no code implementations • LREC 2012 • Ahmet Aker, Evangelos Kanoulas, Robert Gaizauskas
In this work we aim to reduce the amount of time and resources spent for tasks 1 and 2.
1 code implementation • 23 Aug 2016 • Christophe Van Gysel, Evangelos Kanoulas, Maarten de Rijke
Lexical query modeling has been the leading paradigm for session search.
2 code implementations • 25 Aug 2016 • Christophe Van Gysel, Maarten de Rijke, Evangelos Kanoulas
We introduce a novel latent vector space model that jointly learns the latent representations of words, e-commerce products and a mapping between the two without the need for explicit annotations.
1 code implementation • 3 Jan 2017 • Christophe Van Gysel, Evangelos Kanoulas, Maarten de Rijke
We introduce pyndri, a Python interface to the Indri search engine.
1 code implementation • 12 Jun 2017 • Christophe Van Gysel, Maarten de Rijke, Evangelos Kanoulas
Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention.
1 code implementation • 25 Jul 2017 • Christophe Van Gysel, Maarten de Rijke, Evangelos Kanoulas
We discover how clusterings of experts correspond to committees in organizations, the ability of expert representations to encode the co-author graph, and the degree to which they encode academic rank.
4 code implementations • 9 Aug 2017 • Christophe Van Gysel, Maarten de Rijke, Evangelos Kanoulas
We propose the Neural Vector Space Model (NVSM), a method that learns representations of documents in an unsupervised manner for news article retrieval.
1 code implementation • 4 Dec 2017 • Mircea Mironenco, Dana Kianfar, Ke Tran, Evangelos Kanoulas, Efstratios Gavves
In this work we propose a blackbox intervention method for visual dialog models, with the aim of assessing the contribution of individual linguistic or visual components.
1 code implementation • AKBC 2019 • Antonios Minas Krasakis, Evangelos Kanoulas, George Tsatsaronis
To tackle this problem, we propose a methodology for extending training datasets to arbitrarily big sizes and training complex, data-hungry models using weak supervision.
no code implementations • 2 Dec 2018 • Jasper Linmans, Bob van de Velde, Evangelos Kanoulas
This paper investigates neural classifiers as a more robust methodology for controversy detection in general web pages.
no code implementations • 18 Jun 2019 • Julien Rossi, Matthias Wirth, Evangelos Kanoulas
The performance is measured on the search results of a query consisting of the extracted keywords.
no code implementations • 5 Jul 2019 • Ilse van der Linden, Hinda Haned, Evangelos Kanoulas
We present Global Aggregations of Local Explanations (GALE) with the objective to provide insights in a model's global decision making process.
no code implementations • WS 2019 • Christopher Norman, Mariska Leeflang, Ren{\'e} Spijker, Evangelos Kanoulas, Aur{\'e}lie N{\'e}v{\'e}ol
Systematic reviews are important in evidence based medicine, but are expensive to produce.
1 code implementation • 30 Aug 2019 • Jie Zou, Evangelos Kanoulas
The method learns the product relevance as well as the reward of the potential questions to be asked to the user by being trained on the search history and purchase behavior of a specific user together with that of other users.
1 code implementation • 29 Apr 2020 • Pengjie Ren, Zhumin Chen, Zhaochun Ren, Evangelos Kanoulas, Christof Monz, Maarten de Rijke
In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language, and directly receivethe information they need from a short system response in a conversational manner.
no code implementations • LREC 2020 • Chuan Wu, Evangelos Kanoulas, Maarten de Rijke, Wei Lu
To support research on entity salience, we present a new dataset, the WikiNews Salience dataset (WN-Salience), which can be used to benchmark tasks such as entity salience detection and salient entity linking.
1 code implementation • 24 May 2020 • Nikos Voskarides, Dan Li, Pengjie Ren, Evangelos Kanoulas, Maarten de Rijke
Context from the conversational history can be used to arrive at a better expression of the current turn query, defined as the task of query resolution.
no code implementations • 25 May 2020 • Svitlana Vakulenko, Evangelos Kanoulas, Maarten de Rijke
The ability to engage in mixed-initiative interaction is one of the core requirements for a conversational search system.
