Design of Experimental Search & Information REtrieval Systems

15-18 September 2021, Padua, Italy

COVID-19 SAFETY MEASURES

DESIRES needs to be done in presence to favor participation and discussion!

  • Only fully vaccined people can access the conference room and participate to social events. Green pass or vaccination certificates will be checked at the registration desk.
  • Wear a mask! It is mandatory in every public space (not outside, though). Speakers do not need to wear a mask while they are presenting.
  • Social distancing. At least one meter distancing guaranteed in the conference room.
  • Standing and outdoor lunch and coffee breaks. Social dinner will be indoor (you can opt out).

Travel to Italy

Italian Government info (<- click here)

U.S. Embassy in Italy (<- click here)

Key facts

DESIRES is a biennial systems-oriented conference emphasizing the innovative technological aspects of search and retrieval systems.

DESIRES gathers researchers and practitioners from both academia and industry to discuss the latest innovative and visionary ideas in the field.

DESIRES mainly encourages papers about innovative and risky information access and retrieval system ideas, systems-building experience and insight, resourceful experimental studies, provocative position statements, and new application domains.

DESIRES is a single-track conference.

DESIRES invites two kinds of contributions: full papers (up to 6 pages) and abstracts (1 page).

To encourage authors to submit only their best work, each person can be an author or co-author of only a single full paper. That is, authors can submit only 1 (one) paper. Any author of a paper or prototype demo may additionally submit one abstract. Abstracts are expected to have a single author.

Papers

Full Papers

  • Mayank Anand, Jiarui Zhang, Shane Ding, Ji Xin and Jimmy Lin. Serverless BM25 Search and BERT Reranking.
  • Arian Askari and Suzan Verberne. Combining lexical and neural retrieval with longformer-based summarization for effective case law retrieval.
  • Krisztian Balog. Conversational AI from an Information Retrieval Perspective: Remaining Challenges and a Case for User Simulation. Best Paper Award
  • Aleksandar Bobic, Jean-Marie Le Goff and Christian Guetl. Towards Supporting Complex Retrieval Tasks Through Graph-Based Information Retrieval and Visual Analytics.
  • Roger Bradford. Lessons Learned from 20 Years of Implementing LSI Applications. Best Paper Award
  • Guglielmo Faggioli and Stefano Marchesin. What Makes a Query Semantically Hard?
  • Souvick Ghosh and Satanu Ghosh. "Do Users Need Human-like Conversational Agents?'' - Exploring Conversational System Design Using Framework of Human Needs.
  • Benjamin Hättasch, Nadja Geisler and Carsten Binnig. Netted?! How to Improve the Usefulness of Spider & Co.
  • Jeff Heflin, Brian D. Davison and Haiyan Jia. Exploring Dataset via Cell-Centric Indexing.
  • Monica Landoni, Theo Huibers, Mohammad Aliannejadi, Emiliana Murgia and Maria Soledad Pera. Getting to Know You: Search Logs and Expert Grading to Define Children’s Search Roles in the Classroom.
  • Chris Kamphuis and Arjen de Vries. GeeseDB: A Python Graph Engine for Exploration and Search.
  • Johannes Kiesel, Xiaoni Cai, Roxanne El Baff, Benno Stein and Matthias Hagen. Toward Conversational Query Reformulation.
  • David Maxwell and Claudia Hauff. Developing Contemporary Web-Based Interaction Logging Infrastructure: Discussing the Achievements and Remaining Developmental Challenges of LogUI.
  • Kousuke Nagase and Hideo Joho. Enhancing SNS Profile Writing by Search-Based Assistant System.
  • Alberto Purpura and Gian Antonio Susto. A Bayesian Neural Model for Documents’ Relevance Estimation.
  • David Sander and Laura Dietz. EXAM: How to Evaluate Retrieve-and-Generate Systems for Users Who Do Not (Yet) Know What They Want.
  • Somin Wadhwa and Hamed Zamani. Towards System-Initiative Conversational Information Seeking.
  • Eugene Yang, David Lewis and Ophir Frieder. TAR on Social Media: A Framework for Online Content Moderation.

