MRHF: Multi-stage Retrieval and Hierarchical Fusion for Textbook Question Answering

Textbook question answering is challenging as it aims to automatically answer various questions on textbook lessons with long text and complex diagrams, requiring reasoning across modalities. In this work, we propose MRHF, a novel framework that incorporates dense passage re-ranking and the mixture-of-experts architecture for TQA. MRHF...

1^st Workshop on Information Retrieval for Understudied Users (IR4U2)

Information Retrieval (IR) remains an active, fast-paced area of research. However, most advances in IR have predominantly benefited the so-called “classical” users, e.g., English-speaking adults. We envision IR4U2as a forum to spotlight efforts that, while sparse, consider diverse, and often understudied, user groups when designing,...

How does Information Pollution Challenge Children’s Right to Information Access?

Informed by existing literature, in addition to lessons learned from ongoing research work pertaining to online information seeking, in this contribution, we discuss our view of how information pollution affects a critical yet understudied user group: children. We first highlight the need to take into account the unique characteristics of...

Adaptive User Feedback for IR-Based Traceability Recovery

Trace ability recovery allows software engineers to understand the interconnections among software artefacts and, thus, it provides an important support to software maintenance activities. In the last decade, Information Retrieval (IR) has been widely adopted as core technology of semi-automatic tools to extract trace ability links between...

Social Web Data Analytics: Relevance, Redundancy, Diversity

In the past decade, the Social Web has evolved into both an essential channel for people to exchange information and a new type of mass media. The immense amount of data produced presents new possibilities and challenges: algorithms and technologies need to be developed to extract and infer useful information from the Social Web. One of the main...

Contextual Multidimensional Relevance Models

Information retrieval systems centrally build upon the concept of relevance in order to rank documents in response to a user's query. Assessing relevance is a non-trivial operation that can be influenced by a multitude of factors that go beyond mere topical overlap with the query. This thesis argues that relevance depends on personal (Chapter 2)...

Reconstructing Requirements Traceability in Design and Test Using Latent Semantic Indexing

Managing traceability data is an important aspect of the software development process. In this paper we define a methodology, consisting of six steps, for reconstructing requirements views using traceability data. One of the steps concerns the reconstruction of the traceability data. We investigate to what extent Latent Semantic Indexing (LSI),...