Related papers: Memento: Time Travel for the Web
Retrieving information from correlative paragraphs or documents to answer open-domain multi-hop questions is very challenging. To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose…
Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…
Social media content has grown exponentially in the recent years and the role of social media has evolved from just narrating life events to actually shaping them. In this paper we explore how many resources shared in social media are still…
The problem of finding a resource residing in a network node (the \emph{resource location problem}) is a challenge in complex networks due to aspects as network size, unknown network topology, and network dynamics. The problem is especially…
Retrieval-augmented generation over semi-structured sources such as HTML is constrained by a mismatch between document structure and the flat, sequence-based interfaces of today's embedding and generative models. Retrieval pipelines often…
Despite advances in multimodal large language models, autonomous web agents still struggle to reliably execute long-horizon tasks on complex and dynamic web interfaces. Existing agents often suffer from inaccurate element grounding, the…
In this paper, we propose a new event memory architecture (MemNet) for recurrent neural networks, which is universal for different types of time series data such as scalar, multivariate or symbolic. Unlike other external neural memory…
The increasing amount of personal and sensitive information disseminated over the Internet prompts commensurately growing privacy concerns. Digital data often lingers indefinitely and users lose its control. This motivates the desire to…
Is software obsolescence a significant risk? To explore this issue, we analysed a corpus of over 2.5 billion resources corresponding to the UK Web domain, as crawled between 1996 and 2010. Using the DROID and Apache Tika identification…
The competitive analysis fails to model locality of reference in the online paging problem. To deal with it, Borodin et. al. introduced the access graph model, which attempts to capture the locality of reference. However, the access graph…
Range filters are probabilistic data structures that answer approximate range emptiness queries. They aid in avoiding processing empty range queries and have use cases in many application domains such as key-value stores and social web…
Over the last decades the Web has evolved from a human-human communication network to a network of complex human-machine interactions. An increasing amount of data is available as Linked Data which allows machines to "understand" the data,…
Thanks to the wide range of features offered by web browsers, modern websites include various types of content such as JavaScript and CSS in order to create interactive user interfaces. Browser vendors also provided extensions to enhance…
The temporal phenomena have many facets that are studied by different communities. In Semantic Web, large heterogeneous data are handled and produced. These data often have informal, semi-formal or formal temporal information which must be…
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…
Shared reference is an essential aspect of meaning. It is also indispensable for the semantic web, since it enables to weave the global graph, i.e., it allows different users to contribute to an identical referent. For example, an essential…
The web is the prominent way information is exchanged in the 21st century. However, ensuring web-based information is accessible is complicated, particularly with web applications that rely on JavaScript and other technologies to deliver…
Search engines provide cached copies of indexed content so users will have something to "click on" if the remote resource is temporarily or permanently unavailable. Depending on their proprietary caching strategies, search engines will…
In the course of web research it is often necessary to estimate the creation datetime for web resources (in the general case, this value can only be estimated). While it is feasible to manually establish likely datetime values for small…
Despite its troubled past, the AOL Query Log continues to be an important resource to the research community -- particularly for tasks like search personalisation. When using the query log these ranking experiments, little attention is…