposure bias\, and many more. Many of the se works blame the probabilistic formulation of NMT or maximum likelihood estimation. We provide a different view on this: it is mode-seeking search \, e.g. beam search\, that introduces many of these pathologies and biases \, and such a decision rule is not suitable for the type of distributions learnt by NMT systems. We show that NMT models spread probability mass ove r many translations\, and that the most likely translation oftentimes is a rare event. We further show that translation distributions do capture imp ortant aspects of translation well in expectation. Therefore\, we advocate for decision rules that take into account the entire probability distribu tion and not just its mode. We provide one example of such a decision rule \, and show that this is a fruitful research direction.\nBiography\nI am a n assistant professor (UD) in natural language processing at the Institute for Logic\, Language and Computation where I lead the Probabilistic Langu age Learning group.\nMy work concerns the design of models and algorithms that learn to represent\, understand\, and generate language data. Example s of specific problems I am interested in include language modelling\, mac hine translation\, syntactic parsing\, textual entailment\, text classific ation\, and question answering.\nI also develop techniques to approach gen eral machine learning problems such as probabilistic inference\, gradient and density estimation.\nMy interests sit at the intersection of disciplin es such as statistics\, machine learning\, approximate inference\, global optimization\, formal languages\, and computational linguistics.\n \n DTSTART;TZID=America/New_York:20210419T120000 DTEND;TZID=America/New_York:20210419T131500 LOCATION:via Zoom SEQUENCE:0 SUMMARY:Wilker Aziz (University of Amsterdam) “The Inadequacy of the Mode in Neural Machine Translation” URL:https://www.clsp.jhu.edu/events/wilker-aziz-university-of-amsterdam/ X-COST-TYPE:free X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n**Abstr
act**

Neural sequence generation systems oftentimes generat e sequences by searching for the most likely sequence under the learnt pro bability distribution. This assumes that the most likely sequence\, i.e. t he mode\, under such a model must also be the best sequence it has to offe r (often in a given context\, e.g. conditioned on a source sentence in tra nslation). Recent findings in neural machine translation (NMT) show that t he true most likely sequence oftentimes is empty under many state-of-the-a rt NMT models. This follows a large list of other pathologies and biases o bserved in NMT and other sequence generation models: a length bias\, large r beams degrading performance\, exposure bias\, and many more. Many of the se works blame the probabilistic formulation of NMT or maximum likelihood estimation. We provide a different view on this: it is mode-seeking search \, e.g. beam search\, that introduces many of these pathologies and biases \, and such a decision rule is not suitable for the type of distributions learnt by NMT systems. We show that NMT models spread probability mass ove r many translations\, and that the most likely translation oftentimes is a rare event. We further show that translation distributions do capture imp ortant aspects of translation well in expectation. Therefore\, we advocate for decision rules that take into account the entire probability distribu tion and not just its mode. We provide one example of such a decision rule \, and show that this is a fruitful research direction.

\n**Bi
ography**

I am an *assistant professor* (UD) in natu
ral language processing at the Institute
for Logic\, Language and Computation where I lead the Probabilistic Language Learning group.

My work concerns the design of models and algorithms that learn to represe nt\, understand\, and generate language data. Examples of specific problem s I am interested in include language modelling\, machine translation\, sy ntactic parsing\, textual entailment\, text classification\, and question answering.

\nI also develop techniques to approach general machine l earning problems such as probabilistic inference\, gradient and density es timation.

\nMy interests sit at the intersection of disciplines such as statistics\, machine learning\, approximate inference\, global optimiz ation\, formal languages\, and computational linguistics.

\n\n< p> \n X-TAGS;LANGUAGE=en-US:2021\,April\,Aziz END:VEVENT BEGIN:VEVENT UID:ai1ec-20120@www.clsp.jhu.edu DTSTAMP:20230326T000034Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract\nRobotics@Google’s mission is to make robots useful in the real world through machine learning. We are excited about a new model for robotics\, designed for generalization across diverse environments an d instructions. This model is focused on scalable data-driven learning\, w hich is task-agnostic\, leverages simulation\, learns from past experience \, and can be quickly adapted to work in the real-world through limited in teractions. In this talk\, we’ll share some of our recent work in this dir ection in both manipulation and locomotion applications.\nBiography\nCarol ina Parada is a Senior Engineering Manager at Google Robotics. She leads t he robot-mobility group\, which focuses on improving robot motion planning \, navigation\, and locomotion\, using reinforcement learning. Prior to th at\, she led the camera perception team for self-driving cars at Nvidia fo r 2 years. She was also a lead with Speech @ Google for 7 years\, where sh e drove multiple research and engineering efforts that enabled Ok Google\, the Google Assistant\, and Voice-Search. Carolina grew up in Venezuela an d moved to the US to pursue a B.S. and M.S. degree in Electrical Engineeri ng at University of Washington and her Phd at Johns Hopkins University at the Center for Language and Speech Processing (CLSP). DTSTART;TZID=America/New_York:20210423T120000 DTEND;TZID=America/New_York:20210423T131500 LOCATION:via Zoom SEQUENCE:0 SUMMARY:Carolina Parada (Google AI) “State of Robotics @ Google” URL:https://www.clsp.jhu.edu/events/carolina-parada-google-ai/ X-COST-TYPE:free X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n

**Abstr
act**

Robotics@Google’s mission is to make robots useful i n the real world through machine learning. We are excited about a new mode l for robotics\, designed for generalization across diverse environments a nd instructions. This model is focused on scalable data-driven learning\, which is task-agnostic\, leverages simulation\, learns from past experienc e\, and can be quickly adapted to work in the real-world through limited i nteractions. In this talk\, we’ll share some of our recent work in this di rection in both manipulation and locomotion applications.

