Papers with formal model

3 papers
Semantic Role Labelling for Dutch Law Texts (2022.lrec-1)

Copied to clipboard

Challenge: Existing methods to extract formalised representations of legal texts are labor-intensive . a Flint language is a knowledge representation language that allows us to express meaning of sources of norms .
Approach: They propose a method to extract structured representations in the Flint language from natural language.
Outcome: The proposed method outperforms the rule-based method on the Dutch Aliens Act.
Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand? (2021.tacl-1)

Copied to clipboard

Challenge: Language models trained on billions of tokens have recently led to unprecedented results on many NLP tasks.
Approach: They examine whether assertions enable a system to emulate representations preserving semantic relations like equivalence.
Outcome: The proposed model can emulate representations preserving semantic relations like equivalence, but it can become uncomputable for classes of languages where expressions can take different values in different contexts.
Extending AZee with Non-manual Gesture Rules for French Sign Language (2024.lrec-main)

Copied to clipboard

Challenge: Currently, Sign Languages (SLs) are under-resourced and are difficult to develop.
Approach: They propose to extend AZee to formally represent Sign Language discourses, but also to animate them with a virtual signer.
Outcome: The proposed model allows to formally represent Sign Language discourses, but also to animate them with a virtual signer.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations