Sapienza NLP group (@SapienzaNLP)
Guthub

SapienzaNLP

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    663
  • Global Org. Rank 19,739 (Top 7 %)
  • Registered about 4 years ago
  • Most used languages
    Python
         88.2 %
    Shell
         5.9 %
    Perl
         2.9 %
    Java
         2.9 %
  • Location 🇮🇹 Italy
  • Country Total Rank 456
  • Country Ranking
    Perl
         43
    Python
         69
    Shell
         253
    Java
         602

Top repositories

1

extend

Entity Disambiguation as text extraction (ACL 2022)
Python
164
star
2

spring

SPRING is a seq2seq model for Text-to-AMR and AMR-to-Text (AAAI2021).
Python
121
star
3

ewiser

A Word Sense Disambiguation system integrating implicit and explicit external knowledge.
Python
66
star
4

consec

Text Extraction Formulation + Feedback Loop for state-of-the-art WSD (EMNLP 2021)
Python
50
star
5

esc

ESC: Redesigning WSD with Extractive Sense Comprehension
Python
23
star
6

gsrl

GSRL is a seq2seq model for end-to-end dependency- and span-based SRL (IJCAI2021).
Python
18
star
7

unify-srl

Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources (NAACL-2021).
Python
17
star
8

mcl-wic

Semeval-2021 Multilingual and Cross-lingual Word-in-Context Task
17
star
9

xl-amr

XL-AMR is a sequence-to-graph cross-lingual AMR parser that exploits transfer learning (EMNLP2020).
Python
16
star
10

usea

Universal Semantic Annotator (LREC 2022)
Shell
15
star
11

wsd-hard-benchmark

Data and code for "Nibbling at the Hard Core of Word Sense Disambiguation" (ACL 2022).
Python
13
star
12

genesis

GeneSis is the first generative approach for lexical substitution (EMNLP 2021).
Python
12
star
13

xl-wsd-code

Code to train and test Word Sense Disambiguation models based on different pretrained transformers.
Python
12
star
14

srl4e

Python
11
star
15

multi-srl

Code and models for the COLING2020 paper "Bridging the Gap in Multilingual Semantic Role Labeling: a Language-Agnostic Approach".
Python
10
star
16

conception

Code and experiments for the COLING2020 paper "Conception: Multilingually-Enhanced, Human-Readable Concept Vector Representations".
Java
10
star
17

clubert

Distribution of word meanings in Wikipedia for English, Italian, French, German and Spanish.
10
star
18

steps

STEPS is a seq2seq model for Semantic Typing of Event Processes (AAAI 2022).
Python
8
star
19

LeakDistill

Python
8
star
20

bmr

Python
7
star
21

neural-pagerank-wsd

Exploiting the global WordNet graph to perform WSD
Python
6
star
22

srl-pas-probing

Probing for Predicate Argument Structures in Pretrained Language Models (ACL 2022).
Python
5
star
23

mulan

Multilingual Label propagatioN for Word Sense Disambiguation
Python
5
star
24

mwsd-datasets

Semeval-2013 and -2015 multilingual WSD datasets for BabelNet 4.0
Shell
5
star
25

dsrl

Code for "Semantic Role Labeling meets Definition Modeling: using natural language to describe predicate-argument structures"
Perl
5
star
26

MaTESe

MaTESe: Machine Translation Evaluation as a Sequence Tagging Problem
Python
4
star
27

sir

SIR is a sense-enhanced Information Retrieval system for multiple languages (EMNLP2021).
Python
4
star
28

multilabel-wsd

A multi-labeling model for knowledge integration into Word Sense Disambiguation (EACL 2021).
Python
3
star
29

nlp2020-hw1

Python
2
star
30

exploring-srl

Repository for the paper "Exploring Non-Verbal Predicates in Semantic Role Labeling: Challenges and Opportunities"
2
star
31

nlp2021-hw1

Python
2
star
32

nlp2023-hw1

Homework 1 for the NLP 2023 course
Python
2
star
33

united-srl

A unified dataset for span- and dependency-based multilingual and cross-lingual Semantic Role Labeling (EMNLP 2021).
2
star
34

nlp2022-hw1

Python
1
star
35

csi_code

Python
1
star
36

nlp2020-hw2

Python
1
star
37

alasca

New large-scale datasets for the task of lexical substitution (IJCAI 2021)
1
star
38

nlp2023-hw2

Homework 2 for the Multilingual NLP 2023 course
Python
1
star
39

XL-WA

1
star
40

visual-definition-modeling

Python
1
star