10.9k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- M. de Rijke37 · h 84
- Mohammad Aliannejadi2 profiles19 · h 27
- E. Kanoulas17 · h 41
- Harrie Oosterhuis2 profiles17 · h 21
- Maarten de Rijke14 · h 18
- Ali Vardasbi2 profiles7 · h 9
- M. D. Rijke7 · h 18
- M. Welling7 · h 95
- Svitlana Vakulenko6 · h 17
- J. Kamps5 · h 44
- Mostafa Dehghani2 profiles5 · h 42
- Stevan Rudinac5 · h 18
- University of AmsterdamNL235 papers
- Radboud University NijmegenNL80 papers
- Boston UniversityUS68 papers
- University of ManchesterGB68 papers
- University of Science and Technology of ChinaCN68 papers
- Aix-Marseille UniversitéFR67 papers
- Ann Arbor Center for Independent LivingUS67 papers
- Brookhaven National LaboratoryUS67 papers
- Charles UniversityCZ67 papers
- Columbia UniversityUS67 papers
- Indiana University BloomingtonUS67 papers
- Iowa State UniversityUS67 papers
22 papers · 1 filter
Do Images Clarify? A Study on the Effect of Images on Clarifying Questions in Conversational Search
Clemencia Siro, Zahra Abbasiantaeb, Yifei Yuan +2
Conversational search systems increasingly employ clarifying questions to refine user queries and improve the search experience. Previous studies have demonstrated the usefulness o…
Rethinking the Privacy of Text Embeddings: A Reproducibility Study of "Text Embeddings Reveal (Almost) As Much As Text"
Dominykas Seputis, Yongkang Li, Karsten Langerak +1
Text embeddings are fundamental to many natural language processing (NLP) tasks, extensively applied in domains such as recommendation systems and information retrieval (IR). Tradi…
Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge
Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi
Language Models (LMs) memorize a vast amount of factual knowledge, exhibiting strong performance across diverse tasks and domains. However, it has been observed that the performanc…
BrainLLM: Generative Language Decoding from Brain Recordings
Ziyi Ye, Qingyao Ai, Yiqun Liu +4
Generating human language through non-invasive brain-computer interfaces (BCIs) has the potential to unlock many applications, such as serving disabled patients and improving commu…
Data Augmentation for Conversational AI
Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi
Advancements in conversational systems have revolutionized information access, surpassing the limitations of single queries. However, developing dialogue systems requires a large a…
On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering
Georgios Sidiropoulos, Svitlana Vakulenko, Evangelos Kanoulas
Interacting with a speech interface to query a Question Answering (QA) system is becoming increasingly popular. Typically, QA systems rely on passage retrieval to select candidate…
The Role of Complex NLP in Transformers for Text Ranking?
David Rau, Jaap Kamps
Even though term-based methods such as BM25 provide strong baselines in ranking, under certain conditions they are dominated by large pre-trained masked language models (MLMs) such…
Evaluating Mixed-initiative Conversational Search Systems via User Simulation
Ivan Sekulić, Mohammad Aliannejadi, Fabio Crestani
Clarifying the underlying user information need by asking clarifying questions is an important feature of modern conversational search system. However, evaluation of such systems t…
Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you?
Rochelle Choenni, Ekaterina Shutova, Robert van Rooij
In this paper, we investigate what types of stereotypical information are captured by pretrained language models. We present the first dataset comprising stereotypical attributes o…
Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions
Mohammad Aliannejadi, Julia Kiseleva, Aleksandr Chuklin +2
Enabling open-domain dialogue systems to ask clarifying questions when appropriate is an important direction for improving the quality of the system response. Namely, for cases whe…
Highly Parallel Autoregressive Entity Linking with Discriminative Correction
Nicola De Cao, Wilker Aziz, Ivan Titov
Generative approaches have been recently shown to be effective for both Entity Disambiguation and Entity Linking (i.e., joint mention detection and disambiguation). However, the pr…
VerbCL: A Dataset of Verbatim Quotes for Highlight Extraction in Case Law
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. The identifica…
Robustness Evaluation of Entity Disambiguation Using Prior Probes:the Case of Entity Overshadowing
Vera Provatorova, Svitlana Vakulenko, Samarth Bhargav +1
Entity disambiguation (ED) is the last step of entity linking (EL), when candidate entities are reranked according to the context they appear in. All datasets for training and eval…
Improving Response Quality with Backward Reasoning in Open-domain Dialogue Systems
Ziming Li, Julia Kiseleva, Maarten de Rijke
Being able to generate informative and coherent dialogue responses is crucial when designing human-like open-domain dialogue systems. Encoder-decoder-based dialogue models tend to…
Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainability
Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
Abuse on the Internet is an important societal problem of our time. Millions of Internet users face harassment, racism, personal attacks, and other types of abuse across various pl…
Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrieval
Mohammad Aliannejadi, Manajit Chakraborty, Esteban Andrés Ríssola +1
With the improvements in speech recognition and voice generation technologies over the last years, a lot of companies have sought to develop conversation understanding systems that…
Conversations with Documents. An Exploration of Document-Centered Assistance
Maartje ter Hoeve, Robert Sim, Elnaz Nouri +3
The role of conversational assistants has become more prevalent in helping people increase their productivity. Document-centered assistance, for example to help an individual quick…
Sequence Modeling with Unconstrained Generation Order
Dmitrii Emelianenko, Elena Voita, Pavel Serdyukov
The dominant approach to sequence generation is to produce a sequence in some predefined order, e.g. left to right. In contrast, we propose a more general model that can generate t…
Societal Controversies in Wikipedia Articles
Erik Borra, Andreas Kaltenbrunner, Michele Mauri +6
Collaborative content creation inevitably reaches situations where different points of view lead to conflict. We focus on Wikipedia, the free encyclopedia anyone may edit, where di…
Words are Malleable: Computing Semantic Shifts in Political and Media Discourse
Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen +3
Recently, researchers started to pay attention to the detection of temporal shifts in the meaning of words. However, most (if not all) of these approaches restricted their efforts…
What does Attention in Neural Machine Translation Pay Attention to?
Hamidreza Ghader, Christof Monz
Attention in neural machine translation provides the possibility to encode relevant parts of the source sentence at each translation step. As a result, attention is considered to b…
Inducing Semantic Representation from Text by Jointly Predicting and Factorizing Relations
Ivan Titov, Ehsan Khoddam
In this work, we propose a new method to integrate two recent lines of work: unsupervised induction of shallow semantics (e.g., semantic roles) and factorization of relations in te…