Related papers: Creating and Querying Personalized Versions of Wik…
The search for relevant information can be very frustrating for users who, unintentionally, use too general or inappropriate keywords to express their requests. To overcome this situation, query expansion techniques aim at transforming the…
Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observable in the…
A fundamental challenge in the current NLP context, dominated by language models, comes from the inflexibility of current architectures to 'learn' new information. While model-centric solutions like continual learning or parameter-efficient…
Most people do not interact with Semantic Web data directly. Unless they have the expertise to understand the underlying technology, they need textual or visual interfaces to help them make sense of it. We explore the problem of generating…
This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and has high conversationality and low latency. WikiChat is grounded on the English Wikipedia, the largest curated free-text corpus. WikiChat generates…
Knowledge graphs have been adopted in many diverse fields for a variety of purposes. Most of those applications rely on valid and complete data to deliver their results, pressing the need to improve the quality of knowledge graphs. A number…
We introduce a new reading comprehension dataset, dubbed MultiWikiQA, which covers 306 languages and has 1,220,757 samples in total. We start with Wikipedia articles, which also provide the context for the dataset samples, and use an LLM to…
In the era of big and ubiquitous data, professionals and students alike are finding themselves needing to perform a number of textual analysis tasks. Historically, the general lack of statistical expertise and programming skills has stopped…
Most of the world's data is stored in relational databases. Accessing these requires specialized knowledge of the Structured Query Language (SQL), putting them out of the reach of many people. A recent research thread in Natural Language…
KGCleaner is a framework to identify and correct errors in data produced and delivered by an information extraction system. These tasks have been understudied and KGCleaner is the first to address both. We introduce a multi-task model that…
Linked Open Data (LOD) has been proliferated over various domains, however, there are still lots of open data in various format other than RDF, a standard data description framework in LOD. These open data can also be connected to entities…
Computational notebook software such as Jupyter Notebook is popular for data science tasks. Numerous computational notebooks are available on the Web and reusable; however, searching for computational notebooks manually is a tedious task,…
There is a gap between how people explore data and how Jupyter-like computational notebooks are designed. People explore data nonlinearly, using execution undos, branching, and/or complete reverts, whereas notebooks are designed for…
Literate programming - the bringing together of program code and natural language narratives - has become a ubiquitous approach in the realm of data science. This methodology is appealing as well for the domain of Density Functional Theory…
Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the…
Currently, personal assistant systems, run on smartphones and use natural language interfaces. However, these systems rely mostly on the web for finding information. Mobile and wearable devices can collect an enormous amount of contextual…
The ability to generate SQL queries from natural language has significant implications for making data accessible to non-specialists. This paper presents a novel approach to fine-tuning open-source large language models (LLMs) for the task…
Wikidata and Wikipedia have been proven useful for reason-ing in natural language applications, like question answering or entitylinking. Yet, no existing work has studied the potential of Wikidata for commonsense reasoning. This paper…
This paper presents an in-depth analysis of Wikidata qualifiers, focusing on their semantics and actual usage, with the aim of developing a taxonomy that addresses the challenges of selecting appropriate qualifiers, querying the graph, and…
The adoption of Semantic Web technologies, and in particular the Open Data initiative, has contributed to the steady growth of the number of datasets and triples accessible on the Web. Most commonly, queries over RDF data are evaluated over…