Related papers: Laughing Heads: Can Transformers Detect What Makes…

The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master. Puns, in particular, add the challenge of fusing that knowledge with the ability to…

Scene text recognition with arbitrary shape is very challenging due to large variations in text shapes, fonts, colors, backgrounds, etc. Most state-of-the-art algorithms rectify the input image into the normalized image, then treat the…

Nobody knows how language works, but many theories abound. Transformers are a class of neural networks that process language automatically with more success than alternatives, both those based on neural computations and those that rely on…

This paper explores the use of Deep Learning methods for automatic estimation of quality of human translations. Automatic estimation can provide useful feedback for translation teaching, examination and quality control. Conventional methods…

Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer…

A significant challenge in automating hate speech detection on social media is distinguishing hate speech from regular and offensive language. These identify an essential category of content that web filters seek to remove. Only automated…

Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpretable word alignments. In this paper, we show that NMT models…

Humor is a unique and creative communicative behavior displayed during social interactions. It is produced in a multimodal manner, through the usage of words (text), gestures (vision) and prosodic cues (acoustic). Understanding humor from…

The computer realization of a "sense of humour" requires the creation of an algorithm for solving the "linguistic problem", i.e. the problem of recognizing a continuous sequence of polysemantic images. Such algorithm may be realized in the…

Humor is a fundamental aspect of human communication and cognition, as it plays a crucial role in social engagement. Although theories about humor have evolved over centuries, there is still no agreement on a single, comprehensive humor…

This paper presents OxfordTVG-HIC (Humorous Image Captions), a large-scale dataset for humour generation and understanding. Humour is an abstract, subjective, and context-dependent cognitive construct involving several cognitive factors,…

Native speakers can judge whether a sentence is an acceptable instance of their language. Acceptability provides a means of evaluating whether computational language models are processing language in a human-like manner. We test the ability…

In this paper we investigate the explainability of transformer models and their plausibility for hate speech and counter speech detection. We compare representatives of four different explainability approaches, i.e., gradient-based,…

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…

Emotion detection is a central problem in NLP, with recent progress driven by transformer-based models trained on established datasets. However, little is known about the linguistic regularities that characterize how emotions are expressed…

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

Attention mechanisms have recently boosted performance on a range of NLP tasks. Because attention layers explicitly weight input components' representations, it is also often assumed that attention can be used to identify information that…

Annotating abusive language is expensive, logistically complex and creates a risk of psychological harm. However, most machine learning research has prioritized maximizing effectiveness (i.e., F1 or accuracy score) rather than data…

Legal texts routinely use concepts that are difficult to understand. Lawyers elaborate on the meaning of such concepts by, among other things, carefully investigating how have they been used in past. Finding text snippets that mention a…

Transformer-based language models are effective but complex, and understanding their inner workings and reasoning mechanisms is a significant challenge. Previous research has primarily explored how these models handle simple tasks like name…