Short Papers and Abstracts

  • Dirk Ahlers. Searching in the Smart City?
  • Sophia Althammer. RUDI: Real-Time Learning to Update Dense Retrieval Indices. Best Presentation Award (sponsored by the Friends of SIGIR)
  • Serena Canu. It's messy out there. DBC’s journey towards its first test collection.
  • Dima El Zein. User knowledge and search goals in Information Retrieval: A benchmark and study on the evolution of users’ knowledge gain.
  • Benjamin Hättasch. WannaDB: Ad-hoc Structured Exploration of Text Collections Using Queries.
  • Nadja Geisler. Quest: A framework for query-driven explainers on tabular data. Best Presentation Award (sponsored by the Friends of SIGIR)
  • Adam Jatowt. Timeline as Information Retrieval and Ranking Unit in News Search.
  • Jimmy Lin. On the Separation of Logical and Physical Ranking Models for Text Retrieval Applications
  • Yashar Moshfeghi. NeuraSearch: Neuroscience and Information Retrieval.
  • Hugo Sousa. Temporal Relation Extraction: The Event Ordering Task.

Important Dates

Submission deadline is on 15 June 2021 AOE extended to: 25 June 2021 AOE.
Notifications will be on 30 July 2021
Early registration from 20 June 2021 to 30 August 2021
Late registration from 31 August 2021 to 12 September 2021

Keynotes

Speaker 1

Brian Johnson

Head of Search Engineering, Apple Media Products

Brian Johnson (Apple, USA)

Title: Apple Media Products Search

16 September 2021


Abstract

The Apple Media Products Search Team powers search for App Store, iTunes, Apple Music, Apple TV, Books, and Podcasts across multiple platforms (iOS, iPadOS, macOS, watchOS, tvOS, Web, Windows, Android) . App Store Search is used by millions of users daily serving over 1 billion requests a week across 150 countries and 40 languages. This scale and diversity offers incredible opportunities to improve search and solve challenging problems in information retrieval, ranking , query understanding, machine learning at scale, high performance computing and large scale systems design.

This talk covers three main topics.

Query Understanding

Brian will discuss what is necessary to have a deep understanding of our developers, their inventory, our users, and their intents and interests. Understanding user’s query intent is first step in Search. We need robust and scalable query understanding systems to correctly detect the intent of a user's query. Traditional Natural Language Processing techniques are important in query understanding, as are behavioral data mining, and newer deep learning techniques such as query embedding. Statistical query refinements allow us to learn synonyms, aliases, and nicknames.

Ranking beyond text

With this rich understanding of our users, queries, and inventory , we are working to build next generation search ranking for Apple Media Products. Some of the challenges we face include language processing, shifting inventory, and fraud prevention. When searching the App Store, users are presented with content that matches their query as well as content that matches the intent of their query.

Evaluation

How do we know how good we are? A robust evaluation platform helps us answer this question using well defined IR metrics for precision and recall. The ideas teams develop go through rigorous offline and online evaluations to predict how changes will perform in the wild. This allows for an agile development process. Ongoing loss pattern analysis drives continuous improvement.

Speaker 1

Fabian M. Suchanek

Full professor at Télécom Paris University, Paris

Fabian M. Suchanek (Télécom Paris University, Paris, France)

Title: A hitchhiker’s guide to Ontology

18 September 2021 (in presence)


Abstract

Knowledge bases are an important asset in many of today's AI-based applications, including personal assistants and search engines. In this talk, I will give an overview of our recent work in this area.

I will first talk about our main project, the YAGO knowledge base. In this context, I will present different methods of information extraction, in particular also the extraction of beliefs and causal relationships. I will then talk about the incompleteness of knowledge bases. We have developed several techniques to estimate how much data is missing in a knowledge base, as well as rule mining methods to derive that data. I will then present our work on efficient querying of knowledge bases.

Finally, I will talk about applications of knowledge bases in the domain of computational creativity and the digital humanities, as well as about our methods for explainable AI.

Bio

Fabian M. Suchanek is a full professor at the Telecom Paris University in France. Fabian developed inter alia the YAGO knowledge base, one of the largest public general-purpose knowledge bases. This earned him a honorable mention of the SIGMOD dissertation award and the 10 year Test of Time Award of The Web Conference (WWW 2018). His interests include information extraction, automated reasoning, and knowledge bases. Fabian has published around 90 scientific articles, among others at ISWC, VLDB, SIGMOD, WWW, CIKM, ICDE, and SIGIR, and his work has been cited more than 10000 times.

