Search Results for author: André Freitas

Found 36 papers, 11 papers with code

Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers

no code implementations5 Aug 2022 Mokanarangan Thayaparan, Marco Valentino, André Freitas

Integer Linear Programming (ILP) provides a viable mechanism to encode explicit and controllable assumptions about explainable multi-hop inference with natural language.

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

no code implementations2 Aug 2022 Alex Bogatu, Zili Zhou, Dónal Landers, André Freitas

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

Explanation Generation Question Answering

Biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data

no code implementations2 Jul 2022 Magdalena Wysocka, Oskar Wysocki, Marie Zufferey, Dónal Landers, André Freitas

We discuss the recent evolutionary arch of DL models in the direction of integrating prior biological relational and network knowledge to support better generalisation (e. g. pathways or Protein-Protein-Interaction networks) and interpretability.

Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI

no code implementations3 May 2022 Marco Valentino, André Freitas

A fundamental research goal for Explainable AI (XAI) is to build models that are capable of reasoning through the generation of natural language explanations.

Philosophy

Transformers and the representation of biomedical background knowledge

no code implementations4 Feb 2022 Oskar Wysocki, Zili Zhou, Paul O'Regan, Deborah Ferreira, Magdalena Wysocka, Dónal Landers, André Freitas

Specialised transformers-based models (such as BioBERT and BioMegatron) are adapted for the biomedical domain based on publicly available biomedical corpora.

Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders

no code implementations Findings (EMNLP) 2021 Giangiacomo Mercatali, André Freitas

The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled.

Disentanglement Style Transfer +1

Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration

1 code implementation25 Jul 2021 Marco Valentino, Mokanarangan Thayaparan, Deborah Ferreira, André Freitas

Regenerating natural language explanations in the scientific domain has been proposed as a benchmark to evaluate complex multi-hop and explainable inference.

Multi-hop Question Answering Natural Language Inference +1

Context-Preserving Text Simplification

1 code implementation24 May 2021 Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh

We present a context-preserving text simplification (TS) approach that recursively splits and rephrases complex English sentences into a semantic hierarchy of simplified sentences.

Text Simplification

Supporting Context Monotonicity Abstractions in Neural NLI Models

no code implementations ACL (NALOMA, IWCS) 2021 Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, André Freitas

Natural language contexts display logical regularities with respect to substitutions of related concepts: these are captured in a functional order-theoretic property called monotonicity.

Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference

no code implementations7 May 2021 Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, André Freitas

This paper presents Diff-Explainer, the first hybrid framework for explainable multi-hop inference that integrates explicit constraints with neural architectures through differentiable convex optimization.

Multi-hop Question Answering Natural Language Inference +3

Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards

no code implementations IWCS (ACL) 2021 Marco Valentino, Ian Pratt-Hartmann, André Freitas

An emerging line of research in Explainable NLP is the creation of datasets enriched with human-annotated explanations and rationales, used to build and evaluate models with step-wise inference and explanation generation capabilities.

Explanation Generation

Does My Representation Capture X? Probe-Ably

1 code implementation ACL 2021 Deborah Ferreira, Julia Rozanova, Mokanarangan Thayaparan, Marco Valentino, André Freitas

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 models.

Similarity-Based Equational Inference in Physics

1 code implementation24 Mar 2021 Jordan Meadows, André Freitas

Automating the derivation of published results is a challenge, in part due to the informal use of mathematics by physicists, compared to that of mathematicians.

ExplanationLP: Abductive Reasoning for Explainable Science Question Answering

no code implementations25 Oct 2020 Mokanarangan Thayaparan, Marco Valentino, André Freitas

We propose a novel approach for answering and explaining multiple-choice science questions by reasoning on grounding and abstract inference chains.

Answer Selection Multiple-choice +1

A Survey on Explainability in Machine Reading Comprehension

no code implementations1 Oct 2020 Mokanarangan Thayaparan, Marco Valentino, André Freitas

This paper presents a systematic review of benchmarks and approaches for explainability in Machine Reading Comprehension (MRC).

Machine Reading Comprehension

Case-Based Abductive Natural Language Inference

no code implementations30 Sep 2020 Marco Valentino, Mokanarangan Thayaparan, André Freitas

Most of the contemporary approaches for multi-hop Natural Language Inference (NLI) construct explanations considering each test case in isolation.

