Related papers: Fast End-to-End Wikification
Data quality has become a key factor in enhancing model performance with the rapid development of large language models (LLMs). Model-driven data filtering has increasingly become a primary approach for acquiring high-quality data. However,…
The World Wide Web (WWW) is the repository of large number of web pages which can be accessed via Internet by multiple users at the same time and therefore it is Ubiquitous in nature. The search engine is a key application used to search…
Regularization by denoising (RED) is a powerful framework for solving imaging inverse problems. Most RED algorithms are iterative batch procedures, which limits their applicability to very large datasets. In this paper, we address this…
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…
Content moderation in online platforms is crucial for ensuring activity therein adheres to existing policies, especially as these platforms grow. NLP research in this area has typically focused on automating some part of it given that it is…
Mathematical information retrieval (MathIR) applications such as semantic formula search and question answering systems rely on knowledge-bases that link mathematical expressions to their natural language names. For database population,…
Large datasets of paired images and text have become increasingly popular for learning generic representations for vision and vision-and-language tasks. Such datasets have been built by querying search engines or collecting HTML alt-text --…
The digital revolution has brought most of the world on the world wide web. The data available on WWW has increased many folds in the past decade. Social networks, online clubs and organisations have come into existence. Information is…
Wikipedia can be edited by anyone and thus contains various quality sentences. Therefore, Wikipedia includes some poor-quality edits, which are often marked up by other editors. While editors' reviews enhance the credibility of Wikipedia,…
With the growth of the Semantic Web in size and importance, more and more knowledge is stored in machine-readable formats such as the Web Ontology Language OWL. This paper outlines common approaches for efficient reasoning on large-scale…
With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supervising and enhancing these powerful models using smaller,…
Commercial establishments like restaurants, service centres and retailers have several sources of customer feedback about products and services, most of which need not be as structured as rated reviews provided by services like Yelp, or…
While large language models (LLMs) can answer many questions correctly, they can also hallucinate and give wrong answers. Wikidata, with its over 12 billion facts, can be used to ground LLMs to improve their factuality. This paper presents…
Learned reweighting (LRW) approaches to supervised learning use an optimization criterion to assign weights for training instances, in order to maximize performance on a representative validation dataset. We pose and formalize the problem…
Wikipedia is a critical resource for modern NLP, serving as a rich repository of up-to-date and citation-backed information on a wide variety of subjects. The reliability of Wikipedia -- its groundedness in its cited sources -- is vital to…
Using deep learning for different machine learning tasks such as image classification and word embedding has recently gained many attentions. Its appealing performance reported across specific Natural Language Processing (NLP) tasks in…
Previous work on Entity Linking has focused on resources targeting non-nested proper named entity mentions, often in data from Wikipedia, i.e. Wikification. In this paper, we present and evaluate WikiGUM, a fully wikified dataset, covering…
This paper introduces an approach to question answering over knowledge bases like Wikipedia and Wikidata by performing "question-to-question" matching and retrieval from a dense vector embedding store. Instead of embedding document content,…
Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is…
Verifiability is a core content policy of Wikipedia: claims that are likely to be challenged need to be backed by citations. There are millions of articles available online and thousands of new articles are released each month. For this…