Related papers: WebFAQ 2.0: A Multilingual QA Dataset with Mined H…

Question answering and conversational systems are often baffled and need help clarifying certain ambiguities. However, limitations of existing datasets hinder the development of large-scale models capable of generating and utilising…

To combat phishing attacks -- aimed at luring web users to divulge their sensitive information -- various phishing detection approaches have been proposed. As attackers focus on devising new tactics to bypass existing detection solutions,…

In this work, we develop and release Yuan 2.0, a series of large language models with parameters ranging from 2.1 billion to 102.6 billion. The Localized Filtering-based Attention (LFA) is introduced to incorporate prior knowledge of local…

We introduce Mintaka, a complex, natural, and multilingual dataset designed for experimenting with end-to-end question-answering models. Mintaka is composed of 20,000 question-answer pairs collected in English, annotated with Wikidata…

With the rise of online education platforms, there is a growing abundance of educational content across various domain. It can be difficult to navigate the numerous available resources to find the most suitable training, especially in…

Sentiment analysis for the Bengali language has attracted increasing research interest in recent years. However, progress remains constrained by the scarcity of large-scale and diverse annotated datasets. Although several Bengali sentiment…

Conversational search provides a natural interface for information retrieval (IR). Recent approaches have demonstrated promising results in applying dense retrieval to conversational IR. However, training dense retrievers requires large…

Over the past few years, we have built a system that has exposed large volumes of Deep-Web content to Google.com users. The content that our system exposes contributes to more than 1000 search queries per-second and spans over 50 languages…

Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that both are suboptimal, since…

The World Wide Web is not only one of the most important platforms of communication and information at present, but also an area of growing interest for scientific research. This motivates a lot of work and projects that require large…

The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to answer. It has been observed that the original dataset is…

Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face the application scenario of retrieving…

We introduce a large scale MAchine Reading COmprehension dataset, which we name MS MARCO. The dataset comprises of 1,010,916 anonymized questions---sampled from Bing's search query logs---each with a human generated answer and 182,669…

A riddle is a question or statement with double or veiled meanings, followed by an unexpected answer. Solving riddle is a challenging task for both machine and human, testing the capability of understanding figurative, creative natural…

Dense retrieval is a basic building block of information retrieval applications. One of the main challenges of dense retrieval in real-world settings is the handling of queries containing misspelled words. A popular approach for handling…

Retrieval-Augmented Generation (RAG) is a cornerstone of modern question answering (QA) systems, enabling grounded answers based on external knowledge. Although recent progress has been driven by open-domain datasets, enterprise QA systems…

Though exponentially growing health-related literature has been made available to a broad audience online, the language of scientific articles can be difficult for the general public to understand. Therefore, adapting this expert-level…

While natural language processing tools have been developed extensively for some of the world's languages, a significant portion of the world's over 7000 languages are still neglected. One reason for this is that evaluation datasets do not…

Thanks to the development of the Semantic Web, a lot of new structured data has become available on the Web in the form of knowledge bases (KBs). Making this valuable data accessible and usable for end-users is one of the main goals of…

Training robust retrieval and reranker models typically relies on large-scale retrieval datasets; for example, the BGE collection contains 1.6 million query-passage pairs sourced from various data sources. However, we find that certain…