Search Results for author:
Found 49 papers, 16 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.
Integrating Expert Knowledge into Logical Programs via LLMs
Overall, ExKLoP serves as a robust evaluation platform that streamlines the selection of effective models for self-correcting systems while clearly delineating the types of errors encountered.
Formalizing Complex Mathematical Statements with LLMs: A Study on Mathematical Definitions
To address this gap, we investigate the task of autoformalizing real-world mathematical definitions -- a critical component of mathematical discourse.
Diffusion Twigs with Loop Guidance for Conditional Graph Generation
We introduce a novel score-based diffusion framework named Twigs that incorporates multiple co-evolving flows for enriching conditional generation tasks.
SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning
Syllogistic reasoning is crucial for Natural Language Inference (NLI).
Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series
Interacting systems are prevalent in nature.
Gem: Gaussian Mixture Model Embeddings for Numerical Feature Distributions
In this paper, we propose a method called Gem (Gaussian mixture model embeddings) that creates embeddings that build on numerical value distributions from columns.
Consistent Autoformalization for Constructing Mathematical Libraries
Autoformalization is the task of automatically translating mathematical content written in natural language to a formal language expression.
An LLM-based Knowledge Synthesis and Scientific Reasoning Framework for Biomedical Discovery
We present BioLunar, developed using the Lunar framework, as a tool for supporting biological analyses, with a particular emphasis on molecular-level evidence enrichment for biomarker discovery in oncology.
Transformer Normalisation Layers and the Independence of Semantic Subspaces
Recent works have shown that transformers can solve contextual reasoning tasks by internally executing computational graphs called circuits.
Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions
Language models (LMs) can hallucinate when performing complex mathematical reasoning.
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.
Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations
This disparity is demanded in further fine-tuning and affecting the cross-lingual abilities of LLMs.
Towards Controllable Natural Language Inference through Lexical Inference Types
They employ the T5 model to directly generate the tree, which can explain how the answer is inferred.
Abstract Meaning Representation
Natural Language Inference
+1
Controlling Equational Reasoning in Large Language Models with Prompt Interventions
This paper investigates how hallucination rates in Large Language Models (LLMs) may be controlled via a symbolic data generation framework, exploring a fundamental relationship between the rate of certain mathematical errors and types of input intervention.
Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation
The paper introduces a framework for the evaluation of the encoding of factual scientific knowledge, designed to streamline the manual evaluation process typically conducted by domain experts.
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.
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains.
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.
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
On the Visualisation of Argumentation Graphs to Support Text Interpretation
Therefore, AGs were considered to deliver a more critical approach to argument interpretation, especially with unfamiliar topics.
Analysis of business process automation as linear time-invariant system network
In this work, we examined Business Process (BP) production as a signal; this novel approach explores a BP workflow as a linear time-invariant (LTI) system.
Learning Disentangled Representations for Natural Language Definitions
Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing.
Metareview-informed Explainable Cytokine Storm Detection during CAR-T cell Therapy
Cytokine release syndrome (CRS), also known as cytokine storm, is one of the most consequential adverse effects of chimeric antigen receptor therapies that have shown promising results in cancer treatment.
A Survey in Mathematical Language Processing
Informal mathematical text underpins real-world quantitative reasoning and communication.
Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective
Metamorphic testing has recently been used to check the safety of neural NLP models.
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.
PhysNLU: A Language Resource for Evaluating Natural Language Understanding and Explanation Coherence in Physics
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, with correct ordering and relevance of statements.
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.
A Survey of Text Games for Reinforcement Learning informed by Natural Language
Reinforcement Learning has shown success in a number of complex virtual environments.
Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?
Even though BERT and similar pre-trained language models have excelled in several NLP tasks, their use has not been widely explored for the UI grounding domain.
Architectures of Meaning, A Systematic Corpus Analysis of NLP Systems
This paper proposes a novel statistical corpus analysis framework targeted towards the interpretation of Natural Language Processing (NLP) architectural patterns at scale.
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.
Switching Contexts: Transportability Measures for NLP
This paper explores the topic of transportability, as a sub-area of generalisability.
Why scholars are diagramming neural network models
Perhaps because of this, diagrams, as "icons of relation", are a prevalent medium for signifying complex models.
Number and quality of diagrams in scholarly publications is associated with number of citations
We analyse a corpus of diagrams found in scholarly computational linguistics conference proceedings (ACL 2017), and find inclusion of a system diagram to be correlated with higher numbers of citations after 3 years.
Structuralist analysis for neural network system diagrams
Using a corpus-based approach, we argue that the heterogeneous diagrammatic notations used for neural network systems has implications for signification in this domain.
Cost-effective Variational Active Entity Resolution
In this paper, we set out to devise an entity resolution method that builds on the robustness conferred by deep autoencoders to reduce human-involvement costs.
What is SemEval evaluating? A Systematic Analysis of Evaluation Campaigns in NLP
SemEval is the primary venue in the NLP community for the proposal of new challenges and for the systematic empirical evaluation of NLP systems.
Natural Language Premise Selection: Finding Supporting Statements for Mathematical Text
Mathematical text is written using a combination of words and mathematical expressions.
Proceedings of the AAAI-20 Workshop on Intelligent Process Automation (IPA-20)
This is the Proceedings of the AAAI-20 Workshop on Intelligent Process Automation (IPA-20) which took place in New York, NY, USA on February 7th 2020.
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.
DisSim: A Discourse-Aware Syntactic Text Simplification Frameworkfor English and German
We introduce DisSim, a discourse-aware sentence splitting framework for English and German whose goal is to transform syntactically complex sentences into an intermediate representation that presents a simple and more regular structure which is easier to process for downstream semantic applications.
MinWikiSplit: A Sentence Splitting Corpus with Minimal Propositions
We compiled a new sentence splitting corpus that is composed of 203K pairs of aligned complex source and simplified target sentences.
Transforming Complex Sentences into a Semantic Hierarchy
We present an approach for recursively splitting and rephrasing complex English sentences into a novel semantic hierarchy of simplified sentences, with each of them presenting a more regular structure that may facilitate a wide variety of artificial intelligence tasks, such as machine translation (MT) or information extraction (IE).
Semantic Relatedness for All (Languages): A Comparative Analysis of Multilingual Semantic Relatedness Using Machine Translation
The results also show that the benefit of using the most informative corpus outweighs the possible errors introduced by the machine translation.
DINFRA: A One Stop Shop for Computing Multilingual Semantic Relatedness
This demonstration presents an infrastructure for computing multilingual semantic relatedness and correlation for twelve natural languages by using three distributional semantic models (DSMs).
Composite Semantic Relation Classification
Different semantic interpretation tasks such as text entailment and question answering require the classification of semantic relations between terms or entities within text.
