SapienzaNLP / ewiser
A Word Sense Disambiguation system integrating implicit and explicit external knowledge.
☆67Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for ewiser
- UFSAC is a resource containing all WordNet Sense Annotated Corpora, and a Java library for manipulating them☆37Updated 2 years ago
- Language Modelling Makes Sense - WSD (and more) with Contextual Embeddings☆94Updated last year
- Pipeline component for spaCy (and other spaCy-wrapped parsers such as spacy-stanza and spacy-udpipe) that adds CoNLL-U properties to a Do…☆76Updated 4 months ago
- A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations☆54Updated 2 years ago
- GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge (EMNLP 2019)☆92Updated 2 years ago
- XL-AMR is a sequence-to-graph cross-lingual AMR parser that exploits transfer learning (EMNLP2020).☆16Updated 3 months ago
- The Universal Decompositional Semantics (UDS) dataset and the Decomp toolkit☆56Updated last year
- Coreference resolution with different higher-order inference methods; implemented in PyTorch.☆35Updated last year
- Text Extraction Formulation + Feedback Loop for state-of-the-art WSD (EMNLP 2021)☆52Updated 2 years ago
- Repository with code for MaChAmp: https://aclanthology.org/2021.eacl-demos.22/☆82Updated last month
- Reimplementation of a BERT based model (Shi et al, 2019), currently the state-of-the-art for English SRL. This model implements also pred…☆69Updated 2 years ago
- SUPERT: Unsupervised multi-document summarization evaluation & generation☆91Updated last year
- A coreference evaluation package for the CoNLL and ARRAU datasets☆40Updated 4 years ago
- ☆73Updated 3 years ago
- STREUSLE: a corpus with comprehensive lexical semantic annotation (multiword expressions, supersenses)☆63Updated last year
- SacreROUGE is a library dedicated to the use and development of text generation evaluation metrics with an emphasis on summarization.☆138Updated 2 years ago
- GSRL is a seq2seq model for end-to-end dependency- and span-based SRL (IJCAI2021).☆18Updated 3 years ago
- Disambiguate is a tool for training and using state of the art neural WSD models☆58Updated 2 years ago
- Diagnostic tests for linguistic capacities in language models☆66Updated 2 years ago
- Pytorch implementation of Highly Parallel Autoregressive Entity Linking with Discriminative Correction☆67Updated 2 years ago
- Codebase, data and models for the Keep it Simple paper at ACL2021☆36Updated last year
- Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources (NAACL-2021).☆17Updated 3 years ago
- Automatically detect errors in annotated corpora.☆47Updated last year
- Neural CRF Model for Sentence Alignment in Text Simplification☆62Updated last year
- Codebase for probing and visualizing multilingual models.☆45Updated 4 years ago
- Use BERT to Fill in the Blanks☆82Updated 2 years ago
- Lexical Simplification with Pretrained Encoders☆69Updated 3 years ago
- PyTorch implementation of the end-to-end coreference resolution model with different higher-order inference methods.☆59Updated last year
- Conversion scripts for coreference☆27Updated last month
- ☆32Updated 3 years ago