Pinned Repositories
learning-to-generate-answers-with-citations
Repository for CaLF: Learning to Generate Answers with Citations via Factual Consistency Models. CaLF is a weakly-supervised fine-tuning method leveraging factual consistency models to improve the quality of generated answers and their citations. [ACL 2024]
3DScanner.RaspberryPi
3DScanner - implemented with a Raspberry Pi
AdMIRaL
Models and Code to "Autoregressive Multi-hop Document Retrieval Guided by Natural Logic" (AdMIRaL), accepted to EMNLP2022.
AuT-Few
AuT-Few: Automated Few-shot Classification with Instruction-Finetuned Language Models
FEVEROUS
Repository for Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS), accepted to NeurIPS 2021 Dataset and Benchmarks and used for the FEVER Workshop Shared Task at EMNLP2021.
QA-NatVer
Repository for QA-NatVer: Question Answering for Natural Logic-based Fact Verification. QA-NatVer obviates the need for annotated training data while still relying on a interpretable and deterministic inference system. [EMNLP2023]
TabVer
Repository for TabVer: Tabular Fact Verification with Natural Logic. Enabling natural logic proofs over numbers and arithmetic computations on tables. [TACL 2024]
Zero-shot-NERC
Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification, published in ACL 2021.
BlurbGenreCollection-HMC
Hierarchical multi-label text classification of the BlurbGenreCollection using capsule networks.
Taxonomy_Refinement_Embeddings
Taxonomy refinement method to improve domain-specific taxonomy systems.
Raldir's Repositories
Raldir/FEVEROUS
Repository for Fact Extraction and VERification Over Unstructured and Structured information (FEVEROUS), accepted to NeurIPS 2021 Dataset and Benchmarks and used for the FEVER Workshop Shared Task at EMNLP2021.
Raldir/Zero-shot-NERC
Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification, published in ACL 2021.
Raldir/AuT-Few
AuT-Few: Automated Few-shot Classification with Instruction-Finetuned Language Models
Raldir/AdMIRaL
Models and Code to "Autoregressive Multi-hop Document Retrieval Guided by Natural Logic" (AdMIRaL), accepted to EMNLP2022.
Raldir/3DScanner.RaspberryPi
3DScanner - implemented with a Raspberry Pi
Raldir/feverous-wip
Raldir/QA-NatVer
Repository for QA-NatVer: Question Answering for Natural Logic-based Fact Verification. QA-NatVer obviates the need for annotated training data while still relying on a interpretable and deterministic inference system. [EMNLP2023]
Raldir/Smart-Pathing
Intelligent Car Movement realized with MPI/Open-MP
Raldir/autogluon
AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data
Raldir/BenchmarkingZeroShot
Raldir/TabVer
Repository for TabVer: Tabular Fact Verification with Natural Logic. Enabling natural logic proofs over numbers and arithmetic computations on tables. [TACL 2024]
Raldir/CapsNet-Keras
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error ＝ 0.34%.
Raldir/CapsNet-keras-imdb
Raldir/Damegdx
Simple Draughtsgame for mobile devices
Raldir/GuildWars2_MusicCreator
Simple Bot for Keyinputs in Gw2
Raldir/learning-to-generate-answers-with-citations
Repository for CaLF: Learning to Generate Answers with Citations via Factual Consistency Models. CaLF is a weakly-supervised fine-tuning method leveraging factual consistency models to improve the quality of generated answers and their citations. [ACL 2024]
Raldir/Pathfinding
Visualisation of A* Algorithm in Graph
Raldir/poincare-embeddings
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"
Raldir/PyRouge
A python library to compute rouge score for summarization
Raldir/t-few
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"
Raldir/taxi
TAXI: a Taxonomy Induction Method based on Lexico-Syntactic Patterns, Substrings and Focused Crawling
Raldir/test01