The University of British Columbia
The University of British Columbia Vancouver campus
Computer ScienceDr. Vered Shwartz
  • Home
  • Group
  • Research
  • Publications
  • Talks
  • Teaching
  • Contact
  • CV
  • Blog
  • Computer Science /
  • Vered Shwartz /
  • Research
  • Commonsense Reasoning
  • Nonmonotonic Reasoning
  • Computational Semantics

Commonsense Reasoning


robot cutting the branch it's sitting on

We all share basic knowledge and reasoning ability regarding causes and effects, physical commonsense (if you cut the branch you sit on, you will fall), and social commonsense (it's impolite to comment on someone's weight). Endowing machines with such commonsense is challenging. Such knowledge is too vast to collect from humans and often too trivial to be mentioned in texts.

  • ACL 2020 commonsense reasoning tutorial
  • A blog post about commonsense reasoning in NLP
  • I participated in this episode in the TwiML AI podcast and talked about commonsense reasoning in NLP.
  • EMNLP 2021 paper about unsupervised commonsense QA
  • I translated the Winograd Schema Challenge to Hebrew (with name and cultural adaptations): [HTML version] [JSON lines file] 

Nonmonotonic Reasoning


what if?

Everyday causal reasoning requires reasoning about the plausible but potentially defeasible conclusions from incomplete or hypothetical observations. For example, abductive reasoning ("what might explain the current events?"), counterfactual reasoning ("what if?"), and defeasible reasoning ("what might weaken my conclusion?"). I'm working on developing systems capable of nonmonotonic reasoning for a wide range of situations describable in natural language.

  • EMNLP 2021 paper about abductive and counterfactual reasoning
  • Findings of EMNLP 2021 paper about defeasible reasoning

Computational Semantics


if olive oil is made of olives, then that must mean that baby oil...

Lexical variability in human language, i.e. the ability to express the same meaning in various ways, is an obstacle for natural language understanding applications. Word representations excel at capturing topical similarity (elevator/floor), as well as functional similarity (elevator/escalator), but they lack the fine-grained distinction of the specific semantic relation between a pair of words. I developed methods for recognizing lexical semantic relations between words and phrases, including ontological relationships e.g., cat is a type of animal, tail is a part of cat, interpreting noun-compounds, e.g. olive oil is oil made of olives while baby oil is oil for babies and identifying predicate paraphrases, e.g. that X die at Y may have the same meaning as X live until Y in certain contexts.

  • ACL 2016 paper about hypernymy detection
  • CogALex 2016 paper about semantic relation classification
  • NAACL 2018 paper about noun compound interpretation
  • ACL 2018 paper about noun compound interpretation
  • *SEM 2017 paper about predicate paraphrases
  • Findings of EMNLP 2021 paper about paraphrasing



Vered Shwartz
Department of Computer Science
Vancouver Campus
2366 Main Mall, #111
Vancouver, BC Canada V6T 1Z4
Find me on
 
Back to top
The University of British Columbia
  • Emergency Procedures |
  • Terms of Use |
  • Copyright |
  • Accessibility