Speaker 1

Hinrich Schütze

Full professor at University of Munich, Germany

Hinrich Schütze (University of Munich, Germany)

Title: Humans Learn From Task Descriptions and So Should Our Models

17 September 2021 (online)


Abstract

In many types of human learning, task descriptions are a central ingredient. They are usually accompanied by a few examples, but there is very little human learning that is based on examples only. In contrast, the typical learning setup for NLP tasks lacks task descriptions and is supervised with 100s or 1000s of examples. This is even true for so-called few-shot learning, a term often applied to scenarios with tens of thousands of "shots".

Inspired by the GPT models, which also exploit task descriptions, we introduce Pattern-Exploiting Training (PET). PET reformulates task descriptions as cloze questions that can be effectively processed by pretrained language models. In contrast to GPT, PET combines task descriptions with supervised learning. We show that PET learns well from as little as ten training examples and outperforms GPT-3 on GLUE even though it has 99.9% fewer parameters.

Bio

Hinrich Schütze is a full professor at the University of Munich in Germany. He is Chair of Computational Linguistics and Director of the Center for Information and Language Processing. He is known for co-authoring the standard reference book on statistical natural language processing (http://nlp.stanford.edu/fsnlp/). His book "Introduction to Information Retrieval" (http://nlp.stanford.edu/IR-book/information-retrieval-book.html) (co-authored with Chris Manning and Prabhakar Raghavan) was published in 2008 and has been adopted by many IR courses throughout the world. Dr. Schütze obtained his PhD from Stanford University and has worked for a number of Silican Valley companies, including two large search engines and several text mining startups.


Venue

Department of Information Engineering

University of Padua, Padua, Italy

Full address: Via Gradenigo 6, Padova, Italy

University of Padua, Italy

The University of Padua is one of Europe’s oldest and most prestigious seats of learning; it is a multi-disciplinary university that aims to provide its students with both professional training and a solid cultural background.


The University of Padua was established in 1222. Defending freedom of thought in study and teaching has always been a distinctive feature which today lives on in the University motto: Universa Universis Patavina Libertas.


Padua also vaunts the world’s first university botanical garden and a permanent anatomical theatre, which was built by Girolamo Fabrici d’Acquapendente. William Harvey, who became famous for describing the circulation of the blood, studied in Padua, and in 1678 Elena Lucrezia Cornaro Piscopia became the first woman in the world to be awarded a university degree.



Quality Name Distance from the conference venue Distance from the city center Website Address Map
Hotel Galileo 8 min walk 25 min walk http://www.hotelgalileopadova.it/ Via Venezia, 30
Hotel NH Mantegna 8 min walk 22 min walk http://www.nh-hotels.it/hotel/nh-mantegna Via Nicolò Tommaseo, 61
Hotel Igea 14 min walk 11 min walk http://www.hoteligea.it/ Via Ospedale, 87
Hotel Eden 16 min walk 9 min walk http://www.hoteledenpadova.it/ Via C. Battisti, 255
Hotel Donatello 20 min walk 10 min walk http://www.hotel-donatello.net/ Via Del Santo, 102/104
Hotel Giotto 20 min walk 13 min walk http://www.hotelgiotto.com/ Piazzale Pontecorvo, 33
Hotel S. Antonio 22 min walk 9 min walk http://www.hotelsantantonio.it/ Via San Fermo, 118
Majestic Toscanelli 22 min walk 3 min walk http://www.toscanelli.com/ Via dell'Arco, 2
Hotel Dante 24 min walk 9 min walk http://www.hoteldante.eu/ Via San Polo, 5
Albergo Verdi 25 min walk 7 min walk http://www.albergoverdipadova.it/ Via Dondi dall'Orologio, 7
Hotel M14 29 min walk 13 min walk http://www.hotelm14.it/ Via Acquette, 9
B&B Torresino 30 min walk 12 min walk http://www.bb-padova.it/ Via Aleardo Aleardi, 35
Hotel Methis 34 min walk 15 min walk http://www.methishotel.com/ Riviera Paleocapa 70

Registration

DESIRES 2021 is a hybrid event. You can come to Padua, or you can follow online. Speakers are especially welcome to Padua, but we understand those who prefer an online presence only.

