Related papers: Pre-training for Information Retrieval: Are Hyperl…
Machine reading comprehension is a heavily-studied research and test field for evaluating new pre-trained language models (PrLMs) and fine-tuning strategies, and recent studies have enriched the pre-trained language models with syntactic,…
Document-level relation extraction (DocRE) poses the challenge of identifying relationships between entities within a document as opposed to the traditional RE setting where a single sentence is input. Existing approaches rely on logical…
How to leverage cross-document interactions to improve ranking performance is an important topic in information retrieval (IR) research. However, this topic has not been well-studied in the learning-to-rank setting and most of the existing…
We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering. Using web screenshots unlocks a treasure trove of visual and…
Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks. However, conventional pre-training objectives do not explicitly model relational facts in text, which are…
Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of ``\textit{Small Language Model (SLM) + Classifier}''.…
Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while…
Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures,…
Modelling relations between multiple entities has attracted increasing attention recently, and a new dataset called DocRED has been collected in order to accelerate the research on the document-level relation extraction. Current baselines…
Nowadays, learning increasingly involves the usage of search engines and web resources. The related interdisciplinary research field search as learning aims to understand how people learn on the web. Previous work has investigated several…
Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word…
Word vectors and Language Models (LMs) pretrained on a large amount of unlabelled data can dramatically improve various Natural Language Processing (NLP) tasks. However, the measure and impact of similarity between pretraining data and…
Ranking has always been one of the top concerns in information retrieval research. For decades, lexical matching signal has dominated the ad-hoc retrieval process, but it also has inherent defects, such as the vocabulary mismatch problem.…
Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document…
We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike existing pre-training methods that only harvest learning signals…
Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…
In order to assist security analysts in obtaining information pertaining to their network, such as novel vulnerabilities, exploits, or patches, information retrieval methods tailored to the security domain are needed. As labeled text data…
We consider algorithm selection in the context of ad-hoc information retrieval. Given a query and a pair of retrieval methods, we propose a meta-learner that predicts how to combine the methods' relevance scores into an overall relevance…
While large-scale pre-trained language models like BERT have advanced the state-of-the-art in IR, its application in query performance prediction (QPP) is so far based on pointwise modeling of individual queries. Meanwhile, recent studies…
Internet links enable users to deepen their understanding of a topic by providing convenient access to related information. However, the majority of links are unanchored -- they link to a target webpage as a whole, and readers may expend…