Search Results for author:
Found 35 papers, 2 papers with code
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks
COCKATIEL is a novel, post-hoc, concept-based, model-agnostic XAI technique that generates meaningful explanations from the last layer of a neural net model trained on an NLP classification task by using Non-Negative Matrix Factorization (NMF) to discover the concepts the model leverages to make predictions and by exploiting a Sensitivity Analysis to estimate accurately the importance of each of these concepts for the model.
How optimal transport can tackle gender biases in multi-class neural-network classifiers for job recommendations?
To anticipate the certification of recommendation systems using textual data, we then used it on the Bios dataset, for which the learning task consists in predicting the occupation of female and male individuals, based on their LinkedIn biography.
Analyzing Semantic Faithfulness of Language Models via Input Intervention on Conversational Question Answering
While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention).
Interpretive Blindness
We model here an epistemic bias we call \textit{interpretive blindness} (IB).
Transport-based Counterfactual Models
We address the problem of designing realistic and feasible counterfactuals in the absence of a causal model.
Efficient Explanations for Knowledge Compilation Languages
Knowledge compilation (KC) languages find a growing number of practical uses, including in Constraint Programming (CP) and in Machine Learning (ML).
On Relating "Why?" and "Why Not?" Explanations
Explanations of Machine Learning (ML) models often address a ‘Why?’ question.
Adequate and fair explanations
This partiality makes it possible to hide explicit biases present in the algorithm that may be injurious or unfair. We investigate how easy it is to uncover these biases in providing complete and fair explanations by exploiting the structure of the set of counterfactuals providing a complete local explanation.
Weak Supervision for Learning Discourse Structure
We show that on our task the generative model outperforms both deep learning architectures as well as more traditional ML approaches when learning discourse structure{---}it even outperforms the combination of deep learning methods and hand-crafted features.
Apprentissage faiblement supervis\'e de la structure discursive (Learning discourse structure using weak supervision )
Nous d{\'e}crivons nos exp{\'e}rimentations sur l{'}attachement des unit{\'e}s discursives pour former une structure, en utilisant le paradigme du data programming dans lequel peu ou pas d{'}annotations sont utilis{\'e}es pour construire un ensemble de donn{\'e}es d{'}entra{\^\i}nement {``}bruit{\'e}{''}.
Analyse faiblement supervis\'ee de conversation en actes de dialogue (Weakly supervised dialog act analysis)
Nous nous int{\'e}ressons ici {\`a} l{'}analyse de conversation par chat dans un contexte orient{\'e}-t{\^a}che avec un conseiller technique s{'}adressant {\`a} un client, o{\`u} l{'}objectif est d{'}{\'e}tiqueter les {\'e}nonc{\'e}s en actes de dialogue, pour alimenter des analyses des conversations en aval.
Data Programming for Learning Discourse Structure
This paper investigates the advantages and limits of data programming for the task of learning discourse structure.
Bias in Semantic and Discourse Interpretation
In this paper, we show how game-theoretic work on conversation combined with a theory of discourse structure provides a framework for studying interpretive bias.
A Dependency Perspective on RST Discourse Parsing and Evaluation
This allows us to characterize families of parsing strategies across the different frameworks, in particular with respect to the notion of headedness.
How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT
This article evaluates purported progress over the past years in RST discourse parsing.
Parallel Discourse Annotations on a Corpus of Short Texts
We present the first corpus of texts annotated with two alternative approaches to discourse structure, Rhetorical Structure Theory (Mann and Thompson, 1988) and Segmented Discourse Representation Theory (Asher and Lascarides, 2003).
Discourse Structure and Dialogue Acts in Multiparty Dialogue: the STAC Corpus
This paper describes the STAC resource, a corpus of multi-party chats annotated for discourse structure in the style of SDRT (Asher and Lascarides, 2003; Lascarides and Asher, 2009).
An empirical resource for discovering cognitive principles of discourse organisation: the ANNODIS corpus
This paper describes the ANNODIS resource, a discourse-level annotated corpus for French.
