kedz Goto Github PK

amr-guidelines

bolt

candidacy-slides

My candidacy exam slides -- currently a WIP. Wil cover automatic summarization: evaluation, extraction, and abstraction.

cluster

cmr2text

Repository for EMNLP paper coming soon!

cmr2txt_data_and_eval

data generated for paper

cnn_pretrain

Pretrain an cnn on unlabeled data.

coherence

columbianlptoolkit

Plan to put help general nlp stuff here someday. Its a fever dream to be sure!

corenlp

A python wrapper for the Stanford CoreNLP java library.

corenlpxmltopython

Reads an xml output file of the Stanford CoreNLP java library and converts it into a more convenient Python class.

cuttsum

Columbia University - Trec 2015 - Temporal Summarization

cv

da

domain adaptation why not

dialog_curriculum

Some ideas on causally motivated curricula for training meaning representation to text models.

disasters

discourse

dlextsum-paper

Paper repository.

duc_preprocess

Library for pre-processing DUC summarization data.

emnlp2020a

Latex and materials for Controllable Meaning Repre.... yeesh I suck at naming papers!

emnlp2020a_slides

Slides for my emnlp 2020 paper.

event

event-parser

Location of all research materials for my event parser.

eventqa

EventQA system originally developed by Shreya Prasad for the DARPA BOLT project at Columbia NLP lab.

high-dim-project

ijcai2016

Repository for ijcai2016 submission code.

ijcai2016-slides

Slides from my IJCAI 2016 presentation

joeynmt

Minimalist NMT for educational purposes

ldax10

Latent Dirichlet Allocation implemented in x10.

learn2sum

Learning2search (LOLS) for multi-document summarization.