Welcome to The NLP Lab Pages

The Natural Language Processing Lab (NLP-Lab) is focused on theoretical work and implementations of Natural Language Processing (NLP) and Artificial Intelligence (AI) solutions using hybrid approaches, empiricist, neural, probabilistic, and knowledge-driven, with a particular interest in neuro-symbolic modeling. We are also strongly interested in Quantum NLP and NLP combined with Machine Learning (ML) solutions for computer vision and multi-modal information processing.

The NLP-Lab is located at Indiana University at Bloomington. While it is mainly a local group of students and researchers with a strong interest in NLP and AI here in Indiana, it has ties to colleagues all across the country.

During summer 2023 we meet every week in Luddy Hall 0002 every Wednesday 4-6 PM. (See Teams and email announcements for more details.)

• Publications
• Software
• Data
• Projects

Research Foci

During the 2023/2024 academic year the focus is on:

• Ellipsis and Empty Element Parsing
• Discontinuity and Non-local Dependency Processing in Natural Language Discourse
• Time and Event Annotation and NLP Technologies (TIE-ML)
• Knowledge Graph extraction and visualization from relational databases, unstructured text, and images/videos
• Entailment and Reasoning over Knowledge Graphs (and Description Logic/Semantic Web): Using Temporal Graph Neural Networks and Knowledge Graphs.

In all these projects we work on hands-on implementation of technologies, utilizing programming languages like Python and Rust, and graph or RDF libraries, as well as common graph-database systems like Apache Jena, oxigraph, AllegroGraph, GraphDB, or Neo4j.

See for example:

• NLP-Lab’s Rust material
• NLP-Lab’s Python material

If you are interested in joining our Rust tutorials with a focus on using Rust for NLP and AI or in Robotics environments (with the [Robot Operating System] (ROS)), please get in touch!

Previous projects foci:

• 2023 Datathon and Hackathon on Antisemitic and hate speech, using NLP and Machine Learning to process social media posts.
• Language Resources for Turkic Languages - Focusing on Azerbaijani
• Processing of the Mueller Report: corpus analysis, prediction models, Knowledge Graph and Event Graph extraction, time reference and sequencing along the time axis (GitHub repo). The cleaned-out text corpus with basic annotations is finally available. More data coming soon.
• Antisemitism in Social Media
• I was organizing special meetings to refresh our knowledge of Lisp and Prolog for logic computation and reasoning, in particular, related to computational semantics and pragmatics, and probabilistic logic, integrating Semantic Web and Knowledge Graph technologies. See here… but the pandemic interfered with that. We should talk about a continuation. Please get in touch, if you are interested in Lisp / Scheme / Prolog.

Team

• Dr. Damir Cavar
• Andrew Davis
• Aravind Dendukuri
• Shreeja Deshpanbe
• Billy Dickson
• Matthew Fort
• Vance Holthenrichs
• Soyoung Kim
• Ludovic Mompelat
• Harshwardhan Raghunath Patil
• Dr. Zoran Tiganj

Former Team Members

• Aarnav
• Dr. Ali Abdulaziz Aljubailan
• Oren Baldinger
• Abhishek Babuji
• Rohit Bapat
• Aarushi Bisht
• Rushabh Dharia
• Josephine Douglas
• Boli Fang
• Maanvitha Gongalla
• Peace Han
• Murali Kishore Varma Kammili
• Anurag Kumar
• Mahesh Latnekar
• Shujun Liu
• Dr. Anthony Meyer
• Umang Mehta
• Shreejith Panicker
• Chaitanya Patil
• Dr. Falcon Dario Restrepo Ramos
• Animesh Sagar
• Gopal Seshadri
• Jagpreet Singh Chawla
• Surya Prateek Soni
• Ashutosh Tiwari
• Dr. Yuna Won
• Kimball Wu
• Yiwen Zhang

Here is our Event Calendar with all meeting times.