RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.

Aqueduct is no longer being maintained. Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure.

A functional standard library for Python.

Cornell Semantic Parsing Framework

Author implementation of the paper "Span-based Semantic Parsing for Compositional Generalization"

Semantic Parser with Execution

Blueprint applications for MindMeld conversational platform

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

A dataset of complex questions on semi-structured Wikipedia tables

Neural Module Network for Reasoning over Text, ICLR 2020

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Simple Smart Pipe: python productivity-tool for rapid data manipulation

Thin wrapper for the AllenNLP's implementation of supervised open information extraction

Semantic parsing baseline reported in the DROP dataset paper

Open Information Extraction (OpenIE) and Open Relation Extraction (ORE) papers and data.

Utilities to work with Scala/Java code with py4j

End-to-End Differentiable Proving

A data explorer for DROP dataset

This is the official code repository for NumNet+(https://leaderboard.allenai.org/drop/submission/blu418v76glsbnh1qvd0)

Officially supported AllenNLP models

A collections of public and free annotated datasets of relationships between entities/nominals (Portuguese and English)

PyTorch implementation of the position-aware attention model for relation extraction

Source code for "Revisiting Unsupervised Relation Extraction" in ACL 2020

this is the code used in the paper "Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations"

Dataset and codes for ACL 2019 DocRED: A Large-Scale Document-Level Relation Extraction Dataset.

KnowBert -- Knowledge Enhanced Contextual Word Representations

Source code and dataset for ACL 2019 paper "Cognitive Graph for Multi-Hop Reading Comprehension at Scale"

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Programmable CUDA/C++ GPU Graph Analytics