1 code implementation • 4 Mar 2024 • Ivan Sekulić, Krisztian Balog, Fabio Crestani
One approach expands answers with inline definitions of salient entities, making the answer self-contained.
no code implementations • 1 Mar 2024 • Nolwenn Bernard, Ivica Kostric, Krisztian Balog
While interest in conversational recommender systems has been on the rise, operational systems suitable for serving as research platforms for comprehensive studies are currently lacking.
1 code implementation • 12 Feb 2024 • Nolwenn Bernard, Ivica Kostric, Weronika Łajewska, Krisztian Balog, Petra Galuščáková, Vinay Setty, Martin G. Skjæveland
Personal knowledge graphs (PKGs) offer individuals a way to store and consolidate their fragmented personal data in a central place, improving service personalization while maintaining full user control.
1 code implementation • 21 Jan 2024 • Weronika Łajewska, Krisztian Balog
Specifically, our proposed method employs a sentence-level classifier to detect if the answer is present, then aggregates these predictions on the passage level, and eventually across the top-ranked passages to arrive at a final answerability estimate.
no code implementations • 21 Jan 2024 • Ivan Sekulić, Weronika Łajewska, Krisztian Balog, Fabio Crestani
While the body of research directed towards constructing and generating clarifying questions in mixed-initiative conversational search systems is vast, research aimed at processing and comprehending users' answers to such questions is scarce.
1 code implementation • 17 Aug 2023 • Weronika Łajewska, Krisztian Balog
However, synthesizing the top retrieved passages into a complete, relevant, and concise response is still an open challenge.
no code implementations • 26 Jul 2023 • Scott Sanner, Krisztian Balog, Filip Radlinski, Ben Wedin, Lucas Dixon
Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods.
no code implementations • 14 Jun 2023 • Krisztian Balog, ChengXiang Zhai
Information access systems, such as search engines, recommender systems, and conversational assistants, have become integral to our daily lives as they help us satisfy our information needs.
1 code implementation • 25 Apr 2023 • Nolwenn Bernard, Krisztian Balog
To address this, we introduce MG-ShopDial: a dataset of conversations mixing different goals in the domain of e-commerce.
no code implementations • 19 Apr 2023 • Martin G. Skjæveland, Krisztian Balog, Nolwenn Bernard, Weronika Łajewska, Trond Linjordet
We propose our own definition of a PKG, emphasizing the aspects of (1) data ownership by a single individual and (2) the delivery of personalized services as the primary purpose.
no code implementations • 16 Mar 2023 • Krisztian Balog, Filip Radlinski, Andrey Petrov
Despite the potential impact of explanations on decision making, there is a lack of research on quantifying their effect on users' choices.
1 code implementation • 13 Mar 2023 • Arun Tejasvi Chaganty, Megan Leszczynski, Shu Zhang, Ravi Ganti, Krisztian Balog, Filip Radlinski
Users in consumption domains, like music, are often able to more efficiently provide preferences over a set of items (e. g. a playlist or radio) than over single items (e. g. songs).
no code implementations • 27 Jan 2023 • Megan Leszczynski, Shu Zhang, Ravi Ganti, Krisztian Balog, Filip Radlinski, Fernando Pereira, Arun Tejasvi Chaganty
This has motivated conversational recommender systems (CRSs), with control provided through natural language feedback.
no code implementations • 25 Jan 2023 • Weronika Lajewska, Krisztian Balog
While the results can be reproduced within a 19% relative margin with respect to the main evaluation measure, the relative difference between the baseline and the top performing approach shrinks from the reported 18% to 5%.
1 code implementation • 13 Jan 2023 • Jafar Afzali, Aleksander Mark Drzewiecki, Krisztian Balog, Shuo Zhang
We present an extensible user simulation toolkit to facilitate automatic evaluation of conversational recommender systems.
no code implementations • 29 Nov 2022 • Ivica Kostric, Krisztian Balog, Tølløv Alexander Aresvik, Nolwenn Bernard, Eyvinn Thu Dørheim, Pholit Hantula, Sander Havn-Sørensen, Rune Henriksen, Hengameh Hosseini, Ekaterina Khlybova, Weronika Lajewska, Sindre Ekrheim Mosand, Narmin Orujova
DAGFiNN is a conversational conference assistant that can be made available for a given conference both as a chatbot on the website and as a Furhat robot physically exhibited at the conference venue.
2 code implementations • 25 May 2022 • Trond Linjordet, Krisztian Balog
The construction of this test collection also sheds light on the challenges of constructing large-scale KGQA datasets with genuinely NL questions.
no code implementations • 19 May 2022 • Filip Radlinski, Krisztian Balog, Fernando Diaz, Lucas Dixon, Ben Wedin
Natural interaction with recommendation and personalized search systems has received tremendous attention in recent years.
1 code implementation • 3 May 2022 • Shuo Zhang, Mu-Chun Wang, Krisztian Balog
User simulation has been a cost-effective technique for evaluating conversational recommender systems.
1 code implementation • 26 Nov 2021 • Ivica Kostric, Krisztian Balog, Filip Radlinski
These strategies do not perform well in cases where the user does not have sufficient knowledge of the target domain to answer such questions.
no code implementations • 14 Sep 2021 • Vinay Setty, Krisztian Balog
This paper summarizes our participation in the SMART Task of the ISWC 2020 Challenge.
1 code implementation • 19 May 2021 • Jafar Afzali, Aleksander Mark Drzewiecki, Krisztian Balog
These requests are to be resolved from a dataset of POIs, which are collected from a popular online directory, and are further linked to a geographical knowledge base and enriched with relevant web snippets.
no code implementations • 19 May 2021 • Krisztian Balog, Filip Radlinski, Alexandros Karatzoglou
We address how to robustly interpret natural language refinements (or critiques) in recommender systems.
