Invited Speakers - Clic2021

DAN ROTH

Dan Roth is the Eduardo D. Glandt Distinguished Professor at the Department of Computer and Information Science, University of Pennsylvania, an Amazon Scholar, and a Fellow of the AAAS, the ACM, AAAI, and the ACL. In 2017 Roth was awarded the John McCarthy Award, the highest award the AI community gives to mid-career AI researchers. Roth was recognized “for major conceptual and theoretical advances in the modeling of natural language understanding, machine learning, and reasoning.” Roth has published broadly in machine learning, natural language processing, knowledge representation and reasoning, and learning theory, and has developed advanced machine learning based tools for natural language applications that are being used widely. Until February 2017 Roth was the Editor-in-Chief of the Journal of Artificial Intelligence Research (JAIR). He was the program chair of ACL, AAAI and CoNLL, and is the Conference Chair of NAACL-22. Roth has been involved in several startups; most recently he was a co-founder and chief scientist of NexLP, a startup that leverages the latest advances in Natural Language Processing (NLP), Cognitive Analytics, and Machine Learning in the legal and compliance domains. NexLP was acquired by Reveal in 2020. Prof. Roth received his B.A Summa cum laude in Mathematics from the Technion, Israel, and his Ph.D. in Computer Science from Harvard University in 1995.

It’s Time to Reason

The fundamental issue underlying natural language understanding is that of semantics – there is a need to move toward understanding natural language at an appropriate level of abstraction in order to support natural language understanding and communication with computers. Machine Learning has become ubiquitous in our attempt to induce semantic representations of natural language and support decisions that depend on it; however, while we have made significant progress over the last few years, it has focused on classification tasks for which we have large amounts of annotated data. Supporting high level decisions that depend on natural language understanding is still beyond our capabilities, partly since most of these tasks are very sparse and knowledge-intensive, and generating supervision signals for it does not scale. I will discuss some of the challenges underlying reasoning – making natural language understanding decisions that depend on multiple, interdependent, models, and exemplify it mostly using the domain of Reasoning about Time, as it is expressed in natural language.

BARBARA PLANK

Barbara Plank is Professor in the Computer Science Department at ITU (IT University of Copenhagen). She is also the Head of the Master in Data Science Program. She received her PhD in Computational Linguistics from the University of Groningen. Her research interests focus on Natural Language Processing, in particular transfer learning and adaptations, learning from beyond the text, and in general learning under limited supervision and fortuitous data sources. She (co)-organised several workshops and international conferences, amongst which the PEOPLES workshop (since 2016) and the first European NLP Summit (EurNLP 2019). Barbara was general chair of the 22nd Northern Computational Linguistics conference (NoDaLiDa 2019) and workshop chair for ACL in 2019. Barbara is member of the advisory board of the European Association for Computational Linguistics (EACL) and vice-president of the Northern European Association for Language Technology (NEALT).

Returning the L in NLP: Why Language (Variety) Matters and How to Embrace it in Our Models

NLP’s success today is driven by advances in modeling together with huge amounts of unla- beled data to train language models. However, for many application scenarios like low-resource languages, non-standard data and dialects we do not have access to labeled resources and even unlabeled data might be scarce. Moreover, evaluation today largely focuses on standard splits, yet language varies along many dimensions. What is more is that for almost every NLP task, the existence of a single perceived gold answer is at best an idealization. In this talk, I will emphasize the importance of language variation in inputs and outputs and its impact on NLP. I will outline ways on how to go about it. This includes recent work on how to transfer models to low-resource languages and language variants, the use of incidental (or fortuitous) learning signals such as genre for dependency parsing and learning beyond a single ground truth.