1 code implementation • AKBC 2020 • Georgios Sidiropoulos, Nikos Voskarides, Evangelos Kanoulas
Knowledge graph simple question answering (KGSQA), in its standard form, does not take into account that human-curated question answering training data only cover a small subset of the relations that exist in a Knowledge Graph (KG), or even worse, that new domains covering unseen and rather different to existing domains relations are added to the KG.
1 code implementation • 28 May 2020 • Jie Zou, Yi-fan Chen, Evangelos Kanoulas
Previous conversational recommender systems ask users to express their preferences over items or item facets.
no code implementations • 1 Aug 2020 • Jie Zou, Evangelos Kanoulas, Yiqun Liu
Search and recommender systems that take the initiative to ask clarifying questions to better understand users' information needs are receiving increasing attention from the research community.
no code implementations • 9 Aug 2020 • Antonios Minas Krasakis, Mohammad Aliannejadi, Nikos Voskarides, Evangelos Kanoulas
Recent research on conversational search highlights the importance of mixed-initiative in conversations.
no code implementations • 20 Oct 2020 • Spyretta Leivaditi, Julien Rossi, Evangelos Kanoulas
We focus on supporting the review of lease agreements, a contract type that has received little attention in the legal information extraction literature, and we define the types of entities and red flags needed for that task.
1 code implementation • 10 Mar 2021 • Tom Lotze, Stefan Klut, Mohammad Aliannejadi, Evangelos Kanoulas
This research demonstrates the potential for ranking clarification panes based on lexical information only and can serve as a first neural baseline for future research to improve on.
1 code implementation • 15 Mar 2021 • Nikolaos Kondylidis, Jie Zou, Evangelos Kanoulas
We first perform an explainable user model in the form of preferences over the items' categories, and then use the category preferences to recommend items.
no code implementations • 14 Apr 2021 • Svitlana Vakulenko, Evangelos Kanoulas, Maarten de Rijke
These datasets were collected to inform different dialogue-based tasks including conversational search.
1 code implementation • EMNLP (sustainlp) 2021 • Georgios Sidiropoulos, Nikos Voskarides, Svitlana Vakulenko, Evangelos Kanoulas
In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer.
Multi-hop Question Answering Open-Domain Question Answering +2
1 code implementation • 29 Jun 2021 • Shanshan Wang, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Huasheng Liang, Qiang Yan, Evangelos Kanoulas, Maarten de Rijke
We seek to improve the performance for both frequent and rare ICD codes by using a contrastive graph-based EHR coding framework, CoGraph, which re-casts EHR coding as a few-shot learning task.
1 code implementation • 23 Aug 2021 • Julien Rossi, Svitlana Vakulenko, Evangelos Kanoulas
Citing legal opinions is a key part of legal argumentation, an expert task that requires retrieval, extraction and summarization of information from court decisions.
no code implementations • 23 Aug 2021 • Julien Rossi, Evangelos Kanoulas
In this work we describe a method to identify document pairwise relevance in the context of a typical legal document collection: limited resources, long queries and long documents.
no code implementations • 24 Aug 2021 • Vera Provatorova, Svitlana Vakulenko, Samarth Bhargav, Evangelos Kanoulas
We evaluate and report the performance of popular EL systems on the ShadowLink benchmark.
1 code implementation • 13 Sep 2021 • Mohammad Aliannejadi, Leif Azzopardi, Hamed Zamani, Evangelos Kanoulas, Paul Thomas, Nick Craswel
In this paper, we present a model for conversational search -- from which we instantiate different observed conversational search strategies, where the agent elicits: (i) Feedback-First, or (ii) Feedback-After.
1 code implementation • 13 Sep 2021 • Hamed Bonab, Mohammad Aliannejadi, Ali Vardasbi, Evangelos Kanoulas, James Allan
We introduce and formalize the problem of cross-market product recommendation, i. e., market adaptation.