Natural Language Inference Question Answering

XTE: Explainable Text Entailment

no code implementations25 Sep 2020 Vivian S. Silva, André Freitas, Siegfried Handschuh

Text entailment, the task of determining whether a piece of text logically follows from another piece of text, is a key component in NLP, providing input for many semantic applications such as question answering, text summarization, information extraction, and machine translation, among others.

Machine Translation Question Answering +1

How Researchers Use Diagrams in Communicating Neural Network Systems

no code implementations28 Aug 2020 Guy Clarke Marshall, André Freitas, Caroline Jay

Neural networks are a prevalent and effective machine learning component, and their application is leading to significant scientific progress in many domains.

Understanding scholarly Natural Language Processing system diagrams through application of the Richards-Engelhardt framework

no code implementations26 Aug 2020 Guy Clarke Marshall, Caroline Jay, André Freitas

We utilise Richards-Engelhardt framework as a tool for understanding Natural Language Processing systems diagrams.

Identifying and Explaining Discriminative Attributes

1 code implementation IJCNLP 2019 Armins Stepanjans, André Freitas

Identifying what is at the center of the meaning of a word and what discriminates it from other words is a fundamental natural language inference task.

Knowledge Graphs Natural Language Inference +1

On the Semantic Interpretability of Artificial Intelligence Models

no code implementations9 Jul 2019 Vivian S. Silva, André Freitas, Siegfried Handschuh

Artificial Intelligence models are becoming increasingly more powerful and accurate, supporting or even replacing humans' decision making.

Decision Making

The Diagrammatic AI Language (DIAL): Version 0.1

no code implementations28 Dec 2018 Guy Marshall, André Freitas

Currently, there is no consistent model for visually or formally representing the architecture of AI systems.

Graphene: A Context-Preserving Open Information Extraction System

1 code implementation COLING 2018 Matthias Cetto, Christina Niklaus, André Freitas, Siegfried Handschuh

In that way, we preserve the context of the relational tuples extracted from a source sentence, generating a novel lightweight semantic representation for Open IE that enhances the expressiveness of the extracted propositions.

Open Information Extraction

Graphene: Semantically-Linked Propositions in Open Information Extraction

1 code implementation COLING 2018 Matthias Cetto, Christina Niklaus, André Freitas, Siegfried Handschuh

We present an Open Information Extraction (IE) approach that uses a two-layered transformation stage consisting of a clausal disembedding layer and a phrasal disembedding layer, together with rhetorical relation identification.

Open Information Extraction

Semantic Relation Classification: Task Formalisation and Refinement

no code implementations WS 2016 Vivian S. Silva, Manuela Hürliman, Brian Davis, Siegfried Handschuh, André Freitas

This work provides a critique on the set of abstract relations used for semantic relation classification with regard to their ability to express relationships between terms which are found in a domain-specific corpora.

Classification General Classification +1

Word Tagging with Foundational Ontology Classes: Extending the WordNet-DOLCE Mapping to Verbs

no code implementations20 Jun 2018 Vivian S. Silva, André Freitas, Siegfried Handschuh

Semantic annotation is fundamental to deal with large-scale lexical information, mapping the information to an enumerable set of categories over which rules and algorithms can be applied, and foundational ontology classes can be used as a formal set of categories for such tasks.

Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition

no code implementations LREC 2018 Vivian S. Silva, André Freitas, Siegfried Handschuh

Adopting a conceptual model composed of a set of semantic roles for dictionary definitions, we trained a classifier for automatically labeling definitions, preparing the data to be later converted to a graph representation.

Categorization of Semantic Roles for Dictionary Definitions

no code implementations WS 2016 Vivian S. Silva, Siegfried Handschuh, André Freitas

Understanding the semantic relationships between terms is a fundamental task in natural language processing applications.

A Survey on Open Information Extraction

no code implementations COLING 2018 Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh

We provide a detailed overview of the various approaches that were proposed to date to solve the task of Open Information Extraction.

Open Information Extraction

A Sentence Simplification System for Improving Relation Extraction

no code implementations COLING 2016 Christina Niklaus, Bernhard Bermeitinger, Siegfried Handschuh, André Freitas

In this demo paper, we present a text simplification approach that is directed at improving the performance of state-of-the-art Open Relation Extraction (RE) systems.

Relation Extraction Text Simplification

Cannot find the paper you are looking for? You can Submit a new open access paper.