ML Pacheco - Academic Webpage

Maria Leonor Pacheco
CS Department - Purdue University
Advisor: Prof. Dan Goldwasser
pachecog [at] purdue [dot] edu
mlpacheco
google scholar
CV

I am a PhD. candidate in Computer Science at Purdue University, where I work with Dr. Dan Goldwasser as part of the Purdue Natural Language Processing Group. My current research focuses broadly on neural-symbolic methods to model natural language discourse. I am interested in applications that can benefit from the integration of structured human knowledge and large-scale language analysis. Most of my previous work is in analyzing conversations, argumentation, and narratives by modeling the textual content, the discourse structure, and their social context. Whenever appropriate, I connect these analyses with relevant conceptual frameworks.

I am also actively involved in interdisciplinary collaborations with the Network and Dependable Systems and Security Lab at Northeastern University. This work focuses on leveraging NLP for network security.

📢 I’m on the job market! 📢 Please reach out if you think I’d be a good fit for your academic department or research group.

News

Dec, 2021 Our tutorial on Neuro-Symbolic Methods for NLP has been accepted to appear at COLING 2022! This is a joint effort with Sean Welleck, Dan Goldwasser, Vivek Srikumar, Yeijin Choi and Dan Roth
Dec, 2021 Our paper on "Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents", a collaboration with NDS2 at Northeastern, was accepted to IEEE S&P 2022!
Aug, 2021 Our paper on "Identifying Morality Frames in Political Tweets Using Relational Learning" was accepted to EMNLP 2021
Jun, 2021 Dr. Goldwasser and I will be leading a tutorial on Neural-Symbolic Modeling for NLP at IJCAI 2021 on August 20, 1:00 pm EDT
May, 2021 Honored to receive the 2021 Microsoft Research Dissertation Grant!
Apr, 2021 I will present our TACL paper "Modeling Content and Context with Deep Relational Learning" at NAACL 2021!

Publications

Refereed Journals and Conferences (* Indicates co-first authorship)

Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents

ML Pacheco, M von Hippel, B Weintraub, D Goldwasser, C Nita-Rotaru
In IEEE Symposium on Security and Privacy, IEEE S&P 2022.

[Pre-Print] [Code]

Identifying Morality Frames in Political Tweets Using Relational Learning

S Roy, ML Pacheco, D Goldwasser
In Empirical Methods in Natural Language Processing, EMNLP 2021.

[Paper] [Code]

Modeling Content and Context with Deep Relational Learning

ML Pacheco, D Goldwasser
In Transactions of the Association for Computational Linguistics, TACL 2021.
Presented at NAACL 2021

[Paper] [Code] [Slides]

Modeling Human Mental States with an Entity-based Narrative Graph

IT Lee, ML Pacheco, D Goldwasser
In North American Chapter of the Association for Computational Linguistics, NAACL 2021.

[Paper] [Code]

Randomized Deep Structured Prediction for Discourse-level Processing

M Widmoser*, ML Pacheco*, J Honorio, D Goldwasser
In European Chapter of the Association for Computational Linguistics, EACL 2021.
Also presented at the EMNLP 2020 Workshop on Structured Prediction for NLP

[Paper] [Poster] [Code]

Weakly-Supervised Modeling of Contextualized Event Embedding for Discourse Relations

IT Lee, ML Pacheco, D Goldwasser
In Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2020.

[Paper] [Code]

Identifying Collaborative Conversations using Latent Discourse Behaviors

A Jain, ML Pacheco, S Lancette, M Goindani, D Goldwasser
In ACL Special Interest Group on Discourse and Dialogue, SIGDIAL 2020.

[Paper] [Slides] [Code]

Leveraging Textual Specifications for Grammar-based Fuzzing of Network Protocols

S Jero, ML Pacheco, D Goldwasser, C Nita-Rotaru
In Innovative Applications of Artificial Intelligence, IAAI 2019.

[Paper] [Slides] [Code]

Adapting Event Embeddings for Implicit Discourse Relations

ML Pacheco, IT Lee, X Zhang, AK Zehady, P Daga, D Jin, A Parolia, D Goldwasser
In Computational Natural Language Learning, CoNLL Shared Task 2016.

[Paper] [Poster] [Code]

Refereed Workshops (* Indicates co-first authorship)

Neural-Symbolic Modeling for Natural Language Discourse

ML Pacheco, D Goldwasser
ICML 2020 Workshop on Bridge Between Perception and Reasoning

[Paper] [Poster]

Leveraging Representation and Inference through Deep Relational Learning

ML Pacheco, I Dalal, D Goldwasser
NeurIPS 2018 Workshop on Relational Representation Learning

[Paper] [Poster]

Predicting Semantic Textual Similarity with Paraphrase and Event Embeddings

IT Lee, M Goindani, C Li, D Jin, K Johnson, X Zhang, ML Pacheco, D Goldwasser
In International Workshop on Semantic Evaluation, SemEval 2017

[Paper] [Poster]

Introducing DRaiL: A Step Towards Declarative Deep Relational Learning

X Zhang*, ML Pacheco*, C Li, D Goldwasser
EMNLP 2016 Workshop on Structured Prediction for NLP

[Paper] [Poster]

Teaching

Purdue University
- CS180 - Problem Solving and Object Oriented Programming - Instructor and Head TA (Summer 2016, Fall 2016)
- CS180 - Problem Solving and Object Oriented Programming - Graduate TA (Fall 2015, Spring 2016)

Academic and Instutional Service

Student Research Workshop Co-Chair, NAACL 2022
Reviewer for ACL Rolling Review, EMNLP 2021, ACL 2021, NAACL 2021, AAAI 2021, ACM Computing Surveys
Social Media Co-Chair, SIGDIAL 2021
Computer Science Representative, Graduate Women in Science Programs, Purdue University (2021-2022)
Diversity Chair, CS Graduate Student Board, Purdue University (2020-2021)
Graduate Student Representative, CS Department Diversity Task Force, Purdue University (2020-2021)
Global Ambassador, Purdue Graduate School (2018-2021)