KMap
Dr. Surdeanu earned a Ph.D. in Computer Science from Southern Methodist University, Dallas, Texas, in 2001. He has more than 15 years of experience in building systems driven by natural language processing (NLP) and machine learning. His experience spans both academia (Stanford University, University of Arizona) and industry (Yahoo! Research and two NLP-centric startups). During his career he published more than 80 peer-reviewed articles, including two articles that were among the top three most cited articles at two different NLP conferences. He was a leader or member of teams that ranked in the top three at seven highly competitive international evaluations of end-user NLP systems such as question answering and information extraction. His work was funded by several government organizations (DARPA, NIH), as well as private foundations (the Allen Institute for Artificial Intelligence, the Bill & Melinda Gates Foundation).

VOSviewer

Courses
  • SFIA
    Statistical Foundations for the Information Age

  • ANLP
    Algorithms for Natural Language Processing

  • SNLP
    Statistical Natural Language Processing

  • ANLP
    Applied Natural Language Processing

  • ATCI
    Advanced Topics in Computational Intelligence

Grants
  • Funding agency logo
    SKEMA: Scientific Knowledge Extraction and Model Analysis

    Co-Investigator (COI)

    2022

    $1.5M
    Active
  • Funding agency logo
    DASS: A Framework for Accountable Smart Contracts Wills

    Co-Investigator (COI)

    2022

    $748.3K
    Active
  • Funding agency logo
    HEURISTICS: Hyperlocal Elicitation and Understanding of Risks to Stability In Complex Systems

    Principal Investigator (PI)

    2021

    $428.4K
    Active
  • Funding agency logo
    III: Small: Accessible and Interpretable Machine Reading Methods for Extracting Structured Information from Text

    Principal Investigator (PI)

    2020

    $499.9K
    Active
  • Funding agency logo
    III: Small: Collaborative Research: Explainable Natural Language Inference

    Co-Investigator (COI)

    2018

    $262.5K
    Active
  • Funding agency logo
    AutoMATES: Automated Model Assembly from Text, Equations, and Software

    Co-Investigator (COI)

    2018

    $2.2M
  • Funding agency logo
    An Automated Scientific Discovery Framework (ASDF) for Mechanistic Reasoning Across Complex Data

    Principal Investigator (PI)

    2018

    $307.4K
  • Funding agency logo
    GRASP: Global Reading and Assembly for Semantic, Probabilistic World Models

    Principal Investigator (PI)

    2017

    $9.6M
  • Funding agency logo
    GRASP: Global Reading and Assembly for Semantic, Probabilistic World Models

    Principal Investigator (PI)

    2017

    $1.1M
  • Funding agency logo
    Enabling Large-Scale Research on Autism Spectrum Disorders through Automated Processing of EHR Using Natural Language Understanding

    Co-Investigator (COI)

    2017

    $292.4K
Technologies / Patents
      News
      • Grant to Fund Development of Socially Savvy Artificial Intelligence

        2020

      • AI Explained as 'Intelligence Augmentation'

        2018

      • Machines as Co-Workers: A New Era Is Upon Us

        2018

      • Tucson Festival of Books to Celebrate 10th Anniversary

        2018

      • 'Humans, Data and Machines' Is Theme of UA Science Series

        2018

      • Fiscal Year Closes With Continued Momentum for Tech Launch Arizona

        2017

      • Startup Licenses UA-Invented Language Processing Algorithm

        2017

      • Raising Computers to Be Good Scientists

        2015

      • Do You Need a Junk-Food Intervention?

        2014

      Publications (105)
      Recent
      • How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks

        2021

      • Explainable Multi-hop Verbal Reasoning Through Internal Monologue

        2021

      • Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification

        2021

      • Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering

        2021

      • Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractor with an Explanation Decoder

        2021

      • Data and Model Distillation as a Solution for Domain-transferable Fact Verification

        2021

      • Cheap and good? simple and effective data augmentation for low resource machine reading

        2021

      • If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering

        2021

      • Parsing as Tagging

        2020

      • Having Your Cake and Eating it Too: Training Neural Retrieval for Language Inference without Losing Lexical Match

        2020

      • Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?

        2020

      • Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder

        2020

      • An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification

        2020

      • An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource Scenarios

        2020

      • Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering

        2020

      • Eidos, INDRA, \ Delphi: From Free Text to Executable Causal Models

        2019

      • Lightly Supervised Representation Learning with Global Interpretability

        2019

      • University of Arizona at SemEval-2019 Task 12: Deep-Affix Named Entity Recognition of Geolocation Entities

        2019

      • Alignment over Heterogeneous Embeddings for Question Answering

        2019

      • What does the language of foods say about us?

