Papers by Marie Candito
FrSemCor: Annotating a French Corpus with Supersenses (2020.lrec-1)
Copied to clipboard
Lucie Barque, Pauline Haas, Richard Huyghe, Delphine Tribout, Marie Candito, Benoit Crabbé, Vincent Segonne
| Challenge: | a new project aims to provide a sense-annotated corpus of French for NLP and linguistics research . the project uses WordNet Unique Beginners as semantic tags to provide interoperability . |
| Approach: | They propose to use WordNet Unique Beginners as semantic tags to annotate French nouns . the project aims to provide a gold standard resource for linguistics and linguistic research . |
| Outcome: | The proposed resource is released online under a Creative Commons license. |
In the LLM era, Word Sense Induction remains unsolved (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing word sense induction methods rely on predefined sense inventories of arbitrary granularity and require labor intensive sense-annotated data. |
| Approach: | They propose to evaluate an LLM-based word sense induction method for English . they use data augmentation sources, corpus and lexicon, and semi-supervised scenarios to augment the data. |
| Outcome: | The proposed method surpasses the previous SOTA system on a English set by 3.3%. |
Auxiliary tasks to boost Biaffine Semantic Dependency Parsing (2022.findings-acl)
Copied to clipboard
| Challenge: | Semantic dependency parsing (SDP) is a task of producing a dependency graph for a sentence. |
| Approach: | They propose to use simple auxiliary tasks that introduce some form of interdependence between arcs to circumvent such an independence of decision. |
| Outcome: | The proposed method shows modest but systematic performance gains on a near-state-of-the-art baseline using transformer-based contextualized representations. |
Injecting Wiktionary to improve token-level contextual representations using contrastive learning (2024.eacl-short)
Copied to clipboard
| Challenge: | lexical semantics tasks require contextual word embeddings that are not blind to context, despite the fact that vectors of the same meaning are too different. |
| Approach: | They propose to fine-tune pre-trained language models by using automatically self-augmented examples to target contextual word embeddings. |
| Outcome: | The proposed method achieves significant improvements on the original WiC test set and in two new tests. |
Annotating the French Wiktionary with supersenses for large scale lexical analysis: a use case to assess form-meaning relationships within the nominal lexicon (2025.coling-main)
Copied to clipboard
| Challenge: | Conducting large-scale empirical studies in lexical semantics remains an elusive goal for many languages lacking comprehensive semantic resources. |
| Approach: | They propose to use the Princeton WordNet to enrich the French Wiktionary with general semantic classes, known as supersenses, using a limited amount of manually annotated data. |
| Outcome: | The proposed method can be extended to other languages provided an electronic lexicon and manually annotated senses are available. |
Cheating a Parser to Death: Data-driven Cross-Treebank Annotation Transfer (L18-1)
Copied to clipboard
| Challenge: | Using annotated corpus for linguistic purposes is no longer justified . hand-crafted syntactic resources such as grammars and lexicons can be used as sources of features to guide data driven systems. |
| Approach: | They propose an efficient method for transferring annotations between two different treebanks of the same language. |
| Outcome: | The proposed method is based on the Universal Dependency annotation scheme and was evaluated on the gold standard (94.75% of LAS, 99.40% UAS on the test set). |