Arrow Research search

Author name cluster

Nicholas Asher

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers
2 author rows

Possible papers

11

ECAI Conference 2024 Conference Paper

On Explaining with Attention Matrices

  • Omar Naim
  • Nicholas Asher

This paper explores the much discussed, possible explanatory link between attention weights (AW) in transformer models and predicted output. Contrary to intuition and early research on attention, more recent prior research has provided formal arguments and empirical evidence that AW are not explanatorily relevant. We show that the formal arguments are incorrect. We introduce and effectively compute efficient attention, which isolates the effective components of attention matrices in tasks and models in which AW play an explanatory role. We show that efficient attention has a causal role (provides minimally necessary and sufficient conditions) for predicting model output in NLP tasks requiring contextual information, and we show, contrary to [7], that efficient attention matrices are probability distributions and are effectively calculable. Thus, they should play an important part in the explanation of attention based model behavior. We offer empirical experiments in support of our method illustrating various properties of efficient attention with various metrics on four datasets.

Details

JMLR Journal 2024 Journal Article

Transport-based Counterfactual Models

  • Lucas De Lara
  • Alberto González-Sanz
  • Nicholas Asher
  • Laurent Risser
  • Jean-Michel Loubes

Counterfactual frameworks have grown popular in machine learning for both explaining algorithmic decisions but also defining individual notions of fairness, more intuitive than typical group fairness conditions. However, state-of-the-art models to compute counterfactuals are either unrealistic or unfeasible. In particular, while Pearl's causal inference provides appealing rules to calculate counterfactuals, it relies on a model that is unknown and hard to discover in practice. We address the problem of designing realistic and feasible counterfactuals in the absence of a causal model. We define transport-based counterfactual models as collections of joint probability distributions between observable distributions, and show their connection to causal counterfactuals. More specifically, we argue that optimal-transport theory defines relevant transport-based counterfactual models, as they are numerically feasible, statistically-faithful, and can coincide under some assumptions with causal counterfactual models. Finally, these models make counterfactual approaches to fairness feasible, and we illustrate their practicality and efficiency on fair learning. With this paper, we aim at laying out the theoretical foundations for a new, implementable approach to counterfactual thinking. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2024. ( edit, beta )

PDF Details

AAAI Conference 2022 Conference Paper

Tractable Explanations for d-DNNF Classifiers

  • Xuanxiang Huang
  • Yacine Izza
  • Alexey Ignatiev
  • Martin Cooper
  • Nicholas Asher
  • Joao Marques-Silva

Compilation into propositional languages finds a growing number of practical uses, including in constraint programming, diagnosis and machine learning (ML), among others. One concrete example is the use of propositional languages as classifiers, and one natural question is how to explain the predictions made. This paper shows that for classifiers represented with some of the best-known propositional languages, different kinds of explanations can be computed in polynomial time. These languages include deterministic decomposable negation normal form (d-DNNF), and so any propositional language that is strictly less succinct than d-DNNF. Furthermore, the paper describes optimizations, specific to Sentential Decision Diagrams (SDDs), which are shown to yield more efficient algorithms in practice.

PDF Details

AAMAS Conference 2021 Conference Paper

Interpretive Blindness and the Impossibility of Learning from Testimony

  • Nicholas Asher
  • Julie Hunter

We model interpretive blindness, a type of epistemic bias that poses a problem for learning from testimony, in which one acquires information from text or conversation but lacks direct access to ground truth. Interpretive blindness arises when a co-dependence between background beliefs and interpretation leads to a dynamic process of bias hardening that impedes or precludes learning. We argue that when bodies of data are argumentatively complete, even constraints from hierarchical Bayesian learning designed to promote good epistemic practices will fail to stop interpretive blindness.

PDF

ECAI Conference 2012 Conference Paper

Preference Extraction From Negotiation Dialogues

  • Anaïs Cadilhac
  • Nicholas Asher
  • Farah Benamara
  • Vladimir Popescu
  • Mohamadou Seck

This paper presents an NLP-based approach to extracting preferences from negotiation dialogues. We propose a new annotation scheme to study how preferences are linguistically expressed on two different corpus genres. We then automatically extract preferences in two steps: first, we extract the set of outcomes; then, we identify how these outcomes are ordered. We finally assess the reliability of our method on each corpus genre.

Details

IJCAI Conference 1995 Conference Paper

Toward a Geometry of Common Sense: A Semantics and a Complete Axiomatization of Mcreotopology

  • Nicholas Asher
  • Laure Vieu

Mereological and topological notions of connection, part, interior and complement are central to spatial reasoning and to the semantics of natural language expressions concerning locations and relative positions. While several authors have proposed axioms for these notions, no one with the exception of Tarski [18], who based his axiomatization of mereological notions on a Euclidean metric, has attempted to give them a semantics. We offer an alternative to Tarski, starting with mereotopological notions that have proved useful in the semantic analysis of spatial expressions. We also give a complete axiomatization of this account of mereotopological reasoning.

PDF
v2026.09.13