        2019

      • Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods

        2019

      • Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering

        2019

      • Semi-Supervised Teacher-Student Architecture for Relation Extraction

        2019

      • On the Importance of Delexicalization for Fact Verification

        2019

      • Exploration of Noise Strategies in Semi-supervised Named Entity Classification

        2019

      • Visual Supervision in Bootstrapped Information Extraction

        2018

      • Text Annotation Graphs: Annotating Complex Natural Language Phenomena

        2018

      • Sanity Check: A Strong Alignment and Information Retrieval Baseline for Question Answering

        2018

      • A Study of Calorie Estimation in Pictures of Food

        2018

      • Detecting Cyber Threats in Non-English Dark Net Markets: A Cross-Lingual Transfer Learning Approach

        2018

      • Controlling Information Aggregation for Complex Question Answering

        2018

      • A Test of The Risk Perception Attitude Framework as a Message Tailoring Strategy to Promote Diabetes Screening

        2018

      • Large-scale Automated Machine Reading Discovers New Cancer Driving Mechanisms

        2018

      • Keep your bearings: Lightly-supervised Information Extraction with Ladder Networks that avoids Semantic Drift

        2018

      • Grounding Gradable Adjectives through Crowdsourcing

        2018

      • MLStar: Machine Learning in Energy Profile Estimation of Android Apps

        2017

      • Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph

        2017

      • A scaffolding approach to coreference resolution integrating statistical and rule-based models

        2017

      • Focused Reading: Reinforcement Learning for What Documents to Read

        2017

      • Large-scale automated reading with Reach discovers new cancer driving mechanisms

        2017

      • Learning what to read: Focused machine reading

        2017

      • Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification

        2017

      • Creating Causal Embeddings for Question Answering with Minimal Supervision

        2016

      • An Investigation of Coreference Phenomena in the Biomedical Domain

        2016

      • Towards Using Social Media to Identify Individuals at Risk for Preventable Chronic Illness

        2016

      • Odin’s Runes: A Rule Language for Information Extraction

        2016

      • SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction

        2016

      • What's in an Explanation? Characterizing Knowledge and Inference Requirements for Elementary Science Exams

        2016

      • Framing QA as Building and Ranking Intersentence Answer Justifications

        2016

      • This before That: Causal Precedence in the Biomedical Domain

        2016

      • Diamonds in the Rough: Event Extraction from Imperfect Microblog Data

        2015

      • Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering

        2015

      • Two Practical Rhetorical Structure Theory Parsers

        2015

      • A Domain-independent Rule-based Framework for Event Extraction

        2015

      • Higher-order Lexical Semantic Models for Non-factoid Answer Reranking

        2015

      • Event Extraction Using Distant Supervision

        2014

      • Discourse Complements Lexical Semantics for Non-factoid Answer Reranking

        2014

      • On the Importance of Text Analysis for Stock Price Prediction

        2014

      • The Stanford CoreNLP Natural Language Processing Toolkit

        2014

      • Extracting Latent Attributes from Video Scenes Using Text as Background Knowledge

        2014

      • Analyzing the Language of Food on Social Media

        2014

      • Removing noisy mentions for distant supervision

        2013

      • Overview of the English Slot Filling Track at the TAC2014 Knowledge Base Population Evaluation

        2013

      • Bayesian modeling of scenes and captions.

        2013

      • Overview of the TAC2013 Knowledge Base Population Evaluation: English Slot Filling and Temporal Slot Filling

        2013

      • Identifying patent monetization entities

        2013

      • Selectional preferences for semantic role classification

        2013

      • Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules

        2013

      • Transmitting Narrative: An Interactive Shift-Summarization Tool for Improving Nurse Communication

        2013

      • Combining joint models for biomedical event extraction.

        2012

      • Joint entity and event coreference resolution across documents

        2012

      • Multi-instance multi-label learning for relation extraction

        2012

      • Risk analysis for intellectual property litigation

        2011

      • Learning to rank answers to non-factoid questions from web collections

        2011

      • Event extraction as dependency parsing

        2011

      • A multi-pass sieve for coreference resolution

        2010

      • Improving semantic role classification with selectional preferences

        2010

      • Ensemble Models for dependency parsing: Cheap and good?

        2010

      • The CoNLL-2009 shared task: Syntactic and semantic dependencies in multiple languages

        2009

      • Company-oriented extractive summarization of financial news

        2009

      • Learning to rank answers on large online QA collections

        2008

      • DeSRL: A linear-time semantic role labeling system

        2008

      • Cache-aware load balancing for question answering

        2008

      • Analysis of joint inference strategies for the semantic role labeling of Spanish and Catalan

        2008

      • Robust question answering for speech transcripts using minimal syntactic analysis

        2008

      • The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies

        2008

      • A multi-layer collaborative cache for question answering

        2007

      • Combination strategies for semantic role labeling

        2007

      • A comparison of statistical and rule-induction learners for automatic tagging of time expressions in English

        2007

      • Design and performance analysis of a factoid question answering system for spontaneous speech transcriptions

        2006

      • Projective dependency parsing with perceptron

        2006

      • A robust combination strategy for semantic role labeling

        2005

      • A hybrid unsupervised approach for document clustering

        2005

      • TALP-UPC at TREC 2005: Experiments using a voting scheme among three heterogeneous QA systems

        2005

      • The TALP-QA system for Spanish at CLEF 2004: Structural and hierarchical relaxing of semantic constraints

        2005

      • Semantic role labeling using complete syntactic analysis

        2005

      • Named entity recognition from spontaneous open-domain speech

        2005

      • On the role of information retrieval and information extraction in question answering systems

        2003

      • Performance issues and error analysis in an open-domain question answering system

        2003

      • Performance analysis of a distributed question/answering system

        2002

      • Design and performance analysis of a distributed Java Virtual Machine

        2002

      • Distributed Java virtual machine for message passing architectures

        2000

      Grants
      Citations
      H-Index
      Patents
      News
      Books
      Opportunities