Search Results for author:
Found 36 papers, 15 papers with code
To be or not to be an Integer? Encoding Variables for Mathematical Text
The application of Natural Language Inference (NLI) methods over large textual corpora can facilitate scientific discovery, reducing the gap between current research and the available large-scale scientific knowledge.
TextGraphs 2021 Shared Task on Multi-Hop Inference for Explanation Regeneration
While previous editions of this shared task aimed to evaluate explanatory completeness – finding a set of facts that form a complete inference chain, without gaps, to arrive from question to correct answer, this 2021 instantiation concentrates on the subtask of determining relevance in large multi-hop explanations.
TextGraphs 2022 Shared Task on Natural Language Premise Selection
In this summary paper, we present the results of the 1st edition of the NLPS task, providing a description of the evaluation data, and the participating systems.
SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials
Addressing this, we present SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for ClinicalTrials.
Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models
Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems.
A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference
Integer Linear Programming (ILP) has been proposed as a formalism for encoding precise structural and semantic constraints for Natural Language Inference (NLI).
Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement
An increasing amount of research in Natural Language Inference (NLI) focuses on the application and evaluation of Large Language Models (LLMs) and their reasoning capabilities.
Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders
Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explained and improved upon.
Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders
The injection of syntactic information in Variational AutoEncoders (VAEs) has been shown to result in an overall improvement of performances and generalisation.
Multi-Operational Mathematical Derivations in Latent Space
To this end, we introduce different multi-operational representation paradigms, modelling mathematical operations as explicit geometric transformations.
Generating Mathematical Derivations with Large Language Models
In addition, we analyse 1. 7K equations, and over 200 derivations, to highlight common reasoning errors such as the inclusion of incorrect, irrelevant, and redundant equations.
A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers
This paper proposes a methodology for generating and perturbing detailed derivations of equations at scale, aided by a symbolic engine, to evaluate the generalisability of Transformers to out-of-distribution mathematical reasoning problems.
Estimating the Causal Effects of Natural Logic Features in Neural NLI Models
Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems.
Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions
Natural language definitions possess a recursive, self-explanatory semantic structure that can support representation learning methods able to preserve explicit conceptual relations and constraints in the latent space.
NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports
In this work, we present a novel resource to advance research on NLI for reasoning on CTRs.
SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data
This paper describes the results of SemEval 2023 task 7 -- Multi-Evidence Natural Language Inference for Clinical Trial Data (NLI4CT) -- consisting of 2 tasks, a Natural Language Inference (NLI) task, and an evidence selection task on clinical trial data.
Interventional Probing in High Dimensions: An NLI Case Study
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 logic" fragment of the Natural Language Inference task (NLI).
Natural Language Inference
Vocal Bursts Intensity Prediction
Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers
Integer Linear Programming (ILP) provides a viable mechanism to encode explicit and controllable assumptions about explainable multi-hop inference with natural language.
Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI
A fundamental research goal for Explainable AI (XAI) is to build models that are capable of reasoning through the generation of natural language explanations.
Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language
With the methodological support of probing (or diagnostic classification), recent studies have demonstrated that Transformers encode syntactic and semantic information to some extent.
Decomposing Natural Logic Inferences in Neural NLI
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 crucial semantic features central to natural logic: monotonicity and concept inclusion.
Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration
Regenerating natural language explanations in the scientific domain has been proposed as a benchmark to evaluate complex multi-hop and explainable inference.
Supporting Context Monotonicity Abstractions in Neural NLI Models
Natural language contexts display logical regularities with respect to substitutions of related concepts: these are captured in a functional order-theoretic property called monotonicity.
Encoding Explanatory Knowledge for Zero-shot Science Question Answering
This paper describes N-XKT (Neural encoding based on eXplanatory Knowledge Transfer), a novel method for the automatic transfer of explanatory knowledge through neural encoding mechanisms.
Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference
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.
Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards
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.
Does My Representation Capture X? Probe-Ably
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.
ExplanationLP: Abductive Reasoning for Explainable Science Question Answering
We propose a novel approach for answering and explaining multiple-choice science questions by reasoning on grounding and abstract inference chains.
A Survey on Explainability in Machine Reading Comprehension
This paper presents a systematic review of benchmarks and approaches for explainability in Machine Reading Comprehension (MRC).
Case-Based Abductive Natural Language Inference
Most of the contemporary approaches for multi-hop Natural Language Inference (NLI) construct explanations considering each test case in isolation.
Unification-based Reconstruction of Multi-hop Explanations for Science Questions
This paper presents a novel framework for reconstructing multi-hop explanations in science Question Answering (QA).
A Framework for Evaluation of Machine Reading Comprehension Gold Standards
Machine Reading Comprehension (MRC) is the task of answering a question over a paragraph of text.
Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks
Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text.
