My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A Dataset for Grounded Video Description

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

A full spaCy pipeline and models for scientific/biomedical documents.

[EMNLP 2018] PyTorch code for TVQA: Localized, Compositional Video Question Answering

Python script which pulls audio from mp4 video and transcribes audio using google speech and cloud storage APIs, returning an srt formatted document and raw text

An open-source NLP research library, built on PyTorch.

Resources, datasets, papers on Question Answering

Everything you need to know for a Software Engineering interview

Library for fast text representation and classification.

🎥 Repository for our ICCV 2017 paper: A Read Write Network for Movie Story Understanding

Models and examples built with TensorFlow

This is the code&dataset for the paper [Hierarchical Memory Networks for Answer Selection on Unknown Words. COLING 2016]

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Natural language processing pipeline for book-length documents (archival Java version; for current Python version, see: https://github.com/booknlp/booknlp)

This repository contains a resurrected and repaired version of OpenEphyra, from https://mu.lti.cs.cmu.edu/trac/Ephyra/wiki/OpenEphyra.

Contains approaches introduced in the MovieQA benchmark dataset paper

TristouNet: Triplet Loss for Speaker Turn Embedding

Oxford Deep NLP 2017 course

Simple Extended BCubed implementation in Python for clustering evaluation

Code and pre-trained model used in ACL 2013 demo paper

CoMingle: Distributed Logic Programming for Decentralized Mobile Ensembles