3 citations · 5 across the 10 of their papers we have counts for
11 papers
Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models
Julia Rozanova, Marco Valentino, André Freitas
Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a…
Estimating the Causal Effects of Natural Logic Features in Neural NLI Models
Julia Rozanova, Marco Valentino, Andre Freitas
Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a…
Interventional Probing in High Dimensions: An NLI Case Study
Julia Rozanova, Marco Valentino, Lucas Cordeiro +1
Probing strategies have been shown to detect the presence of various linguistic features in large language models; in particular, semantic features intermediate to the "natural log…
Montague semantics and modifier consistency measurement in neural language models
Danilo S. Carvalho, Edoardo Manino, Julia Rozanova +2
This work proposes a novel methodology for measuring compositional behavior in contemporary language embedding models. Specifically, we focus on adjectival modifier phenomena in ad…
Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective
Edoardo Manino, Julia Rozanova, Danilo Carvalho +2
Metamorphic testing has recently been used to check the safety of neural NLP models. Its main advantage is that it does not rely on a ground truth to generate test cases. However,…
Decomposing Natural Logic Inferences in Neural NLI
Julia Rozanova, Deborah Ferreira, Marco Valentino +2
In the interest of interpreting neural NLI models and their reasoning strategies, we carry out a systematic probing study which investigates whether these models capture the crucia…
Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?
Julia Rozanova, Deborah Ferreira, Krishna Dubba +3
Models designed for intelligent process automation are required to be capable of grounding user interface elements. This task of interface element grounding is centred on linking i…
Supporting Context Monotonicity Abstractions in Neural NLI Models
Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan +2
Natural language contexts display logical regularities with respect to substitutions of related concepts: these are captured in a functional order-theoretic property called monoton…
Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference
Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira +2
This paper presents Diff-Explainer, the first hybrid framework for explainable multi-hop inference that integrates explicit constraints with neural architectures through differenti…
Does My Representation Capture X? Probe-Ably
Deborah Ferreira, Julia Rozanova, Mokanarangan Thayaparan +2
Probing (or diagnostic classification) has become a popular strategy for investigating whether a given set of intermediate features is present in the representations of neural mode…
On the Evaluation of Intelligent Process Automation
Deborah Ferreira, Julia Rozanova, Krishna Dubba +2
Intelligent Process Automation (IPA) is emerging as a sub-field of AI to support the automation of long-tail processes which requires the coordination of tasks across different sys…