Dr. Agrawal presenting her work at CETI
Dr. Agrawal presenting her work at CETI
Our lab at Women in Big Data Northwest AI Summit
Our lab at Women in Big Data Northwest AI Summit
Panel discussion at CETI
Panel discussion at CETI
Sina and Dr. Agrawal presenting at NeSy 2025
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

August 2026

Internship 💼: Congratulations to Rhitabrat for completing his summer internship as an AI Scientist Intern at Cambia Health Solutions, working on evaluation, robustness, reliability, and calibration of LLM-based systems.
Invited talk🎤 : Dr. Agrawal gave an invited talk to Oregon’s Data Equity Committee, with 80+ attendees, on AI equity, reliability and trustworthiness, when to trust—and not trust—current AI, and considerations for responsible public-sector adoption, including sustainability.
Paper Accepted : 🎉 Our paper Choosing the Right Language Mode at Inference Time for Multilingual Reliability was accepted to EMNLP 2026 Findings. Congratulations to Ekata and Ameeta.
Award🏆: Our survey Engagingness in Open-Domain Dialogue Systems: A Systematic Survey of Datasets, Metrics and Methods was recognized as one of ACRT journal’s Top 5 Rising Star papers of 2025. Congratulations to Ekata, Amila, and Ameeta. Read the paper.

July 2026

ACL 2026: 🌴 PortNLP celebrates at ACL 2026!
  • Amber presented at the CRAC Workshop.
  • Yufei presented our NWCAD work at ACL Findings.
  • Bisi presented ThreadSumm at ACL Main.
  • PortNLP also hosted an affinity session, bringing together researchers from across the Pacific Northwest.

June 2026

Presentations: Malini had a busy summer with back-to-back presentations 🎤.
  • NAIRR Pilot Workshop: Many congratulations to Malini on presenting at the NAIRR Pilot Workshop, Orlando, FL, June 18–19, 2026. Talk: “Teaching AI Where It’s Hardest: Deploying LLM-Based Tutors in Rural and Resource-Constrained Settings.” 🎤
  • AI Unlocked / NAIRR Workshop: Many congratulations to Malini on presenting at the AI Unlocked / NAIRR Workshop, Denver, CO, June 2–3, 2026. Talk: “A Reproducible Evaluation Scaffold for LLM-Assisted Computer Science Education.” 🎤
  • ASEE 2026: Many congratulations to Malini again on presenting at ASEE 2026, Charlotte, NC, June 21–24, 2026. Talk: “Diagnosing CS1 Misconceptions with LLMs: A Pilot Study on Alignment, Variability, and Prompt Sensitivity.” 🎤
View All News

Sponsors

This webpage, "PortNLP", is adapted from Research Group Web Site Template by Sampa, used under CC BY 4.0.