activity
20172023
most citedA Survey on Explainability in Machine Reading Comprehension

32 citations · 122 across the 25 of their papers we have counts for

collaborators
Showing 2022 · cs.CLShow all

6 papers · 2 filters

cs.CL2022

Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder

Yingji Zhang, Danilo S. Carvalho, André Freitas

Formal/symbolic semantics can provide canonical, rigid controllability and interpretability to sentence representations due to their \textit{localisation} or \textit{composition} p…

cs.CL2022★ 1 cited

Learning Disentangled Representations for Natural Language Definitions

Danilo S. Carvalho, Giangiacomo Mercatali, Yingji Zhang +1

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing…

cs.CL2022★ 1 cited

Active entailment encoding for explanation tree construction using parsimonious generation of hard negatives

Alex Bogatu, Zili Zhou, Dónal Landers +1

Entailment trees have been proposed to simulate the human reasoning process of explanation generation in the context of open--domain textual question answering. However, in practic…

cs.CL2022★ 8 cited

A Survey in Mathematical Language Processing

Jordan Meadows, Andre Freitas

Informal mathematical text underpins real-world quantitative reasoning and communication. Developing sophisticated methods of retrieval and abstraction from this dual modality is c…

cs.CL2022★ 9 cited

Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language

Mael Jullien, Marco Valentino, Andre Freitas

With the methodological support of probing (or diagnostic classification), recent studies have demonstrated that Transformers encode syntactic and semantic information to some exte…

cs.CL2022

PhysNLU: A Language Resource for Evaluating Natural Language Understanding and Explanation Coherence in Physics

Jordan Meadows, Zili Zhou, Andre Freitas

In order for language models to aid physics research, they must first encode representations of mathematical and natural language discourse which lead to coherent explanations, wit…