Tuesday, November 19, 2019 - 10:30

Speaker: Sam Bowman
Location: CSE 305

Abstract: The GLUE and SuperGLUE shared-task benchmarks aim to measure progress toward the goal of building general-purpose pretrained neural network models for language understanding. This goal turns out to have been widely shared, and these benchmarks have become a significant target for research in the NLP and machine learning communities. In this talk, I'll review the motivations behind these benchmarks and what these benchmarks can tell us about recent progress in NLP, and raise a few (open!) questions about how we should measure further progress in this area.

Bio: Sam Bowman has been an assistant professor at NYU since 2016, when he completed PhD with Chris Manning and Chris Potts at Stanford. At NYU, Sam is jointly appointed between the new school-level Center for Data Science, which focuses on machine learning, and the Department of Linguistics. Sam's research focuses on data, evaluation techniques, and modeling techniques for sentence and paragraph understanding in natural language processing, and on applications of machine learning to scientific questions in linguistic syntax and semantics. Sam organized a twenty-three person research team at JSALT 2018 and received a 2015 EMNLP Best Resource Paper Award, a 2017 Google Faculty Research Award, and a 2019 *SEM Best Paper Award.

Thursday, October 31, 2019 - 10:30

Speaker: Marine Carpuat, University of Maryland
Location: CSE 305
Abstract: While deep neural network models have dramatically improved the quality of machine translation (MT), truly breaking language barriers requires not only translating accurately, but also comparing what is said and how it is said across languages. In this talk, I will argue that modeling divergences from common assumptions about the data used to model machine translation (MT) can not only improve MT, but also help broaden the framing of MT to make it more responsive to user needs. I will first discuss recent work on automatically detecting cross-lingual semantic divergences, which occur when translation does not preserve meaning [Vyas & Carpuat, EMNLP 2019]. Next, I will introduce a training objective for neural sequence-to-sequence models that accounts for divergences between MT model hypotheses and reference human translation [Xu, Niu & Carpuat, NAACL 2019]. Finally, I will argue that translation does not necessarily need to preserve all properties of the input and introduce a family of models that let us tailor translation style while preserving input meaning [Niu, Rao & Carpuat, COLING 2017; Agrawal & Carpuat, EMNLP 2019].

Bio: Marine Carpuat is an Assistant Professor in Computer Science at the University of Maryland. Her research focuses on multilingual natural language processing and machine translation. Before joining the faculty at Maryland, Marine was a Research Scientist at the National Research Council Canada. She received a PhD in Computer Science and a MPhil in Electrical Engineering from the Hong Kong University of Science & Technology, and a Diplome d'Ingenieur from the French Grande Ecole Supelec. Marine is the recipient of an NSF CAREER award, research awards from Google and Amazon, best paper awards at *SEM and TALN, and an Outstanding Teaching Award.

Tuesday, October 22, 2019 - 10:30

Speaker: Yoav Artzi
Location: CSE 305

Abstract: I will present two projects studying the problem of learning to follow natural language instructions. I will present new datasets, a class of interpretable models for instruction following, learning methods that combine the benefits of supervised and reinforcement learning, and new evaluation protocols. In the first part, I will discuss the task of executing natural language instructions with a robotic agent. In contrast to existing work, we do not engineer formal representations of language meaning or the robot environment. Instead, we learn to directly map raw observations and language to low-level continuous control of a quadcopter drone. In the second part, I will propose the task of learning to follow sequences of instructions in a collaborative scenario, where both the user and the system execute actions in the environment and the user controls the system using natural language. To study this problem, we build CerealBar, a multi-player 3D game where a leader instructs a follower, and both act in the environment together to accomplish complex goals.
The two projects were led by Valts Blukis, Alane Suhr, and collaborators. Additional information about both projects is available here:
https://github.com/lil-lab/drif
http://lil.nlp.cornell.edu/cerealbar/

Bio: Yoav Artzi is an Assistant Professor in the Department of Computer Science and Cornell Tech at Cornell University. His research focuses on learning expressive models for natural language understanding, most recently in situated interactive scenarios. He received an NSF CAREER award, paper awards in EMNLP 2015, ACL 2017, and NAACL 2018, a Google Focused Research Award, and faculty awards from Google, Facebook, and Workday. Yoav holds a B.Sc. summa cum laude from Tel Aviv University and a Ph.D. from the University of Washington.

