We introduce C-Pack, a package of resources that significantly advances the field of general
text embeddings for Chinese. C-Pack includes three critical resources. 1) C-MTP is a …

A reliable resume-job matching system helps a company find suitable candidates from a
pool of resumes, and helps a job seeker find relevant jobs from a list of job posts. However …

The bi-encoder architecture provides a framework for understanding machine-learned
retrieval models based on dense and sparse vector representations. Although these …

Learned sparse retrieval (LSR) is a family of neural methods that encode queries and
documents into sparse lexical vectors that can be indexed and retrieved efficiently with an …

This paper presents our analysis of neural IR models, particularly focusing on over-
penalization for extra information (OPEX)-a phenomenon where addition of a sentence to a …

Despite the recent advancements in information retrieval (IR), zero-shot IR remains a
significant challenge, especially when dealing with new domains, languages, and newly …

In our research, we aim to assess the effectiveness of Large Language Models (LLMs) in
performing query expansion in the context of Information Retrieval (IR). Some recent …

Legal case entailment is a fundamental principle of the legal system in which the verdict of
previous cases serves as a guiding precedent for later cases with similar factual …

Learned sparse retrieval (LSR) is a family of neural methods that encode queries and
documents into sparse lexical vectors that can be indexed and retrieved efficiently with an …

Suppose you want to learn more about a certain topic. For the sake of argument, let us
assume this topic is multimodal machine learning for information retrieval. How would you …