Related papers: DenseReviewer: A Screening Prioritisation Tool for…
We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily available. Each model…
In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent…
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.…
Deep neural network models represent the state-of-the-art methodologies for natural language processing. Here we build on top of these methodologies to incorporate temporal information and model how to review data changes with time.…
We propose a tool for experts finding applied to academic data generated by the start-up DSRT in the context of its application Peerus. A user may submit the title, the abstract and optionnally the authors and the journal of publication of…
The practice of unit testing enables programmers to obtain automated feedback on whether a currently edited program is consistent with the expectations specified in test cases. Feedback is most valuable when it happens immediately, as…
A comprehensive literature review has always been an essential first step of every meaningful research. In recent years, however, the availability of a vast amount of information in both open-access and subscription-based literature in…
Dense retrieval has become the new paradigm in passage retrieval. Despite its effectiveness on typo-free queries, it is not robust when dealing with queries that contain typos. Current works on improving the typo-robustness of dense…
The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and…
Systematic literature reviews play a vital role in identifying the best available evidence for health and social care policy. The resources required to produce systematic reviews can be significant, and a key to the success of any review is…
Searching, filtering and analysing scientific literature are time-consuming tasks when performing a systematic literature review. With the rise of artificial intelligence, some steps in the review process are progressively being automated.…
Deep learning models have become essential in software engineering, enabling intelligent features like image captioning and document generation. However, their popularity raises concerns about environmental impact and inefficient model…
Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the information retrieval…
Retrieval module can be plugged into many downstream NLP tasks to improve their performance, such as open-domain question answering and retrieval-augmented generation. The key to a retrieval system is to calculate relevance scores to query…
When medical researchers conduct a systematic review (SR), screening studies is the most time-consuming process: researchers read several thousands of medical literature and manually label them relevant or irrelevant. Screening…
Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality…
Conducting systematic reviews is laborious. In the screening or study selection phase, the number of papers can be overwhelming. Recent research has demonstrated that large language models (LLMs) can perform title-abstract screening and…
Pre-trained transformer-based language models are becoming increasingly popular due to their exceptional performance on various benchmarks. However, concerns persist regarding the presence of hidden biases within these models, which can…
Conducting systematic reviews (SR) is a time consuming endeavor that requires several iterations to setup right. We present ReLiS, a framework to configure and deploy projects while conducting a SR. It features a domain-specific modeling…
Deploying dense retrieval models efficiently is becoming increasingly important across various industries. This is especially true for enterprise search services, where customizing search engines to meet the time demands of different…