84 open source projects by allenai

Given a scholarly PDF, extract figures, tables, captions, and section titles.

Code associated with the Don't Stop Pretraining ACL 2020 paper

S2ORC: The Semantic Scholar Open Research Corpus: https://www.aclweb.org/anthology/2020.acl-main.447/

Officially supported AllenNLP models

A collaborative platform for rapid and reproducible research.

KnowBert -- Knowledge Enhanced Contextual Word Representations

Code for the AllenNLP demo.

Variational Methods for Pretraining in Resource-limited Environments

UnifiedQA: Crossing Format Boundaries With a Single QA System

A citation recommendation system that allows users to find relevant citations for their paper drafts. The tool is backed by Semantic Scholar's OpenCorpus dataset.

An open source framework for research in Embodied-AI from AI2.

Science-parse version 2

Learning to Learn how to Learn: Self-Adaptive Visual Navigation using Meta-Learning (https://arxiv.org/abs/1812.00971)

Discovering Neural Wirings (https://arxiv.org/abs/1906.00586)

interactive explorer for language models

Tensorflow implementation of contextualized word representations from bi-directional language models

LM Pretraining with PyTorch/TPU

Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.

A simple example for how to build your own model using AllenNLP as a dependency.

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

Command line tool to extract figures, tables, and captions from scholarly documents in PDF form.

With alexafsm, developers can model dialog agents with first-class concepts such as states, attributes, transition, and actions. alexafsm also provides visualization and other tools to help understand, test, debug, and maintain complex FSM conversations.

Aristo mini is a light-weight question answering system that can quickly evaluate Aristo science questions with an evaluation web server and the provided baseline solvers.

Companion code to the paper "Extracting Scientific Figures with Distantly Supervised Neural Networks" 🤖

A tool for visualizing trees, tailored specifically to the analysis of parse trees.

A framework for building semantic parsers (including neural module networks) with AllenNLP, built by the authors of AllenNLP

Longformer: The Long-Document Transformer

Question Answering via Integer Programming (TableILP)

TuffyLite is an open-source MLN inference engine that modifies the original Tuffy solver.

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

A BERT model for scientific text.

ImageNet classification using binary Convolutional Neural Networks

A companion repository for the "Writing code for NLP Research" Tutorial at EMNLP 2018

An open-source platform for Visual AI.

A deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too)

Science Parse parses scientific papers (in PDF form) and returns them in structured form.

Data and code for Kang et al., NAACL 2018's paper titled "A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications"

Quality information extraction at web scale. Edit

A mini-framework for running AI2-Thor with Docker.

Converter from UD-trees to BART representation

Repository for NAACL 2019 paper on Citation Intent prediction

Combining Distant and Direct Supervision for Neural Relation Extraction

The official code for PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization

static-dir files for a simple-server demo with ReactJS visualizations

WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Relevant code for the "Show Your Work" paper, EMNLP 2019.

ARC Question Solvers