There are no reviews yet. Be the first to send feedback to the community and the maintainers!
OpenIE-standalone
openie6
OpenIE6 systemimojie
Neural generation model for Open Information ExtractionCaRB
CaRB - A Crowdsourced Benchmark for Open IEjeebench
JEEBench, EMNLP 2023tkbi
KBI
dl-with-constraints
Code for experiments in 'Primal Dual Formulation For Deep Learning With Constraints'BossNet
BossNet: Disentangling Language and Knowledge in Task Oriented DialogsECQA-Dataset
Dataaset Release for Explanations for CommonsenseQA, ACL 2021 PaperDeGPR
DSRE
Resources for the paper "PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction"FloNet
Code for "End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs"nsrmp
NSRM: Neuro-Symbolic Robot ManipulationDiS-ReX
FloDial
NS-KGC-AUG
moie
ECQA
Code Repository for the Explanations for CommonsenseQA, ACL 2021 paperkglr
PoolingAnalysis
[EMNLP'20][Findings] Official Repository for the paper "Why and when should you pool? Analyzing Pooling in Recurrent Architectures."symnet
torpido
Planning using Reinforcement LearningBoxCell
Official Repo for "Guided Prompting in SAM for Weakly Supervised Cell Segmentation in Histopathological Images"OxKBC
State-of-the-art models for Knowledge Base Completion (KBC) for large KBs (such as FB15k1and YAGO) are based on tensor factorization (TF), e.g, DistMult, ComplEx. While they produce2good results, they cannot expose any rationale behind their predictions, potentially reducing the3trust of a user in the outcome of the model. Previous works have explored creating an inherently4explainable model, e.g. Neural Theorem Proving (NTP), DeepPath, MINERVA, but explainability5in them comes at the cost of performance. Others have tried to create an auxiliary explainable6model having high fidelity with the underlying TF model, but unfortunately, they do not scale well7to large KBs. In this work, we proposeOXKBC– anOutcome eXplanation engine forKBC,8which provides a post-hoc explanation for every triple inferred by a (uninterpretable) factorization9based model. It first augments the underlying Knowledge Graph by introducing weighted edges10between entities based on their similarity given by the underlying model. It then defines a notion11of human-understandable explanation paths along with a language to generate them. Depending12on the edges, the paths are aggregated into second–order templates for further selection. The best13template with its grounding is then selected by a neural selection module that is trained with minimal14supervision by a novel loss function. Experiments over Mechanical Turk demonstrate that users15overwhelmingly find our explanations more trustworthy compared to rule mining.MPdialog
TourismQA
KGC-Ensemble
pronci
Code for the paper: "Covid vaccine is against Covid but Oxford vaccine is made at Oxford!" Semantic Interpretation of Proper Noun Compounds (EMNLP 2022)asap-uct
This repository contains all source files corresponding to a novel MDP Planner - which combines abstractions/symmteries and UCTCDNet
mokb6
ACL 2023 (main): Multilingual Open Knowledge Base CompletionLocationTagger
This repository provides a Location Tagger, for identifying locations, using a BERT-CRF Tagger. It creates a Location chunk using IOB tags when it finds one or more location words.ZGUL
output-space-invariance
Source code for Neural Models for Output-Space Invariance in Combinatorial ProblemsFuSIC-KBQA
symnet2
octopus
Octopus: Cost-Quality-Time Optimization in Crowdsourcingcon-mcmc
This repository maintains code base for contextual symmeties framework! "Contextual Symmetries in Graphical Models" Ankit Anand, Aditya Grover, Mausam and Parag Singla , International Joint Conference on Artificial Intelligence (IJCAI). New York, NY. July 2016.trapsnet
kbi-regex
oga-uct
On-the-Go Abstractions in UCTsa-flonet
trine
This page is under progress! Will be updated soon !symnet3
1oML_workdir
Working directory for the paper Neural Learning One-of-Many Solutions for Combinatorial Problems in Structured Output Spacesnc-mcmc
Conjunction-Splitting
Conjunction splitting and its analysisFlexAE
Code for the paper "FlexAE: Flexibly Learning Latent Priors for Wasserstein Auto-Encoders"RetinaQA
SpatialReasoner
This repository presents a detailed study of a spatial-reasoner using a simple artificially generated toy-dataset. This allows us to probe and study different aspects of spatial-reasoning in the absence of textual reasoning.Love Open Source and this site? Check out how you can help us