PhilippChr
I am a PhD student at the at the Max Planck Institute for Informatics. My research focuses on Question Answering and Knowledge Graphs.
Max Planck Institute for InformaticsSaarbrücken, Germany
Pinned Repositories
CLOCQ
Code for our WSDM 2022 paper. CLOCQ is a framework which allows efficient access to knowledge bases (KB) for functionalities related to question answering (QA). CLOCQ can retrieve a set of relevant facts from the KB for a given user question. Further, it provides efficient retrieval of KB-neighborhoods, KB-connectivities and labels, aliases etc.
CLOCQ-pruning-module
Implementation of a post-hoc cleaning module for CLOCQ, that can help to apply CLOCQ on entity or relation linking tasks.
CONVEX
Code for our CIKM 2019 paper. As far as we know, CONVEX is the first unsupervised method for conversational question answering over knowledge graphs. A demo and our benchmark (and more) can be found at
CONVINSE
Code for our SIGIR 2022 paper. CONVINSE is a framework for conversational question answering (ConvQA) over heterogeneous information sources.
datasets
🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools
EXPLAIGNN
Code for our SIGIR 2023 paper. EXPLAIGNN provides a pipeline for conversational question answering (ConvQA) over heterogeneous sources, and code for iterative graph neural networks (GNNs). Such iterative GNNs can help to causally explaignn GNN outputs.
FAITH
FAITH code and data for our WWW'24 paper "Faithful Temporal Qestion Answering over Heterogeneous Sources"
FiD
Fusion-in-Decoder -> To run on standard CPU/GPU
TIQ
TIQ code and data for our WWW'24 paper "Faithful Temporal Qestion Answering over Heterogeneous Sources"
wikidata-core-for-QA
Project to prepare a n-triples wikidata dump for QA access.
PhilippChr's Repositories
PhilippChr/CONVEX
Code for our CIKM 2019 paper. As far as we know, CONVEX is the first unsupervised method for conversational question answering over knowledge graphs. A demo and our benchmark (and more) can be found at
PhilippChr/wikidata-core-for-QA
Project to prepare a n-triples wikidata dump for QA access.
PhilippChr/CLOCQ
Code for our WSDM 2022 paper. CLOCQ is a framework which allows efficient access to knowledge bases (KB) for functionalities related to question answering (QA). CLOCQ can retrieve a set of relevant facts from the KB for a given user question. Further, it provides efficient retrieval of KB-neighborhoods, KB-connectivities and labels, aliases etc.
PhilippChr/CONVINSE
Code for our SIGIR 2022 paper. CONVINSE is a framework for conversational question answering (ConvQA) over heterogeneous information sources.
PhilippChr/EXPLAIGNN
Code for our SIGIR 2023 paper. EXPLAIGNN provides a pipeline for conversational question answering (ConvQA) over heterogeneous sources, and code for iterative graph neural networks (GNNs). Such iterative GNNs can help to causally explaignn GNN outputs.
PhilippChr/CLOCQ-pruning-module
Implementation of a post-hoc cleaning module for CLOCQ, that can help to apply CLOCQ on entity or relation linking tasks.
PhilippChr/TIQ
TIQ code and data for our WWW'24 paper "Faithful Temporal Qestion Answering over Heterogeneous Sources"
PhilippChr/datasets
🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools
PhilippChr/FAITH
FAITH code and data for our WWW'24 paper "Faithful Temporal Qestion Answering over Heterogeneous Sources"
PhilippChr/FiD
Fusion-in-Decoder -> To run on standard CPU/GPU