1

We enhance multi-label classification model in the perspective of model, data, and evalution, using a BiEncoder-CrossEncoder based label ranking model, active learning and ChatGPT.

Label aggregation (LA) is the task of inferring a high-quality label for an example from multiple noisy labels generated by either …

We build a semantic search engine on scientific articles. The major challenge is that there is no labeled data for training and testing. We apply a state-of-the-art unsupervised dense retrieval model called Generative Pseudo Labeling that generates high-quality pseudo training labels.

Test collection has been a crucial factor for developing information retrieval systems. Constructing a test collection requires …

The availability of test collections in Cranfield paradigm has significantly benefited the development of models, methods and tools in …

Systematic reviews constitute the cornerstone of Evidence-based Medicine. They can provide guidance to medical policy-making by …

In this work we focus on multi-turn passage retrieval as a crucial component of conversational search. One of the key challenges in …

The effectiveness of information retrieval systems heavily depends on a large number of hyperparameters that need to be tuned. …

Information Retrieval systems rely on large test collections to measure their effectiveness in retrieving relevant documents. While the …

The goal of a technology-assisted review is to achieve high recall with low human effort. Continuous active learning algorithms have …