1 code implementation • 23 Sep 2021 • Dan Li, Shuai Wang, Jie Zou, Chang Tian, Elisha Nieuwburg, Fengyuan Sun, Evangelos Kanoulas
We create abenchmark for Paint4Poem: we train two representative text-to-image generation models: AttnGAN and MirrorGAN, and evaluate theirperformance regarding painting pictorial quality, painting stylistic relevance, and semantic relevance between poems and paintings. The results indicate that the models are able to generate paintings that have good pictorial quality and mimic Feng Zikai's style, but thereflection of poem semantics is limited.
no code implementations • 11 Oct 2021 • Samarth Bhargav, Evangelos Kanoulas
We show that by updating the disentangled latent space based on user feedback, and by exploiting the generative nature of the recommender, controlled and personalized recommendations can be produced.
no code implementations • 14 Dec 2021 • Weijia Zhang, Svitlana Vakulenko, Thilina Rajapakse, Yumo Xu, Evangelos Kanoulas
In this dataset, answering the query requires document retrieval from a knowledge corpus.
no code implementations • 21 Jan 2022 • Leif Azzopardi, Mohammad Aliannejadi, Evangelos Kanoulas
Various conceptual and descriptive models of conversational search have been proposed in the literature -- while useful, they do not provide insights into how interaction between the agent and user would change in response to the costs and benefits of the different interactions.
1 code implementation • dialdoc (ACL) 2022 • Vaishali Pal, Evangelos Kanoulas, Maarten de Rijke
In this work, we study parameter-efficient abstractive QA in encoder-decoder models over structured tabular data and unstructured textual data using only 1. 5% additional parameters for each modality.
1 code implementation • 22 Apr 2022 • Antonios Minas Krasakis, Andrew Yates, Evangelos Kanoulas
Current conversational passage retrieval systems cast conversational search into ad-hoc search by using an intermediate query resolution step that places the user's question in context of the conversation.
1 code implementation • 4 May 2022 • Georgios Sidiropoulos, Evangelos Kanoulas
Dense retrieval is becoming one of the standard approaches for document and passage ranking.
1 code implementation • 26 Sep 2022 • Georgios Sidiropoulos, Svitlana Vakulenko, Evangelos Kanoulas
Finally, we create a new dataset with questions voiced by human users and use their transcriptions to show that the retrieval performance can further degrade when dealing with natural ASR noise instead of synthetic ASR noise.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +7
no code implementations • 12 Oct 2022 • Vera Provatorova, Simone Tedeschi, Svitlana Vakulenko, Roberto Navigli, Evangelos Kanoulas
Entity disambiguation (ED) is the task of mapping an ambiguous entity mention to the corresponding entry in a structured knowledge base.
1 code implementation • 13 Jan 2023 • Patrick Jonk, Vincent de Vries, Rombout Wever, Georgios Sidiropoulos, Evangelos Kanoulas
In support of safety data analysis, reports are often categorized according to a taxonomy.
no code implementations • 14 Feb 2023 • Samarth Bhargav, Mohammad Aliannejadi, Evangelos Kanoulas
We consider the cross-market recommendation (CMR) task, which involves recommendation in a low-resource target market using data from a richer, auxiliary source market.
no code implementations • 13 Apr 2023 • Guglielmo Faggioli, Laura Dietz, Charles Clarke, Gianluca Demartini, Matthias Hagen, Claudia Hauff, Noriko Kando, Evangelos Kanoulas, Martin Potthast, Benno Stein, Henning Wachsmuth
When asked, large language models (LLMs) like ChatGPT claim that they can assist with relevance judgments but it is not clear whether automated judgments can reliably be used in evaluations of retrieval systems.
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 • 22 May 2023 • Vaishali Pal, Andrew Yates, Evangelos Kanoulas, Maarten de Rijke
Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table.
no code implementations • 23 Jun 2023 • Chieling Yueh, Evangelos Kanoulas, Bruno Martins, Camilo Thorne, Saber Akhondi
The high volume of published chemical patents and the importance of a timely acquisition of their information gives rise to automating information extraction from chemical patents.
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 • 5 Dec 2023 • Zahra Abbasiantaeb, Yifei Yuan, Evangelos Kanoulas, Mohammad Aliannejadi
Our framework involves two LLMs interacting on a specific topic, with the first LLM acting as a student, generating questions to explore a given search topic.
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 • 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 • 16 Mar 2024 • Georgios Sidiropoulos, Evangelos Kanoulas
Dense retrieval has become the new paradigm in passage retrieval.
no code implementations • EMNLP 2021 • Vera Provatorova, Samarth Bhargav, Svitlana Vakulenko, Evangelos Kanoulas
We evaluate and report the performance of popular EL systems on the ShadowLink benchmark.