\n< strong>Biography

\nCarolina Parad a is a Senior Engineering Manager at Google Robotics. She leads the robot-mobility group\, which focuses on improving robot motion planning\, navigation\, and locomotion\, using reinforcement learning. Prior to that \, she led the camera perception team for self-driving cars at Nvidia for 2 years. She was also a lead with Speech @ Google for 7 years\, where she drove multiple research and engineering efforts that enabled Ok Google\, t he Google Assistant\, and Voice-Search. Carolina< /span> grew up in Venezuela and moved to the US to pursue a B.S. and M.S. degree in Electrical Engineering at University of Washington and her Phd a t Johns Hopkins University at the Center for Language and Speech Processin g (CLSP).

\n X-TAGS;LANGUAGE=en-US:2021\,April\,Parada END:VEVENT BEGIN:VEVENT UID:ai1ec-22395@www.clsp.jhu.edu DTSTAMP:20230326T000034Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract\nRecursive calls over recursive data are widely useful for generating probability distributions\, and probabilistic programming allows computations over these distributions to be expressed in a modular and intuitive way. Exact inference is also useful\, but unfortunately\, ex isting probabilistic programming languages do not perform exact inference on recursive calls over recursive data\, forcing programmers to code many applications manually. We introduce a probabilistic language in which a wi de variety of recursion can be expressed naturally\, and inference carried out exactly. For instance\, probabilistic pushdown automata and their gen eralizations are easy to express\, and polynomial-time parsing algorithms for them are derived automatically. We eliminate recursive data types usin g program transformations related to defunctionalization and refunctionali zation. These transformations are assured correct by a linear type system\ , and a successful choice of transformations\, if there is one\, is guaran teed to be found by a greedy algorithm. I will also describe the implement ation of this language in two phases: first\, compilation to a factor grap h grammar\, and second\, computing the sum-product of the factor graph gra mmar.\n\nBiography\nDavid Chiang (PhD\, University of Pennsylvania\, 2004) is an associate professor in the Department of Computer Science and Engin eering at the University of Notre Dame. His research is on computational m odels for learning human languages\, particularly how to translate from on e language to another. His work on applying formal grammars and machine le arning to translation has been recognized with two best paper awards (at A CL 2005 and NAACL HLT 2009). He has received research grants from DARPA\, NSF\, Google\, and Amazon\, has served on the executive board of NAACL and the editorial board of Computational Linguistics and JAIR\, and is curren tly on the editorial board of Transactions of the ACL. DTSTART;TZID=America/New_York:20221017T120000 DTEND;TZID=America/New_York:20221017T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:David Chiang (University of Notre Dame) “Exact Recursive Probabilis tic Programming with Colin McDonald\, Darcey Riley\, Kenneth Sible (Notre Dame) and Chung-chieh Shan (Indiana)” URL:https://www.clsp.jhu.edu/events/david-chiang-university-of-notre-dame/ X-COST-TYPE:free X-ALT-DESC;FMTTYPE=text/html:\\n\\n\\n**Abstr
act**

Recursive calls over recursive data are w
idely useful for generating probability distributions\, and probabilistic
programming allows computations over these distributions to be expressed i
n a modular and intuitive way. Exact inference is also useful\, but unfort
unately\, existing probabilistic programming languages do not perform exac
t inference on recursive calls over recursive data\, forcing programmers t
o code many applications manually. We introduce a probabilistic language i
n which a wide variety of recursion can be expressed naturally\, and infer
ence carried out exactly. For instance\, probabilistic pushdown automata a
nd their generalizations are easy to express\, and polynomial-time parsing
algorithms for them are derived automatically. We eliminate recursive dat
a types using program transformations related to defunctionalization and r
efunctionalization. These transformations are assured correct by a linear
type system\, and a successful choice of transformations\, if there is one
\, is guaranteed to be found by a greedy algorithm. I will also describe t
he implementation of this language in two phases: first\, compilation to a
factor graph grammar\, and second\, computing the sum-product of the fact
or graph grammar.

\n\nDavid Chiang (PhD\,
University of Pennsylvania\, 2004) is an associate professor in the Depart
ment of Computer Science and Engineering at the University of Notre Dame.
His research is on computational models for learning human languages\, par
ticularly how to translate from one language to another. His work on apply
ing formal grammars and machine learning to translation has been recognize
d with two best paper awards (at ACL 2005 and NAACL HLT 2009). He has rece
ived research grants from DARPA\, NSF\, Google\, and Amazon\, has served o
n the executive board of NAACL and the editorial board of Computational Li
nguistics and JAIR\, and is currently on the editorial board of Transactio
ns of the ACL.

\n
X-TAGS;LANGUAGE=en-US:2022\,Chiang\,October
END:VEVENT
BEGIN:VEVENT
UID:ai1ec-23515@www.clsp.jhu.edu
DTSTAMP:20230326T000034Z
CATEGORIES;LANGUAGE=en-US:Student Seminars
CONTACT:
DESCRIPTION:
DTSTART;TZID=America/New_York:20230403T120000
DTEND;TZID=America/New_York:20230403T131500
LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218
SEQUENCE:0
SUMMARY:Student Seminar – Samik Sadhu
URL:https://www.clsp.jhu.edu/events/student-seminar-samik-sadhu/
X-COST-TYPE:free
X-TAGS;LANGUAGE=en-US:2023\,April\,Sadhu
END:VEVENT
END:VCALENDAR