Luca J. Frost's Projects
Links to conference/journal publications in automated fact-checking (resources for the TACL22 paper).
Citron is an experimental quote extraction system created by BBC R&D
This repository provides the implementation for the paper "Combining Fact Extraction and Verification with Neural Semantic Matching Networks".
Code repo for EMNLP21 paper "Zero-Shot Information Extraction as a Unified Text-to-Triple Translation"
A Dataset for Direct Quotation Extraction and Attribution in News Articles.
Extension of the SentenceSimplification project
A tool for batch loading data files (json, parquet, csv, tsv) into ElasticSearch
Extract embedded metadata from HTML markup
Coreference Resolution, Simplification and Open Relation Extraction Pipeline
A Munch is a Python dictionary that provides attribute-style access (a la JavaScript objects).
Open Information Extraction (OpenIE) and Open Relation Extraction (ORE) papers and data.
revised implementation of openie6
Python Client for OpenSearch
Corpus of Attribution-Annotated news articles covering the campaigns during the year leading up to the 2016 US Presidential election.
Quote extraction for modular journalism (JournalismAI collab 2021)
šÆ sitesniper ~ a lil python package for detecting + extracting domains and URLs from text
Implementation of the ClausIE information extraction system for python+spacy
A library for generating OpenIE tuples from QA pairs (e.g. the SQuAD dataset).
The Plumber framework for KG completion and structured triples extraction
Repo containing code for Towards Data Science articles