1 code implementation • 3 Mar 2024 • Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi
The two prominent approaches to enhance the performance of LLMs on low-frequent topics are: Retrieval Augmented Generation (RAG) and fine-tuning (FT) over synthetic data.
1 code implementation • 14 Sep 2023 • Chris Kamphuis, Aileen Lin, Siwen Yang, Jimmy Lin, Arjen P. de Vries, Faegheh Hasibi
MMEAD, or MS MARCO Entity Annotations and Disambiguations, is a resource for entity links for the MS MARCO datasets.
1 code implementation • 9 Sep 2023 • Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi
This tutorial provides a comprehensive and up-to-date overview of DA approaches in the context of conversational systems.
1 code implementation • COLING 2022 • Gizem Aydin, Seyed Amin Tabatabaei, Giorgios Tsatsaronis, Faegheh Hasibi
Automatic extraction of funding information from academic articles adds significant value to industry and research communities, such as tracking research outcomes by funding organizations, profiling researchers and universities based on the received funding, and supporting open access policies.
1 code implementation • 15 Jun 2022 • Hideaki Joko, Faegheh Hasibi
It is, however, shown that existing EL methods developed for annotating documents are suboptimal for conversations, where personal entities (e. g., "my cars") and concepts are essential for understanding user utterances.
1 code implementation • 2 May 2022 • Emma J. Gerritse, Faegheh Hasibi, Arjen P. de Vries
Pre-trained language models such as BERT have been a key ingredient to achieve state-of-the-art results on a variety of tasks in natural language processing and, more recently, also in information retrieval. Recent research even claims that BERT is able to capture factual knowledge about entity relations and properties, the information that is commonly obtained from knowledge graphs.
1 code implementation • 11 May 2021 • Hideaki Joko, Faegheh Hasibi, Krisztian Balog, Arjen P. de Vries
Further, we report on the performance of traditional EL systems on our Conversational Entity Linking dataset, ConEL, and present an extension to these methods to better fit the conversational setting.
no code implementations • 20 Oct 2020 • Emma J. Gerritse, Faegheh Hasibi, Arjen P. de Vries
We review existing definitions of bias in the literature: people bias, algorithm bias, and a combination of the two, and further propose different strategies for tackling these biases for conversational search systems.
1 code implementation • 2 Jun 2020 • Johannes M. van Hulst, Faegheh Hasibi, Koen Dercksen, Krisztian Balog, Arjen P. de Vries
Entity linking is a standard component in modern retrieval system that is often performed by third-party toolkits.
Ranked #3 on Entity Linking on Derczynski
1 code implementation • 6 May 2020 • Emma J. Gerritse, Faegheh Hasibi, Arjen P. de Vries
In this research, we improve upon the current state of the art in entity retrieval by re-ranking the result list using graph embeddings.