Tuesday, October 15, 2019 - 10:30

Speaker: Mark Riedl
Location: CSE 305

Abstract: Storytelling is a pervasive part of the human experience--we as humans tell stories to communicate, inform, entertain, and educate. In this talk, I will lay out the case for the study of storytelling through the lens of artificial intelligence. I will explore the grand challenge of building an intelligent systems that learn to tell stories. I will specifically look at two challenges pertaining to neural generative processes: control of text generation to achieve goal-driven behavior, and the challenge of maintaining and transferring long-term world knowledge. While both of these challenges are necessary for automated story generation, they also appear in other artificial intelligence and natural language processing tasks as well.

Bio: Dr. Mark Riedl is an Associate Professor in the Georgia Tech School of Interactive Computing and director of the Entertainment Intelligence Lab. Dr. Riedl’s research focuses on human-centered artificial intelligence—the development of artificial intelligence and machine learning technologies that understand and interact with human users in more natural ways. Dr. Riedl’s recent work has focused on story understanding and generation, computational creativity, explainable AI, and teaching virtual agents to behave safely. His research is supported by the NSF, DARPA, ONR, the U.S. Army, U.S. Health and Human Services, Disney, and Google. He is the recipient of a DARPA Young Faculty Award and an NSF CAREER Award.

Wednesday, October 9, 2019 - 12:45

Speaker: Nathan Schneider
Location: CSE 305

Abstract: In most linguistic meaning representations that are used in NLP, prepositions fly under the radar. I will argue that they should instead be put front and center given their crucial status as linkers of meaning—whether for spatial and temporal relations, for predicate-driven roles, or in special constructions. To that end, we have sought to characterize and disambiguate semantic functions expressed by prepositions and possessives in English (Schneider et al., ACL 2018; https://github.com/nertnlp/streusle/), and similar markers in other languages (ongoing work on Korean, Hebrew, German, and Mandarin Chinese). This approach can be broadened to provide language-neutral, lexicon-free semantic relations in structured meaning representation parsing (Prange et al., CoNLL 2019; Shalev et al., DMR 2019).

Bio: Nathan Schneider is an annotation schemer and computational modeler for natural language. As Assistant Professor of Linguistics and Computer Science at Georgetown University, he looks for synergies between practical language technologies and the scientific study of language. He specializes in broad-coverage semantic analysis: designing linguistic meaning representations, annotating them in corpora, and automating them with statistical natural language processing techniques. A central focus in this research is the nexus between grammar and lexicon as manifested in multiword expressions and adpositions/case markers. He has inhabited UC Berkeley (BA in Computer Science and Linguistics), Carnegie Mellon University (Ph.D. in Language Technologies), and the University of Edinburgh (postdoc). Now a Hoya and leader of NERT, he continues to play with data and algorithms for linguistic meaning.

Wednesday, October 9, 2019 - 12:00

Speaker: Vivek Srikumar
Location: CSE 305

Abstract: Today, the most common approach for training neural networks involves minimizing task loss on large datasets. While this agenda has been undeniably successful, we may not have the luxury of annotated data every task or domain. Reducing dependence on labeled examples may require us to rethink how we supervise models. In this talk, I will describe recent work where we use knowledge to inform neural networks without introducing additional parameters. Declarative rules in logic can be systematically compiled into computation graphs that augment the structure of neural models, and also into regularizers that can use labeled or unlabeled examples. I will present experiments on text understanding tasks, which show that such declaratively constrained neural networks are not only more accurate, but also more consistent in their predictions across examples. This is joint work with my students Tao Li, Vivek Gupta and Maitrey Mehta.

Bio: Vivek Srikumar is an assistant professor in the School of Computing at the University of Utah. His research lies in the areas of natural learning processing and machine learning and has primarily been driven by questions arising from the need to reason about textual data with limited explicit supervision and to scale NLP to large problems. His work has been published in various AI, NLP and machine learning venues and received the best paper award at EMNLP 2014. His work has been supported by NSF and BSF, and gifts from Google, Nvidia and Intel. He obtained his Ph.D. from the University of Illinois at Urbana-Champaign in 2013 and was a post-doctoral scholar at Stanford University.

Tuesday, October 1, 2019 - 10:30

Speaker: Sanja Fidler, University of Toronto / NVIDIA
Location: CSE 305
Abstract: The most natural way for an artificial agent to communicate with a human is through language. Language allows an agent to convey what it is seeing, what its internal goals are, ask questions about concepts that it is uncertain about, and possibly engage in a conversation. Similarly, a human can use language to teach an agent new concepts, describe instructions for tasks that the agent should perform, and possibly give feedback to the agent by describing its mistakes. In this talk, I will describe our recent work in this domain.

