1 code implementation • 28 Apr 2024 • Chuan Meng, Negar Arabzadeh, Arian Askari, Mohammad Aliannejadi, Maarten de Rijke
RLT is crucial for re-ranking as it can improve re-ranking efficiency by sending variable-length candidate lists to a re-ranker on a per-query basis.
1 code implementation • 1 Apr 2024 • Chuan Meng, Negar Arabzadeh, Arian Askari, Mohammad Aliannejadi, Maarten de Rijke
This allows us to predict any IR evaluation measure using the generated relevance judgments as pseudo-labels; Also, this allows us to interpret predicted IR evaluation measures, and identify, track and rectify errors in generated relevance judgments to improve QPP quality.
no code implementations • 27 Mar 2024 • Amin Abolghasemi, Zhaochun Ren, Arian Askari, Mohammad Aliannejadi, Maarten de Rijke, Suzan Verberne
In this work, we leverage large language models (LLMs) and unlock their ability to generate satisfaction-aware counterfactual dialogues to augment the set of original dialogues of a test collection.
no code implementations • 9 Mar 2024 • Amin Abolghasemi, Leif Azzopardi, Arian Askari, Maarten de Rijke, Suzan Verberne
With TExFAIR, we extend the AWRF framework to allow for the evaluation of fairness in settings with term-based representations of groups in documents in a ranked list.
1 code implementation • 18 Feb 2024 • Arian Askari, Roxana Petcu, Chuan Meng, Mohammad Aliannejadi, Amin Abolghasemi, Evangelos Kanoulas, Suzan Verberne
Furthermore, we propose SOLID-RL, which is further trained to generate a dialog in one step on the data generated by SOLID.
1 code implementation • 9 Jan 2024 • Arian Askari, Zihui Yang, Zhaochun Ren, Suzan Verberne
Furthermore, we propose LegalQA: a real-world benchmark dataset for evaluating answer retrieval in the legal domain.
no code implementations • 19 Jun 2023 • Rishabh Upadhyay, Arian Askari, Gabriella Pasi, Marco Viviani
In this paper, we propose a novel approach to consider multiple dimensions of relevance beyond topicality in cross-encoder re-ranking.
1 code implementation • 3 May 2023 • Arian Askari, Mohammad Aliannejadi, Evangelos Kanoulas, Suzan Verberne
We introduce a new dataset, ChatGPT-RetrievalQA, and compare the effectiveness of models fine-tuned on LLM-generated and human-generated data.
1 code implementation • 2 Mar 2023 • Arian Askari, Suzan Verberne, Amin Abolghasemi, Wessel Kraaij, Gabriella Pasi
Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data, and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available.
1 code implementation • 23 Jan 2023 • Arian Askari, Amin Abolghasemi, Gabriella Pasi, Wessel Kraaij, Suzan Verberne
In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token in the middle of the input of the cross-encoder re-ranker.
1 code implementation • 11 Oct 2022 • Amin Abolghasemi, Arian Askari, Suzan Verberne
In this work, we examine the generalizability of two of these deep contextualized term-based models in the context of query-by-example (QBE) retrieval in which a seed document acts as the query to find relevant documents.
no code implementations • 26 May 2022 • Arian Askari, Georgios Peikos, Gabriella Pasi, Suzan Verberne
Our methodology consists of four steps; in detail, given a legal case as a query, we reformulate it by extracting various meaningful sentences or n-grams.
1 code implementation • 19 Jan 2022 • Arian Askari, Suzan Verberne, Gabriella Pasi
In the legal domain, there is a large knowledge gap between the experts and the searchers, and the content on the legal QA websites consist of a combination formal and informal communication.
1 code implementation • 9 Aug 2021 • Sophia Althammer, Arian Askari, Suzan Verberne, Allan Hanbury
We address this challenge by combining lexical and dense retrieval methods on the paragraph-level of the cases for the first stage retrieval.