SunLab-OSU

CliniQG4QA

CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering

covid-faq

COUGH: A Challenge Dataset and Models for COVID-19 FAQ Retrieval

GAT-AnswerTriggering

We propose Group-Level Answer Triggering (GAT), an end-to-end deep neural network framework which is trained by a novel group-level objective function and directly optimizes the answer triggering performance. More details are in the paper "An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective" published in EMNLP'17.

Group-Meeting-Reading

https://sunlab-osu.github.io/Group-Meeting-Reading/

IterPrompt

MISP

Model-based Interactive Semantic Parsing (MISP) framework

ReasonBERT

Code and pre-trained models for "ReasonBert: Pre-trained to Reason with Distant Supervision", EMNLP'2021

REDS2

Code and dataset for "Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction" (EMNLP'19)

TURL

Code and data for "TURL: Table Understanding through Representation Learning"

Understanding-CoT

sunlab-osu/TURL

Code and data for "TURL: Table Understanding through Representation Learning"

sunlab-osu/Understanding-CoT

sunlab-osu/MISP

Model-based Interactive Semantic Parsing (MISP) framework

sunlab-osu/ReasonBERT

Code and pre-trained models for "ReasonBert: Pre-trained to Reason with Distant Supervision", EMNLP'2021

sunlab-osu/CliniQG4QA

CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering

sunlab-osu/IterPrompt

sunlab-osu/covid-faq

COUGH: A Challenge Dataset and Models for COVID-19 FAQ Retrieval

sunlab-osu/REDS2

Code and dataset for "Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction" (EMNLP'19)

sunlab-osu/GAT-AnswerTriggering

We propose Group-Level Answer Triggering (GAT), an end-to-end deep neural network framework which is trained by a novel group-level objective function and directly optimizes the answer triggering performance. More details are in the paper "An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective" published in EMNLP'17.

sunlab-osu/Group-Meeting-Reading

https://sunlab-osu.github.io/Group-Meeting-Reading/

sunlab-osu/BioNEV

This repository contains source code and datasets for paper "Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations". This work aims to systematically evaluate recent advanced graph embedding techniques on biomedical tasks.

sunlab-osu/CliniRC

Code for the paper "Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset" (ACL 2020)

sunlab-osu/GraphQuestions

GraphQuestions is a characteristic-rich dataset for factoid question answering described in the paper "On Generating Characteristic-rich Question Sets for QA Evaluation" - EMNLP'16.

sunlab-osu/incremental_tree_edit

Code for "Learning Structural Edits via Incremental Tree Transformations" (ICLR'21)

sunlab-osu/Interactive-Semantic-Parsing

Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning (AAAI'19)

sunlab-osu/ReDR

Code for ACL 2019 paper "Reinforced Dynamic Reasoning for Conversational Question Generation".

sunlab-osu/Riker

Riker: Mining Rich Keyword Representations for Interpretable Product Question Answering (KDD19)

sunlab-osu/StaQC

StaQC (Stack Overflow Question-Code pairs) is the largest dataset to date of around 148K Python and 120K SQL domain question-code pairs, which are automatically mined from Stack Overflow using a Bi-View Hierarchical Neural Network, as described in the paper "StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow" (WWW'18).

sunlab-osu/tacobot

Alexa Prize TaskBot by OSU NLP

sunlab-osu/QQC

Adversarial Training for Code Retrievalwith Question-Description Relevance Regularization

sunlab-osu/CoaCor

Code for "CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning" (WWW 2019)

sunlab-osu/ConPI

Source Code for WSDM 2021 paper, "Modeling Context Pair Interaction for Pairwise Tasks on Graphs"

sunlab-osu/GloRE

GloRE is a relation embedding model that can be used to augment existing relation extraction models and improve their performance. Most remarkably, for the top 1,000 relational facts discovered by the best existing model (PCNN+ATT), the precision can be improved from 83.9% to 89.3%.

sunlab-osu/PhraseMiningLM

This repository contains the source code and models for our work on a system to easily and efficiently extract quality and meaningful phrases from clinical documents with limited amount of training data. We use deep neural network based language models such as BERT and ELMO to extract a set of quality phrases.

sunlab-osu/qa-annotation

PyTorch implementation of the EMNLP 2020 paper Learning a Cost-Effective Annotation Policy for Question Answering

sunlab-osu/SurfCon

Implementation of SurfCon model for Synonym Discovery on Privacy-Aware Clinical Data

sunlab-osu/X-MedRELA

Source Code for ACL 2020 paper, "Rationalizing Medical Relation Prediction from Corpus-level Statistics"