Greg Durrett

berkeley-doc-summarizer. The Berkeley Document Summarizer is a learning-based, single-document summarization system that extracts source document content, exploits syntactic information to compress it, and uses coreference constraints to ensure clarity.

berkeley-entity. The Berkeley Entity Resolution System jointly solves the problems of named entity recognition, coreference resolution, and entity linking with a feature-rich discriminative model.

fp-dataset-artifacts. Final project starter code for NLP classes at UT Austin: provides a HuggingFace trainer to enable studying of dataset artifacts.

nlp-qa-finalproj. Final project starter code for the question answering final project, for Natural Language Processing at UT Austin

nyu-llm-reasoners-a1. Assignment 1 for CSCI-GA.3033-131 · DS-GA.3001-009 Building LLM Reasoners at NYU.

naacl13-morph. Code for the NAACL 2013 paper "Supervised Learning of Complete Morphological Paradigms"