activity
20182022
most citedEvaluating Mixed-initiative Conversational Search Systems via User Simulation

55 citations · 95 across the 5 of their papers we have counts for

collaborators

8 papers

cs.CL202255 cited

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…

cs.CL2021

Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering

Xu Wang, Shuai Zhao, Bo Cheng +5

Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities. Although effective, most o…

physics.optics20217 cited

-matrix method for calculation of second-harmonic generation in clusters of spherical particles

Ivan Sekulic, Jian Wei You, Nicolae C. Panoiu

In this article, we present a -matrix method for numerical computation of second-harmonic generation from clusters of arbitrarily distributed spherical particles made of centros…

cs.IR2021

User Engagement Prediction for Clarification in Search

Ivan Sekulić, Mohammad Aliannejadi, Fabio Crestani

Clarification is increasingly becoming a vital factor in various topics of information retrieval, such as conversational search and modern Web search engines. Prompting the user fo…

cs.IR20205 cited

Longformer for MS MARCO Document Re-ranking Task

Ivan Sekulić, Amir Soleimani, Mohammad Aliannejadi +1

Two step document ranking, where the initial retrieval is done by a classical information retrieval method, followed by neural re-ranking model, is the new standard. The best perfo…

cs.CL202028 cited

Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

Guoshun Nan, Zhijiang Guo, Ivan Sekulić +1

Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence ent…