Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation

Staliūnaitė, Ieva; Gorinski, Philip John; Iacobacci, Ignacio

doi:10.48550/arxiv.2101.04966

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While recently adverserial approaches (Staliūnaitė et al, 2021) have been proposed, a core point is that models that can explain human plausible reasoning need some form of symbolic form to understand how these systems reason and use knowledge.…”

Section: D) Nervously Sets Her Fingers On the Keysmentioning

confidence: 99%

Modeling Associative Reasoning Processes

Schon¹,

Furbach²,

Ragni³

2022

Preprint

View full text Add to dashboard Cite

The human capability to reason about one domain by using knowledge of other domains has been researched for more than 50 years, but models that are formally sound and predict cognitive process are sparse. We propose a formally sound method that models associative reasoning by adapting logical reasoning mechanisms. In particular it is shown that the combination with large commensense knowledge within a single reasoning system demands for an efficient and powerful association technique. This approach is also used for modelling mind-wandering and the Remote Associates Test (RAT) for testing creativity. In a general discussion we show implications of the model for a broad variety of cognitive phenomena including consciousness.

show abstract

Section: D) Nervously Sets Her Fingers On the Keysmentioning

confidence: 99%

Modeling Associative Reasoning Processes

Schon¹,

Furbach²,

Ragni³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…They used combinations of dropout and adversarial example for evaluation. Another work[97] proposed data augmentation for adversarial training for increasing the robustness of casual reasoning task. The proposed data augmentation by synonym substitution and by filtering out casually linked clauses in the larger dataset and used generative language models to generate distractor sentences as potential adversarial examples.…”

mentioning

confidence: 99%

A survey in Adversarial Defences and Robustness in NLP

Goyal¹,

Doddapaneni²,

Khapra³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, it has been seen that deep neural networks are lacking robustness and are likely to break in case of adversarial perturbations in input data. Strong adversarial attacks are proposed by various authors for computer vision and Natural Language Processing (NLP). As a counter-effort, several defense mechanisms are also proposed to save these networks from failing. In contrast with image data, generating adversarial attacks and defending these models is not easy in NLP because of the discrete nature of the text data. However, numerous methods for adversarial defense are proposed of late, for different NLP tasks such as text classification, named entity recognition, natural language inferencing, etc. These methods are not just used for defending neural networks from adversarial attacks, but also used as a regularization mechanism during training, saving the model from overfitting. The proposed survey is an attempt to review different methods proposed for adversarial defenses in NLP in the recent past by proposing a novel taxonomy. This survey also highlights the fragility of the advanced deep neural networks in NLP and the challenges in defending them.

show abstract

Improving Commonsense Causal Reasoning by Adversarial Training and Data Augmentation

Cited by 2 publications

References 0 publications

Modeling Associative Reasoning Processes

Modeling Associative Reasoning Processes

A survey in Adversarial Defences and Robustness in NLP

Contact Info

Product

Resources

About