Related papers: Information Type Classification with Contrastive T…

Writers such as journalists often use automatic tools to find relevant content to include in their narratives. In this paper, we focus on supporting writers in the news domain to develop event-centric narratives. Given an incomplete…

Media plays an important role in shaping public opinion. Biased media can influence people in undesirable directions and hence should be unmasked as such. We observe that featurebased and neural text classification approaches which rely…

The detection of hate speech online has become an important task, as offensive language such as hurtful, obscene and insulting content can harm marginalized people or groups. This paper presents TU Berlin team experiments and results on the…

Small class-imbalanced datasets, common in many high-level semantic tasks like discourse analysis, present a particular challenge to current deep-learning architectures. In this work, we perform an extensive analysis on sentence-level…

The interplay between the image and comment on a social media post is one of high importance for understanding its overall message. Recent strides in multimodal embedding models, namely CLIP, have provided an avenue forward in relating…

Text classification is crucial for applications such as sentiment analysis and toxic text filtering, but it still faces challenges due to the complexity and ambiguity of natural language. Recent advancements in deep learning, particularly…

In this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks across a number of diverse language pairs. We first treat…

Encoder-decoder models have achieved remarkable success in abstractive text summarization, which aims to compress one or more documents into a shorter version without the loss of the essential content. Unfortunately, these models mostly…

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or…

Identifying related entities and events within and across documents is fundamental to natural language understanding. We present an approach to entity and event coreference resolution utilizing contrastive representation learning. Earlier…

We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text encoder, SuperClass directly utilizes tokenized raw text as…

Effectively modeling text-rich fresh content such as news articles at document-level is a challenging problem. To ensure a content-based model generalize well to a broad range of applications, it is critical to have a training dataset that…

The remarkable success of Artificial Intelligence in advancing automated decision-making is evident both in academia and industry. Within the plethora of applications, ranking systems hold significant importance in various domains. This…

Since state-of-the-art approaches to offensive language detection rely on supervised learning, it is crucial to quickly adapt them to the continuously evolving scenario of social media. While several approaches have been proposed to tackle…

Pre-trained models for Czech Natural Language Processing are often evaluated on purely linguistic tasks (POS tagging, parsing, NER) and relatively simple classification tasks such as sentiment classification or article classification from a…

Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a method of generating…

Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach…

Tasks such as semantic search and clustering on crisis-related social media texts enhance our comprehension of crisis discourse, aiding decision-making and targeted interventions. Pre-trained language models have advanced performance in…

Contrastive learning has achieved impressive success in generation tasks to militate the "exposure bias" problem and discriminatively exploit the different quality of references. Existing works mostly focus on contrastive learning on the…

Large knowledge bases typically contain data adhering to various schemas with incomplete and/or noisy type information. This seriously complicates further integration and post-processing efforts, as type information is crucial in correctly…