Zeon Trevor Fernando

Koustav Rudra, Zeon Trevor Fernando, Avishek Anand

Pre-trained contextual language models such as BERT, GPT, and XLnet work quite well for document retrieval tasks. Such models are fine-tuned based on the query-document/query-passage level relevance labels to capture the ranking signals. However, the documents are longer than the passages and such document ranking models suffer from the token limitation (512) of BERT. Researchers proposed ranking strategies that either truncate the documents beyond the token limit or chunk the documents into units that can fit into the BERT. In the later case, the relevance labels are either directly transferred from the original query-document pair or learned through some external model. In this paper, we conduct a detailed study of the design decisions about splitting and label transfer on retrieval effectiveness and efficiency. We find that direct transfer of relevance labels from documents to passages introduces label noise that strongly affects retrieval effectiveness for large training datasets. We also find that query processing times are adversely affected by fine-grained splitting schemes. As a remedy, we propose a careful passage level labelling scheme using weak supervision that delivers improved performance (3-14% in terms of nDCG score) over most of the recently proposed models for ad-hoc retrieval while maintaining manageable computational complexity on four diverse document retrieval datasets.

Jaspreet Singh, Zeon Trevor Fernando, Saniya Chawla

In addition to user-generated content, Open Educational Resources are increasingly made available on the Web by several institutions and organizations with the aim of being re-used. Nevertheless, it is still difficult for users to find appropriate resources for specific learning scenarios among the vast amount offered on the Web. Our goal is to give users the opportunity to search for authentic resources from the Web and reuse them in a learning context. The LearnWeb-OER platform enhances collaborative searching and sharing of educational resources providing specific means and facilities for education. In the following, we provide a description of the functionalities that support users in collaboratively collecting, selecting, annotating and discussing search results and learning resources.

Zeon Trevor Fernando

In Social Science research, multimedia documents are often collected to answer particular research questions like: "Which of the aesthetic properties of a photo are considered important on the web" or "How has Street Art developed over the past 50 years". Therefore, a researcher generally issues multiple queries to a number of search engines. This activity may span over long time intervals and results in a collection which can be further analyzed. Documenting the collection building process which includes the context of the carried out searches is imperative for social scientists to reproduce their research. Such context documentation consists of several user actions and search attributes like: the issued queries; the results clicked and saved; duration a particular result was viewed for; the set of results that was displayed but neither clicked, nor saved; as well as user annotations like comments or tags. In this work we will describe a search process tracking module and a search history visualization module. These modules can be integrated into keyword based search systems through a REST API which was developed to help capture, document and revisit past search contexts while building a web corpora. Finally, we detail the implementation of how the module was integrated into the LearnWeb2.0 platform - a multimedia web2.0 search and sharing application which can obtain resources from various web2.0 tools such as Youtube, Bing, Flickr, etc using keyword search.