no code implementations • Findings (EMNLP) 2021 • Hitarth Narvala, Graham McDonald, Iadh Ounis
The relationships that exist between entities can be a reliable indicator for classifying sensitive information, such as commercially sensitive information.
Ranked #1 on Sensitivity Classification on GovSensitivity
no code implementations • EMNLP (scai) 2020 • Sarawoot Kongyoung, Craig Macdonald, Iadh Ounis
Furthermore, we propose a novel hybrid dynamic method combining Abridged Linear for the main task with a Loss-Balanced Task Weighting (LBTW) for the auxiliary tasks, so as to automatically fine-tune task weighting during learning, ensuring that each of the task’s weights is adjusted by the relative importance of the different tasks.
1 code implementation • 2 May 2024 • Andrew Parry, Thomas Jaenich, Sean MacAvaney, Iadh Ounis
In re-ranking, we investigate operating points of adaptive re-ranking with different first stages to find the point in graph traversal where the first stage no longer has an effect on the performance of the overall retrieval pipeline.
no code implementations • 4 Apr 2024 • Zixuan Yi, Xi Wang, Iadh Ounis
To account for and model possible noise in the users' interactions in graph neural recommenders, we propose a novel Diffusion Graph Transformer (DiffGT) model for top-k recommendation.
no code implementations • 11 Mar 2024 • Manish Chandra, Debasis Ganguly, Yiwen Li, Iadh Ounis
While existing work uses a static number of examples during inference for each data instance, in this paper we propose a novel methodology of dynamically adapting the number of examples as per the data.
no code implementations • 24 Jan 2024 • Thomas Jaenich, Graham McDonald, Iadh Ounis
With this in mind, it is beneficial to predict the amount of exposure that a group of documents is likely to receive in the results of the first stage retrieval process, in order to ensure that there are a sufficient number of documents included from each of the groups.
no code implementations • 27 Nov 2023 • Siwei Liu, Xi Wang, Craig Macdonald, Iadh Ounis
We propose a novel recommendation model, the Social-aware Gaussian Pre-trained model (SGP), which encodes the user social relations and interaction data at the pre-training stage in a Graph Neural Network (GNN).
no code implementations • 31 Oct 2023 • Zixuan Yi, Zijun Long, Iadh Ounis, Craig Macdonald, Richard McCreadie
In recent years, the rapid growth of online multimedia services, such as e-commerce platforms, has necessitated the development of personalised recommendation approaches that can encode diverse content about each item.
no code implementations • 21 Aug 2023 • Zixuan Yi, Iadh Ounis, Craig Macdonald
In our research, we introduce the Personalised Graph Prompt-based Recommendation (PGPRec) framework.
no code implementations • 1 Aug 2023 • Xiao Wang, Sean MacAvaney, Craig Macdonald, Iadh Ounis
GenQR directly reformulates the user's input query, while GenPRF provides additional context for the query by making use of pseudo-relevance feedback information.
1 code implementation • 1 Aug 2023 • Andreas Chari, Sean MacAvaney, Iadh Ounis
One advantage of neural ranking models is that they are meant to generalise well in situations of synonymity i. e. where two words have similar or identical meanings.
1 code implementation • European Conference on Information Retrieval 2023 • Hitarth Narvala, Graham McDonald, Iadh Ounis
With the tremendous growth in the volume of information produced online every day (e. g. news articles), there is a need for automatic methods to identify related information about events as the events evolve over time (i. e., information threads).
Ranked #1 on Information Threading on NewSHead
1 code implementation • Information Processing & Management 2023 • Hitarth Narvala, Graham McDonald, Iadh Ounis
Due to the massive volume of articles produced online every day, it is challenging for online platforms (e. g., news agencies) to present the information about an event, activity or discussion to their users in an easily digestible format.
Ranked #1 on Information Threading on Multi-News
no code implementations • 19 Nov 2022 • Ting Su, Craig Macdonald, Iadh Ounis
Our results show that the neural language models significantly outperform traditional TF. IDF and LSTM methods.
no code implementations • 19 Nov 2022 • Ting Su, Craig Macdonald, Iadh Ounis
We conclude that the Twitter users' friendship and followers network information can significantly outperform language-based approaches, as well as the existing state-of-the-art fake news detection models that use a more sophisticated network structure, in classifying fake news on Twitter.
no code implementations • 21 Jan 2022 • Sean MacAvaney, Craig Macdonald, Iadh Ounis
Given that web documents are prone to change over time, we study the differences present between a version of the corpus containing documents as they appeared in 2017 (which has been used by several recent works) and a new version we construct that includes documents close to as they appeared at the time the query log was produced (2006).
no code implementations • 26 Nov 2021 • Sean MacAvaney, Craig Macdonald, Iadh Ounis
We present ir-measures, a new tool that makes it convenient to calculate a diverse set of evaluation measures used in information retrieval.
