Papers by Samuel Carton

8 papers
Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Dataset (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for ad-hoc schema-based information extraction are brittle and non-transferable, limiting their practicality for this type of one-off extraction task.
Approach: They propose to use GPT-4 to perform ad-hoc schema-based information extraction from scientific literature.
Outcome: The proposed model can replicate two existing material science datasets, one pertaining to multi-principal element alloys and one to silicate diffusion, and draw on their insights to suggest future research directions.
Human-Centered Evaluation of Explanations (2022.naacl-tutorials)

Copied to clipboard

Challenge: This tutorial will provide an overview of human-centered evaluations of explanations .
Approach: This tutorial will provide an overview of human-centered evaluations of explanations . it will introduce the psychological foundation of explanation and types of NLP explanations.
Outcome: This tutorial will provide an overview of human-centered evaluations of explanations . it will cover the two categories of evaluation: evaluation based on human-annotated explanations and evaluation with human-subjects studies.
What to Learn, and How: Toward Effective Learning from Rationales (2022.findings-acl)

Copied to clipboard

Challenge: Increasing interest in learning from rationales has led to the use of human-annotated explanations to inject useful inductive biases into models.
Approach: They propose several novel loss functions and learning strategies to exploit human rationales to augment model prediction accuracy.
Outcome: The proposed learning strategies improve on three datasets with human rationales and show that they are more efficient than baselines.
Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation (D19-1)

Copied to clipboard

Challenge: Existing evaluation methods for natural language generation are inadequate . distinguishing machine-generated text is challenging even for human evaluators .
Approach: They compare human-based evaluators with automated evaluation procedures . they find human evaluers do not correlate well with discriminative evalators .
Outcome: The proposed evaluation methods are compared with a dozen state-of-the-art generators for online product reviews.
Evaluating and Characterizing Human Rationales (2020.emnlp-main)

Copied to clipboard

Challenge: a new study examines how human rationales perform on automatic metrics . human-generated rationale evaluation is difficult because of its ambiguity .
Approach: They propose to use model-dependent baseline performance to evaluate rationale quality . they propose to also use "fidelity curves" to reveal properties such as irrelevance and redundancy .
Outcome: The proposed methods characterize rationale quality based on model retraining and using "fidelity curves" the proposed methods lead to actionable suggestions for evaluating and characterizing rationales .
Learning to Ignore Adversarial Attacks (2023.eacl-main)

Copied to clipboard

Challenge: Despite the strong performance of current NLP models, they can be brittle against adversarial inputs.
Approach: They propose a rationale model that explicitly learns to ignore adversarial tokens . their approach leads to sizable improvements in robustness over baseline models .
Outcome: The proposed model outperforms data augmentation with adversarial examples and closes the gap between model performance and an attacked test set.
Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts (D18-1)

Copied to clipboard

Challenge: Existing work on explaining classifier decisions has not addressed local feature redundancy . a common way to explain why a model classified an example is to extract a sparse subset of features that were responsible for the decision .
Approach: They propose an adversarial method for producing high-recall explanations of text classifier decisions . they use a method which scans the residual of attention for remaining predictive signal .
Outcome: The proposed method produces high-recall explanations of text classifier decisions . it uses a set of human-annotated personal attacks to evaluate the impact .
Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification (2021.acl-long)

Copied to clipboard

Challenge: Text simplification reduces the language complexity of professional content for accessibility purposes.
Approach: They propose that text simplification can be decomposed into a pipeline of tasks . they show that the pipeline can be used to predict whether a text needs to be simplified .
Outcome: The proposed model improves the performance of out-of-sample simplification tests on a blackbox lexical model . the proposed model reduces the complexity of professional text by a large margin .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations