babelscape Goto Github PK

alert

Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"

amr-alignment

This is the repo for Cross-lingual AMR Aligner, a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, presented at ACL 2023.

amrs-assemble

This is the repo for AMRs Assemble!, a novel approach to AMR ensembling, presented at ACL 2023. This repository provides resources and tools for ensemble modeling of Abstract Meaning Representation (AMR) graphs.

cner

CNER: Concept and Named Entity Recognition

crocoalign

A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts.

crocodile

cRocoDiLe is a dataset extraction tool for Relation Extraction using Wikipedia and Wikidata presented in REBEL (EMNLP 2021).

echoes-from-alexandria

This repository provides the source code used to automatically generate the book summarization datasets described in the paper titled "Echoes from Alexandria: A Large Resource for Multilingual Book Summarization".

fenice

FENICE (Factuality Evaluation of Summarization based on Natural Language Inference and Claim Extraction) is a factuality-oriented metric for summarization.

id10m

Data and code for the paper "ID10M: Idiom Identification in 10 Languages" (NAACL 2022).

multinerd

Repository for the paper "MultiNERD: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition (and Disambiguation)" (NAACL 2022).

multirebel

ner4el

Repository for the paper "Named Entity Recognition for Entity Linking: What Works and What's Next" (EMNLP 2021).

ner4id

Data and code for the paper "NER4ID at SemEval-2022 Task 2: Named Entity Recognition for Idiomaticity Detection".

rebel

REBEL is a seq2seq model that simplifies Relation Extraction (EMNLP 2021).

wikineural

Data and evaluation code for the paper WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER (EMNLP 2021).

wsl

Word Sense Linking model is designed to identify and disambiguate spans of text to their most suitable senses from a reference inventory.