brmson's repositories
dataset-sts
Semantic Text Similarity Dataset Hub
dataset-factoid-webquestions
WebQuestions QA Benchmarking Dataset
Sentence-selection
Answer Sentence Selection using Deep Learning
dataset-factoid-curated
A curated question answering research dataset of factoid questions
Personal-Assistant
Household Intelligent Assistant
label-lookup
Stand-alone service for fuzzy lookup of string labels of resources
Deep-Learning-for-NLP-Resources
List of resources to get started with Deep Learning for NLP.
dataset-factoid-movies
A question answering research dataset of movie-related factoids
dawg-levenshtein
Fuzzy search
qasurvey-paper
A scientific survey in state-of-art Question Answering
YodaQA-client
HTML5 mobile client for YodaQA
YodaQA-twitter-bot
Twitter bot for YodaQA
wikipedia-extractor
Extracts and cleans text from Wikipedia database dump and stores output in a number of files of similar size in a given directory. This is a mirror of the script by Giuseppe Attardi.
aristo-chios
Chios was our framework for the Paul Allen Kaggle AI challenge for Aristo
jobimservice
RESTful API for querying JoBimText
tweetmotif
Topical search for Twitter. See twokenize.py, emoticons.py for tokenization.
LiveQAServerDemo
Demo server for TREC LiveQA competition
numberLabeller
Label numbers in text corpora for a dataset to train a numeric NER
paper-poster2015
Our paper published at POSTER2015
synonyms-pccp
Compute Czech word synonyms based on distributional semantics