1 code implementation • 13 Aug 2021 • Craig Macdonald, Nicola Tonellotto, Iadh Ounis
The advent of contextualised language models has brought gains in search effectiveness, not just when applied for re-ranking the output of classical weighting models such as BM25, but also when used directly for passage indexing and retrieval, a technique which is called dense retrieval.
no code implementations • 10 Aug 2021 • Jingmin Huang, Bowei Chen, Lan Luo, Shigang Yue, Iadh Ounis
There is a growing interest in product aesthetics analytics and design.
no code implementations • 9 Aug 2021 • Sean MacAvaney, Craig Macdonald, Roderick Murray-Smith, Iadh Ounis
Existing approaches often rely on massive query logs and interaction data to generate a variety of possible query intents, which then can be used to re-rank documents.
no code implementations • 8 Jul 2021 • Zaiqiao Meng, Siwei Liu, Craig Macdonald, Iadh Ounis
For the GCN-P model, two single-relational graphs are constructed from all the users' and items' side information respectively, to pre-train entity representations by using the Graph Convolutional Networks.
3 code implementations • 21 Jun 2021 • Xiao Wang, Craig Macdonald, Nicola Tonellotto, Iadh Ounis
In particular, based on the pseudo-relevant set of documents identified using a first-pass dense retrieval, we extract representative feedback embeddings (using KMeans clustering) -- while ensuring that these embeddings discriminate among passages (based on IDF) -- which are then added to the query representation.
Ranked #1 on TREC 2019 Passage Ranking on MSMARCO
1 code implementation • 18 Apr 2021 • Amir H. Jadidinejad, Craig Macdonald, Iadh Ounis
Using the relative comparison of many recommendation models as in the typical offline evaluation of recommender systems, and based on the Kendall rank correlation coefficient, we show that our proposed evaluation methodology exhibits statistically significant improvements of 14% and 40% on the examined open loop datasets (Yahoo!
no code implementations • 5 Feb 2021 • Xi Wang, Iadh Ounis, Craig Macdonald
Furthermore, inspired by the users' information adoption framework, we integrate two loss functions and a negative sampling strategy into our proposed RPRM model, to ensure that the properties of reviews are correlated with the users' preferences.
no code implementations • 14 Aug 2020 • Xi Wang, Iadh Ounis, Craig Macdonald
However, a classification model that learns to classify binary instances with incomplete positive labels while assuming all unlabelled data to be negative examples will often generate a biased classifier.
no code implementations • 26 Jul 2020 • Zaiqiao Meng, Richard McCreadie, Craig Macdonald, Iadh Ounis
In this paper, we both show that there is no standard splitting strategy and that the selection of splitting strategy can have a strong impact on the ranking of recommender systems.
no code implementations • 15 Jul 2020 • Xiao Wang, Craig Macdonald, Iadh Ounis
Query reformulations have long been a key mechanism to alleviate the vocabulary-mismatch problem in information retrieval, for example by expanding the queries with related query terms or by generating paraphrases of the queries.
1 code implementation • 17 Sep 2019 • Zaiqiao Meng, Richard McCreadie, Craig Macdonald, Iadh Ounis
We train our VBCAR model based on the Bayesian Skip-gram framework coupled with the amortized variational inference so that it can learn more expressive latent representations that integrate both the non-linearity and Bayesian behaviour.
no code implementations • 5 Jul 2019 • Graham McDonald, Craig Macdonald, Iadh Ounis
However, many government documents contain sensitive information, such as personal or confidential information.
no code implementations • 22 Jun 2016 • Xiao Yang, Craig Macdonald, Iadh Ounis
In this paper, using a Twitter election classification task that aims to detect election-related tweets, we investigate the impact of the background dataset used to train the embedding models, the context window size and the dimensionality of word embeddings on the classification performance.
no code implementations • ACL 2014 • Miles Osborne, Sean Moran, Richard McCreadie, Alex Von Lunen, er, Martin Sykora, Elizabeth Cano, Neil Ireson, Craig Macdonald, Iadh Ounis, Yulan He, Tom Jackson, Fabio Ciravegna, Ann O{'}Brien