1 code implementation • 13 May 2021 • Shuo Zhang, Krisztian Balog
The main novel contribution of this work is a semantic table retrieval framework for matching information needs (keyword or table queries) against tables.
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.
1 code implementation • 8 May 2021 • Weiwei Sun, Shuo Zhang, Krisztian Balog, Zhaochun Ren, Pengjie Ren, Zhumin Chen, Maarten de Rijke
The purpose of the task is to increase the evaluation power of user simulations and to make the simulation more human-like.
1 code implementation • 24 Sep 2020 • Kristian Gingstad, Øyvind Jekteberg, Krisztian Balog
Providing personalized recommendations that are also accompanied by explanations as to why an item is recommended is a research area of growing importance.
no code implementations • 10 Sep 2020 • Trond Linjordet, Krisztian Balog
The quality of the data and the partitioning of the datasets into training, validation and test splits impact the performance of the models trained on this data.
2 code implementations • 8 Sep 2020 • Javeria Habib, Shuo Zhang, Krisztian Balog
Conversational recommender systems support users in accomplishing recommendation-related goals via multi-turn conversations.
no code implementations • 19 Aug 2020 • Shuo Zhang, Krisztian Balog, Jamie Callan
Category systems are central components of knowledge bases, as they provide a hierarchical grouping of semantically related concepts and entities.
1 code implementation • 15 Jun 2020 • Shuo Zhang, Krisztian Balog
Conversational information access is an emerging research area.
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 • 23 May 2020 • Shuo Zhang, Zhuyun Dai, Krisztian Balog, Jamie Callan
We propose to generate natural language summaries as answers to describe the complex information contained in a table.
no code implementations • 1 Feb 2020 • Shuo Zhang, Krisztian Balog
Tables are a powerful and popular tool for organizing and manipulating data.
1 code implementation • 1 Feb 2020 • Shuo Zhang, Edgar Meij, Krisztian Balog, Ridho Reinanda
We refer to this process as novel entity discovery and, to the best of our knowledge, it is the first endeavor on mining the unlinked cells in web tables.
no code implementations • 19 Jan 2020 • Krisztian Balog, Lucie Flekova, Matthias Hagen, Rosie Jones, Martin Potthast, Filip Radlinski, Mark Sanderson, Svitlana Vakulenko, Hamed Zamani
This paper discusses the potential for creating academic resources (tools, data, and evaluation approaches) to support research in conversational search, by focusing on realistic information needs and conversational interactions.
1 code implementation • 8 Sep 2019 • Shuo Zhang, Krisztian Balog
We address the task of auto-completing data cells in relational tables.
no code implementations • WS 2019 • Filip Radlinski, Krisztian Balog, Bill Byrne, Karthik Krishnamoorthi
Studying the dialogues in one domain, we present a brief quantitative analysis of how people describe movie preferences at scale.
no code implementations • 5 Aug 2019 • Darío Garigliotti, Dyaa Albakour, Miguel Martinez, Krisztian Balog
Monitoring entities in media streams often relies on rich entity representations, like structured information available in a knowledge base (KB).
no code implementations • 8 Jul 2019 • Shuo Zhang, Krisztian Balog
Tables are an extremely powerful visual and interactive tool for structuring and manipulating data, making spreadsheet programs one of the most popular computer applications.
no code implementations • 5 Jul 2019 • Jon Arne Bø Hovda, Darío Garigliotti, Krisztian Balog
Knowledge bases store information about the semantic types of entities, which can be utilized in a range of information access tasks.
1 code implementation • 31 May 2019 • Li Deng, Shuo Zhang, Krisztian Balog
Tables contain valuable knowledge in a structured form.
no code implementations • 29 Jan 2019 • Trond Linjordet, Krisztian Balog
It is held as a truism that deep neural networks require large datasets to train effective models.
1 code implementation • 18 Jan 2019 • Jan Trienes, Krisztian Balog
Thousands of complex natural language questions are submitted to community question answering websites on a daily basis, rendering them as one of the most important information sources these days.
no code implementations • 2 Sep 2018 • Darío Garigliotti, Krisztian Balog
We address the problem of constructing a knowledge base of entity-oriented search intents.
no code implementations • 14 Jul 2018 • Heng Ding, Krisztian Balog
Since natural language questions are available in large quantities, we develop models to automatically generate the corresponding keyword queries.
no code implementations • 22 Feb 2018 • Heng Ding, Shuo Zhang, Darío Garigliotti, Krisztian Balog
We address the task of generating query suggestions for task-based search.
no code implementations • 22 Feb 2018 • Darío Garigliotti, Krisztian Balog
Entity-oriented search deals with a wide variety of information needs, from displaying direct answers to interacting with services.
2 code implementations • 16 Feb 2018 • Shuo Zhang, Krisztian Balog
Specifically, we (i) represent queries and tables in multiple semantic spaces (both discrete sparse and continuous dense vector representations) and (ii) introduce various similarity measures for matching those semantic representations.
1 code implementation • 18 Sep 2017 • Jan R. Benetka, Krisztian Balog, Kjetil Nørvåg
We address the problem of extracting structured representations of economic events from a large corpus of news articles, using a combination of natural language processing and machine learning techniques.
no code implementations • 28 Aug 2017 • Darío Garigliotti, Krisztian Balog
Today, the practice of returning entities from a knowledge base in response to search queries has become widespread.
no code implementations • 28 Aug 2017 • Darío Garigliotti, Krisztian Balog
We address the problem of generating query suggestions to support users in completing their underlying tasks (which motivated them to search in the first place).