Please note that on-site registration is not possible.

At least one author, for each accepted paper, must register (one registration-one paper policy).


Registration link
https://www.registerme.eu/event/desires-2021/


Fees

Early registration (up to August, 30) Late registration (from August, 31 to September, 12)
Full (in presence) 350€ 450€
Student (in presence) 250€ 350€
Online only 70€ 85€

Online Conference registration fees include the access to all Conference Sessions.
In-person Conference registration fees also include:
  1. Coffee breaks as in the final program
  2. Lunches as in the final program
  3. Light dinner on September 16, 2021
  4. Social Dinner on September 17, 2021


Registration Fees are in Euro and include 22% VAT

Fees must be paid in Euro (€) to Sistema Congressi by credit card (Visa, Mastercard, Maestro, American Express, PayPal) or bank transfer. Xpay, the online payment system of Nexi (our payment platform) guarantees the security of the transaction.

If you prefer to pay by bank transfer, you should complete the registration form first. Bank transfer details and instructions are included in the registration confirmation email.

Please note that admission to the Symposium cannot be guaranteed unless full payment has been received. Where payment is still pending or delayed, registrations will be automatically cancelled without prior notice.



Confirmation email

Once you have completed your registration, you will receive an automatic registration confirmation from with the summary of the selected options. If you do not see the email in your inbox then please be sure to check your spam folder in case it got flagged as spam. If you do not receive this email, either your email was entered incorrectly or your registration is not complete. If this happens, please contact and do not re-register until further instructions



Cancellation policy and refunds

Online registration: No payment will be refunded.


In presence registration: The cancellation of the registration for personal reasons must be confirmed in writing before August 16, 2021 and accompanied by all personal bank information needed to proceed for the reimbursement.

Registration fees will be reimbursed, less the amount of € 50,00 for organizational and administrative charges. No reimbursement will be possible in case of no-show or after this date. All reimbursements will be processed after the Conference.



If you need further assistance or information about registration procedures, payments and invoices, contact registration@sistemacongressi.com

Organization

General Chairs

Omar Alonso (Instacart, USA)
Marc Najork (Google, USA)
Gianmaria Silvello (University of Padua, Italy)

Advisory Board

Maristella Agosti (University of Padua, Italy)
Ricardo Baeza-Yates (NTENT, USA; UPF, Spain; Univ. de Chile)
Bruce Croft (University of Massachusetts, USA)
J. Shane Culpepper (RMIT University, Australia)
Susan Dumais (Microsoft, USA)
Norbert Fuhr (University of Duisburg-Essen, Germany)
Donna Harman (NIST, USA)
Kalervo Jarvelin (University of Tampere, Finland)
Jan Pedersen (eBay, USA)
Gerhard Weikum (MPI, Germany)

