Related papers: Improving Commonsense Causal Reasoning by Adversar…

Previous studies have shown the efficacy of knowledge augmentation methods in pretrained language models. However, these methods behave differently across domains and downstream tasks. In this work, we investigate the augmentation of…

Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcome. For natural language inference tasks, previous results…

Story generation, namely generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2)…

Reading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation. Training with adversarially augmented dataset improves robustness against those adversarial attacks but hurts generalization of…

Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with…

We present DiscoSense, a benchmark for commonsense reasoning via understanding a wide variety of discourse connectives. We generate compelling distractors in DiscoSense using Conditional Adversarial Filtering, an extension of Adversarial…

This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…

Generative commonsense reasoning is the capability of a language model to generate a sentence with a given concept-set that is based on commonsense knowledge. However, generative language models still struggle to provide outputs, and the…

When people reason about cause and effect, they often consider many competing "what if" scenarios before deciding which explanation fits best. Analogously, advanced language models capable of causal inference can consider multiple…

Causal reasoning and logical reasoning are two important types of reasoning abilities for human intelligence. However, their relationship has not been extensively explored under machine intelligence context. In this paper, we explore how…

Tailoring persuasive conversations to users leads to more effective persuasion. However, existing dialogue systems often struggle to adapt to dynamically evolving user states. This paper presents a novel method that leverages causal…

Contextualized or discourse aware commonsense inference is the task of generating coherent commonsense assertions (i.e., facts) from a given story, and a particular sentence from that story. Some problems with the task are: lack of…

Healthcare data often come from multiple sites in which the correlations between confounding variables can vary widely. If deep learning models exploit these unstable correlations, they might fail catastrophically in unseen sites. Although…

Wake-up word detection models are widely used in real life, but suffer from severe performance degradation when encountering adversarial samples. In this paper we discuss the concept of confusing words in adversarial samples. Confusing…

Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even…

Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

Memorizing and utilizing speakers' personas is a common practice for response generation in long-term conversations. Yet, human-authored datasets often provide uninformative persona sentences that hinder response quality. This paper…

Commonsense reasoning is intuitive for humans but has been a long-term challenge for artificial intelligence (AI). Recent advancements in pretrained language models have shown promising results on several commonsense benchmark datasets.…

With the rise of Large Language Models(LLMs), it has become crucial to understand their capabilities and limitations in deciphering and explaining the complex web of causal relationships that language entails. Current methods use either…