Currently looking for full-time job opportunities!
My name is Evangelia Spiliopoulou and I am a Ph.D. candidate in NLP advised by Eduard Hovy. I am studying at
Language Technologies Institute, Carnegie Mellon University.
My research focuses on the study of events and their outcomes, specifically targeted in low-resource or real-time
scenarios. I am interested on the modeling / representation aspect; how can we take full advantage of what we
already know (e.g., through LLMs) to solve problems in zero- or few-shot scenarios.
2021-11-10 Our paper in collaboration with Dataminr: "A Novel Framework for Detecting Important Subevents from Crisis Events via Dynamic Semantic Graphs"
was accepted at W-NUT, EMNLP 2021!
2021-05-13 I passed my Thesis Proposal, under the title Modeling Event Implications via Multi-faceted Entity Representations!
Many thanks to my committee for their valuable feedback: Yonatan Bisk, Lori Levin and Alan Ritter.
2020-12-08 Presenting our work on Definition Frames at COLING'2020!
2020-09-14 Our work on Event-Specific Bias Removal was accepted at EMNLP Findings!
2020-05-25 Excited to start my internship with Dataminr!
Selected Research Projects
Event Implications
Current project, Thesis
How do events impact an entity’s state?
How can we teach LLMs what to learn, and apply it in unseen entities?
Detecting important sub-events from large-scale crisis events
Completed in May 2021, internship with Dataminr
Detect sub-events from social media that may help in humanitarian aid efforts
Information is scattered across multiple posts, need to aggregate & combine
Importance of temporality and sub-event dependencies (i.e., each sub-event is dependent,
on other sub-events)
Event-Specific Bias Removal
Completed in May 2020
Detect critical tweets in real-time crisis scenarios
No data for the current event, few previous events of similar nature annotated
Data bias problem: use adversarial techniques to retain only the useful information for the task
Definition Frames
Completed in March 2020
Design explainable entity representations via the use of definitions
Representations with structure help us identify which information is important: less data needed
Other Projects
World Modelers, Sofia
Funded by DARPA, Advisor: Eduard Hovy
Design & Implementation of SOFIA (code) and Project Management
Detect causal links & events from noisy documents, real-time
SAFT, DAFT
Funded by DARPA, Advisor: Eduard Hovy
Detecting events & arguments from news articles
System integration for extraction of entities, relations, events and
sentiments into ColdStart++ KBs
Final report and code
Relation Extraction & Classification
Class Project, Fall 2017
Relation Extraction from scientific publications on NLP (SemEval 2018, task 7)
Multi-genre Natural Language Inference
Class Project, Fall 2017
Classify sentence pairs as Inference/Contradiction/Neutral (multi-NLI corpus)
Linguistic Markers of Influence
Class Project, Spring 2017
Classify sentence pairs as Inference/Contradiction/Neutral (multi-NLI corpus)
Document Clustering
Class Project, Fall 2017
Using automatically extracted events as features to cluster documents according to topic (ECB+ dataset)
Health Insurance Analytics
Funded by MetLife, Advisor: Anatole Gershman
Anomaly detection on health insurance data based on medical history, diagnosis & patient self-reports
Goal was to detect insurance fraud from disability claims
Information Extraction for Biologically-Inspired Design
Design & Intelligence Lab, Georgia Tech, Advisor: Ashok Goel
Extract information from biology papers in the form of knowledge graphs
Knowledge graphs used for biologically-inspired design
Effort to commercialize our application in finance sector, via the NSF i-Corps program
Publications
* = equal contribution
2021
SD^2G: A Novel Framework for Detecting Important Subevents from Crisis Events via Dynamic Semantic Graphs.
In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021).
Evangelia Spiliopoulou, Tanay K. Saha, Joel Tetreault, Alejandro Jaimes.
PDF
2020
Event-Related Bias Removal for Real-time Disaster Events.
In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings.
Evangelia Spiliopoulou*, Salvador Medina Maza*, Eduard Hovy, Alexander Hauptmann.
PDF &
Code/Data
Definition Frames: Using Definitions for Hybrid Concept Representations
In Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020).
Evangelia Spiliopoulou, Artidoro Pagnoni and Eduard Hovy.
PDF &
Code/Data
2017
Event Detection Using Frame-Semantic Parser.
In Proceedings of the Events and Stories in the News Workshop.
Evangelia Spiliopoulou, Eduard Hovy and Teruko Mitamura.
PDF &
Code/Data
Linguistic Markers of Influence in Informal Interactions.
In Proceedings of the Second Workshop on NLP and Computational Social Science.
Choudhary S., Prabhumoye S.,
Evangelia Spiliopoulou, Bogart C., Rose C. and Black A., W.
PDF
Last updated Nov 16th 2021