Program Committee for DESIRES 2021

Re-confirmation in progress

Dyaa Albakour (Signal Media, UK) - confirmed for 2021!
James Allan (University of Massachusetts, USA) - confirmed for 2021!
Leif Azzopardi (University of Strathclyde, UK)
Krisztian Balog (University of Stavanger, Norway)
Alessandro Benedetti (Sease, UK) - confirmed for 2021!
B. Barla Cambazoglu (RMIT University, Australia) - confirmed for 2021!
Diego Ceccarelli (Bloomberg L.P., UK) - confirmed for 2021!
Nick Craswell (Microsoft, USA) - confirmed for 2021!
Jeff Dalton (University of Glasgow, UK) - confirmed for 2021!
Arjen de Vries (Radboud University, The Netherlands) - confirmed for 2021!
Nicola Ferro (University of Padua, Italy) - confirmed for 2021!
Dennis Fetterly (Google, USA)
Parth Gupta (Amazon, USA)
Claudia Hauff (Delft University of Technology, The Netherlands) - confirmed for 2021!
Vasileios Kandylas (Microsoft, USA) - confirmed for 2021!
Evangelos Kanoulas (University of Amsterdam, The Netherlands) - confirmed for 2021!
Jussi Karlgren (Gavagai and KTH Royal Institute of Technology, Sweden) - confirmed for 2021!
Emre Kiciman (Microsoft, USA) - confirmed for 2021!
Matthew Lease (University of Texas at Austin, USA) - confirmed for 2021!
Dave Lewis (Brainspace, A Cyxtera Business, USA)
Jimmy Lin (University of Waterloo, Canada)
Craig Macdonald (University of Glasgow, UK) - confirmed for 2021!
Maria Maistro (University of Copenhagen, Denmark) - confirmed for 2021!
Edgar Meij (Bloomberg L.P., UK) - confirmed for 2021!
Donald Metzler (Google, USA) - confirmed for 2021!
Yashar Moshfeghi (University of Strathclyde, UK)
Jeremy Pickens (Catalyst Repository Systems, USA) - confirmed for 2021!
Paolo Rosso (Universitat Politècnica de València, Spain) - confirmed for 2021!
Tony Russell-Rose (Goldsmiths, University of London, UK) - confirmed for 2021!
Sunita Sarawagi (IIT Bombay, India)
Ian Soboroff (NIST, USA) - confirmed for 2021!
Damiano Spina (RMIT University, Australia) - confirmed for 2021!
Paul Thomas (Microsoft, USA)
Andrew Trotman (University of Otago, Australia) - confirmed for 2021!
Christophe Van Gysel (Apple Inc., USA)
Olivier Van Laere (Apple Inc., USA) - confirmed for 2021!
Wouter Weerkamp (904Labs, The Netherlands)
Cong Yu (Google, USA)
Hamed Zamani (University of Massachusetts, USA) - confirmed for 2021!

Organization Chair

Dennis Dosso (University of Padua, Italy)

Proceedings Chair

Stefano Marchesin (University of Padua, Italy)

Program

All the events will take place in Padua.

Early Registration

meetup

London Information Retrieval Meetup (in Padua)

DESIRES hosts the Information Retrieval Meetup, usually organized by Sease in London, UK, as a satellite event. Participation is free of charge.


Online participation is free of charges, please join the Zoom meeting: Click here


Alessandro Benedetti and Andrea Gazzarini

Rated Ranking Evaluator Enterprise: the next generation of free Search Quality Evaluation Tools


Giorgio Maria Di Nunzio

Am I Missing Something? Query Performance Prediction by Means of Intent-Aware Metrics in Systematic Reviews

Welcome reception

Welcome reception

Hendrix Bar, Piazza dei Signori, 38

This is an aperitif on the public square. We will gather in 'Piazza dei Signori' to enjoy the lively atmosphere typical of Padua and its students.

This aperitif is a pre-dinner moment. Afterwards, the participants can enjoy the city and its many dinner places. Please consider to reserve a table given the possible limited availability due to COVID-19 restrictions.

Opening

Opening Gianmaria Silvello

Opening

Systems

Chair: Jaap Kamps


Mayank Anand, Jiarui Zhang, Ji Xin and Jimmy Lin.

Serverless BM25 Search and BERT Reranking


Chris Kamphuis and Arjen de Vries.

GeeseDB: A Python Graph Engine for Exploration and Search


David Maxwell and Claudia Hauff.

Contemporary Web-Based Interaction Logging Infrastructure: Discussing the Achievements and Remaining Developmental Challenges of LogUI

Opening

Coffee Break

Opening

Search Domains and Applications

Chair: Arjen de Vries


Aleksandar Bobic, Jean-Marie Le Goff and Christian Guetl.

Towards Supporting Complex Retrieval Tasks Through Graph-Based Information Retrieval and Visual Analytics


Benjamin Hättasch, Nadja Geisler and Carsten Binnig.

Netted?! How to Improve the Usefulness of Spider & Co.


Monica Landoni, Theo Huibers, Mohammad Aliannejadi, Emiliana Murgia and Maria Soledad Pera.

Getting to Know You: Search Logs and Expert Grading to Define Children’s Search Roles in the Classroom

Opening

Lunch Pizzeria al Porteo (3 minutes from the venue)

Opening

Short Papers Session 1

Chair: Omar Alonso


Dirk Ahlers.

