Related papers: WIKITIDE: A Wikipedia-Based Timestamped Definition…
In the evolving field of Natural Language Processing (NLP), understanding the temporal context of text is increasingly critical for applications requiring advanced temporal reasoning. Traditional pre-trained language models like BERT, which…
Topic modeling algorithms traditionally model topics as list of weighted terms. These topic models can be used effectively to classify texts or to support text mining tasks such as text summarization or fact extraction. The general…
Acknowledged as one of the most successful online cooperative projects in human society, Wikipedia has obtained rapid growth in recent years and desires continuously to expand content and disseminate knowledge values for everyone globally.…
Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a previously untapped…
The advent of neural-networks in NLP brought with it substantial improvements in supervised relation extraction. However, obtaining a sufficient quantity of training data remains a key challenge. In this work we propose a process for…
The vast amount of online information today poses challenges for non-English speakers, as much of it is concentrated in high-resource languages such as English and French. Wikipedia reflects this imbalance, with content in low-resource…
Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge -- their types. Previous methods to learn entity types rely on training classifiers on datasets with coarse, noisy, and…
The wealth of structured (e.g. Wikidata) and unstructured data about the world available today presents an incredible opportunity for tomorrow's Artificial Intelligence. So far, integration of these two different modalities is a difficult…
Natural Language Inference (NLI) has been extensively studied by the NLP community as a framework for estimating the semantic relation between sentence pairs. While early work identified certain biases in NLI models, recent advancements in…
Pretrained Transformer models have emerged as state-of-the-art approaches that learn contextual information from text to improve the performance of several NLP tasks. These models, albeit powerful, still require specialized knowledge in…
Text simplification research has mostly focused on sentence-level simplification, even though many desirable edits - such as adding relevant background information or reordering content - may require document-level context. Prior work has…
Our research focuses on solving the zero-shot text classification problem in NLP, with a particular emphasis on innovative self-training strategies. To achieve this objective, we propose a novel self-training strategy that uses labels…
Temporal Point Processes (TPPs) have been widely used for modeling event sequences on the Web, such as user reviews, social media posts, and online transactions. However, traditional TPP models often struggle to effectively incorporate the…
Textual entailment models are increasingly applied in settings like fact-checking, presupposition verification in question answering, or summary evaluation. However, these represent a significant domain shift from existing entailment…
Many researchers have made use of the Wikipedia network for relatedness and similarity tasks. However, most approaches use only the most recent information and not historical changes in the network. We provide an analysis of entity…
The milestone improvements brought about by deep representation learning and pre-training techniques have led to large performance gains across downstream NLP, IR and Vision tasks. Multimodal modeling techniques aim to leverage large…
Temporal concept drift refers to the problem of data changing over time. In NLP, that would entail that language (e.g. new expressions, meaning shifts) and factual knowledge (e.g. new concepts, updated facts) evolve over time. Focusing on…
Despite recent progress in computer vision, finegrained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we construct a novel dataset called WikiSatNet by…
We present a simple but effective approach for leveraging Wikipedia for neural machine translation as well as cross-lingual tasks of image captioning and dependency parsing without using any direct supervision from external parallel data or…
The limited size of existing query-focused summarization datasets renders training data-driven summarization models challenging. Meanwhile, the manual construction of a query-focused summarization corpus is costly and time-consuming. In…