Bio: Sanja Fidler is an Assistant Professor at the Department of Computer Science, University of Toronto. She joined UofT in 2014. In 2018, she took a role of Director of AI at NVIDIA, leading a research lab in Toronto. Previously she was a Research Assistant Professor at TTI-Chicago, a philanthropically endowed academic institute located in the campus of the University of Chicago. She completed her PhD in computer science at University of Ljubljana in 2010, and was a postdoctoral fellow at University of Toronto during 2011-2012. In 2010 she visited UC Berkeley as a visiting research scientist. She has served as a Program Chair of the 3DV conference, and as an Area Chair of CVPR, ICCV, EMNLP, ICLR, NIPS, and AAAI, and will serve as Program Chair of ICCV'21. She received the NVIDIA Pioneer of AI award, Amazon Academic Research Award, Facebook Faculty Award, and the Connaught New Researcher Award. In 2018 she was appointed as the Canadian CIFAR AI Chair. She has also been ranked among the top 3 most influential AI female researchers in Canada by Re-WORK. Her work on semi-automatic object instance annotation won the Best Paper Honorable Mention at CVPR’17. Her main research interests are scene parsing from images and videos, interactive annotation, 3D scene understanding, 3D content creation, and multimodal representations.

Wednesday, August 7, 2019 - 10:30

Speaker: Peng Qi
Location: Allen 305

Abstract: TBD.

Bio: Peng Qi is a PhD student in Computer Science at Stanford University. His research interests revolve around building natural language processing systems that better bridge between humans and the large amount of (textual) information we are engulfed in. Specifically, he is interested in building knowledge representations, (open-domain) question answering, explainability, and multi-lingual NLP. He is also interested in linguistics, and builds tools for linguistic structure analysis applicable to many languages.

Friday, June 28, 2019 - 15:30

Speaker: Ankur Parikh
Location: Allen 305

Abstract: Despite large advances in neural text generation in terms of fluency, existing generation techniques are prone to hallucination and often produce output that is factually incorrect or structurally incoherent. In this talk, we study this problem from the perspectives of evaluation, modeling, and robustness. We first discuss how existing evaluation metrics like BLEU or ROUGE show poor correlation to human judgement when the reference text diverges from information in the source, a common phenomena in generation datasets. We propose a new metric, PARENT, which aligns n-grams to the source before computing precision and recall, making it considerably more robust to divergence. Next, we discuss modeling, proposing an exemplar-based approach to conditional text generation that aims to leverage training instances to build instance-specific decoders that can more easily capture style and structure. Results on 3 datasets show that our model achieves strong performance and outperforms comparable baselines. Lastly, we discuss generalization of neural generation in non-iid settings, focusing on the problem of zero shot translation — a challenging setup that tests models on translation directions they have not been optimized for at training time. We define the notion of zero-shot consistency and introduce a consistent agreement-based training method that results in a 2-3 BLEU zero shot improvement over strong baselines.

Collaborators: This is joint work with Maruan Al-Shedivat, Bhuwan Dhingra, Hao Peng, Manaal Faruqui, Ming-Wei Chang, William Cohen, and Dipanjan Das.

Bio: Ankur Parikh is a Senior Research Scientist at Google NYC and adjunct assistant professor at NYU. His primary interests are in natural language processing and machine learning. Ankur received his PhD from Carnegie Mellon in 2015 and his B.S.E. from Princeton University in 2009. He has received a best paper runner up award at EMNLP 2014 and a best paper in translational bioinformatics at ISMB 2011.

Thursday, December 13, 2018 - 10:30

Speaker: Aida Nematzadeh
Location: CSE 305

Abstract: Language is one of the greatest puzzles of both human and artificial intelligence (AI). Children learn and understand their language effortlessly; yet, we do not fully understand how they do so. Moreover, although access to more data and computation has resulted in recent advances in AI systems, they are still far from human performance in many language tasks. In my research, I try to address two broad questions: how do humans learn, represent, and understand language? And how can this inform AI? In the first part of my talk, I show how computational modeling can help us understand the mechanisms underlying child word learning. I introduce an unsupervised model that learns word meanings using general cognitive mechanisms; this model processes data that approximates child input and assumes no built-in linguistic knowledge. Next, I explain how cognitive science of language can help us examine current AI models and develop improved ones. In particular, I focus on how investigating human semantic processing helps us model semantic representations more accurately. Finally, I explain how we can use experiments in theory-of-mind to examine question-answering models with respect to reasoning capacity about beliefs.

Bio: Aida Nematzadeh is a research scientist at DeepMind. Previously she was a postdoctoral researcher at UC Berkeley affiliated with the Computational Cognitive Science Lab and BAIR. She received a PhD and an MSc in Computer Science from the University of Toronto. Her research interests lie in the intersection of cognitive science, computational linguistics, and machine learning.