Searching in the Smart City?


Jimmy Lin, Xueguang Ma, Joel Mackenzie and Antonio Mallia.

On the Separation of Logical and Physical Ranking Models for Text Retrieval Applications


Adam Jatowt.

Timeline as Information Retrieval and Ranking Unit in News Search.

Opening

Explorative search and querying

Chair: Nicola Ferro


Jeff Heflin, Brian D. Davison and Haiyan Jia.

Exploring Dataset via Cell-Centric Indexing


Guglielmo Faggioli and Stefano Marchesin.

What Makes a Query Semantically Hard?


Roger Bradford.

Lessons Learned from 20 Years of Implementing LSI Applications

Opening

Keynote 1 Brian Johnson, Apple

Apple Media Products Search

conference

"Light" dinner

Enotavola, Via dell'arco 37, Padova

Enotavola is a delicious restaurant right in the middle of the old Jewish ghetto.

The restaurants is reserved for DESIRES participants. We will dine inside with a full course menu based on fish. Veggie alternatives are available, of course.

Opening

Keynote 2 Hinrich Schütze

Humans Learn From Task Descriptions and So Should Our Models

Opening

Coffee Break

Opening

Short Papers Session 2

Dima El Zein.

User knowledge and search goals in Information Retrieval: A benchmark and study on the evolution of users’ knowledge gain


Benjamin Hättasch.

WannaDB: Ad-hoc Structured Exploration of Text Collections Using Queries


Nadja Geisler.

Quest: A framework for query-driven explainers on tabular data


Serena Canu.

It's messy out there. DBC’s journey towards its first test collection


Sophia Althammer.

RUDI: Real-Time Learning to Update Dense Retrieval Indices

Opening

Lunch Pizzeria al Porteo (3 minutes from the venue)

Opening

Conversational Search

Krisztian Balog.

Conversational AI from an Information Retrieval Perspective: Remaining Challenges and a Case for User Simulation


Johannes Kiesel, Xiaoni Cai, Roxanne El Baff, Benno Stein and Matthias Hagen.

Toward Conversational Query Reformulation


Souvick Ghosh and Satanu Ghosh.

"Do Users Need Human-like Conversational Agents?'' - Exploring Conversational System Design Using Framework of Human Needs.


Somin Wadhwa and Hamed Zamani.

Towards System-Initiative Conversational Information Seeking.

Opening

Search and user-generated content

Kousuke Nagase and Hideo Joho.

Enhancing SNS Profile Writing by Search-Based Assistant System


Eugene Yang, David Lewis and Ophir Frieder.

TAR on Social Media: A Framework for Online Content Moderation


David Sander and Laura Dietz.

EXAM: How to Evaluate Retrieve-and-Generate Systems for Users Who Do Not (Yet) Know What They Want

conference

Social activity

We'll stroll around Padua, do some sightseeing.

conference

Social dinner

Caffè Pedrocchi, Via VIII Febbraio, Padova

The Pedrocchi Café (Caffè Pedrocchi in italian) is a café founded in the 18th century in central Padua, Italy.

The café has historical prominence because of its role in the 1848 riots against the Habsburg monarchy, as well as for being an attraction for artists over the last century from the French novelist Stendhal to Lord Byron to the Italian writer Dario Fo.

We will have an entire floor dedicated to the conference and we will enjoy a full-course Italian dinner.

Opening

Keynote 3 Fabian M. Suchanek

A hitchhiker’s guide to Ontology

Opening

Coffee Break

Opening

Neural Models

Alberto Purpura and Gian Antonio Susto.

A Bayesian Neural Model for Documents’ Relevance Estimation


Arian Askari and Suzan Verberne.

Combining lexical and neural retrieval with longformer-based summarization for effective case law retrieval


Opening

Short Papers Session 3

Yashar Moshfeghi.

NeuraSearch: Neuroscience and Information Retrieval


Hugo Sousa.

Temporal Relation Extraction: The Event Ordering Task

Opening

Closing Omar Alonso

Announcement of the next DESIRES conference: when and where

Gold sponsor

Silver sponsors

Bronze sponsor

Patrocinated by