PortNLP - NLP Lab at Portland State: About

Dr. Agrawal presenting her work at CETI

Our lab at Women in Big Data Northwest AI Summit

Panel discussion at CETI

Sina and Dr. Agrawal presenting at NeSy 2025

Pop a Lang.!

Lang. Popped: 0

The PortNLP lab is led by Dr. Ameeta Agrawal.

At PortNLP, we explore new ways to advance language technologies -- from understanding complex texts to generating multilingual summaries. We aim to design systems that are effective, efficient, fair, and human-centered. We envision a future where language technologies are trustworthy and useful in everyday life.

PortNLP started in 2021 with PI and two students focusing on a few specific domains of text summarization and multilingual language models. As we have continued to grow, our past students and present members are contributing to a wide range of topics in natural language understanding and processing.

We are also affiliated with the Coco Lab, a sister research group focused on the intersection of computer science, management, and anthropology.

Research Themes

Language Understanding

Long Context
Ambiguity
Contextual Grounding

Language Generation

Summarization
Multilingual Modeling
Efficient NLP

Human-Centered NLP

Affective Modeling
Conversational Systems
Bias Mitigation

Recent News

October 2025

Accepted at the Findings of IJCNLP-AACL 2025

CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences (Rhitabrat Pokharel, Yufei Tao, Ameeta Agrawal)
MTQ-Eval: Multilingual Text Quality Evaluation for Language Models (Rhitabrat Pokharel, Ameeta Agrawal)

Paper at EPJ Data Science: Dr. Agrawal’s paper, Understanding the Role of Sentiment and Emotion for Predicting Forced Displacement, was recently published in EPJ Data Science. Congratulations!

CCSC-NW: Dr. Agrawal delivered a keynote on “LLMs and the Shifting Landscape of CS Education” during CCSC-NW at Saint Martin’s University College of Business, Engineering, and Technology, sparking great discussion on rethinking computer science education.

September 2025

CETI Event: A huge thank-you to Nandini R. for hosting such an incredible convening at CETI and to all the amazing panelists and audience members for sharing their insights. We’re grateful to be part of such a dynamic community that continues to push the boundaries of building (with) AI (with Ekata Mitra and Yufei Tao).

Invited Talk: On September 13, Prof. Agrawal delivered an invited talk at the AI Institute, Thinking with Machines, hosted by CETI, a local non-profit dedicated to fostering collaborative conversation and experiential learning.

Presented at NeSy 2025: Sina Bagheri Nezhad and Ameeta Agrawal presented their paper Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks at NeSy 2025 on September 10 in Santa Cruz, California. Look out for updates on their presentation and experiences in our next issue!

August 2025

ACL 2025: Russell Scheinberg and Ameeta Agrawal attended ACL 2025 in Vienna, Austria, along with University of Miami collaborator So Young Lee, where they presented their paper Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments.

Accepted at EMNLP 2025:

Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs (Amber Shore, Russell Scheinberg, Ameeta Agrawal, So Young Lee).
MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Hate Speech Multi-hop Explanations (Jackson Trager, Francielle Vargas, Diego Alves, Matteo Guida, Mikel K. Ngueajio, Flor Plaza-del-Arco, Yalda Daryanai, Farzan Karimi-Malekabadi, Ameeta Agrawal)

Presented at ISPE 2025: Andy Dang (PSU/Eli Lilly) presented Benchmarking Large Language Models and Optical Character Recognition to Enhance Network Meta-Analyses (Andy Dang, Ameeta Agrawal, Mingyang Shan).

Mentored NSF REU Program, 2025: Ameeta Agrawal and Ekata Mitra mentored Aniley Garcia at the Summer REU program at Portland State, focusing on code-switched text and bilingual generation in Spanglish.

View All News