<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta>
      <title-group>
        <article-title>Preface to the CLiC-it 2024 Proceedings</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Felice Dell'Orletta</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Alessandro Lenci</string-name>
          <xref ref-type="aff" rid="aff2">2</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Simonetta Montemagni</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Rachele Sprugnoli</string-name>
          <xref ref-type="aff" rid="aff1">1</xref>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>CNR-Institute for Computational Linguistics “A. Zampolli”</institution>
          ,
          <addr-line>Pisa</addr-line>
        </aff>
        <aff id="aff1">
          <label>1</label>
          <institution>University of Parma</institution>
        </aff>
        <aff id="aff2">
          <label>2</label>
          <institution>University of Pisa</institution>
        </aff>
      </contrib-group>
      <abstract>
        <p>This year marks the 10th anniversary of the Italian Con- ference and for publication in the proceedings, resulting ference on Computational Linguistics. To celebrate this in an acceptance rate of 85.7% (with respect to the rate important achievement for the whole Italian community, of 87.21% for CLiC-it 2023). CLiC-it 2024 is held in Pisa, like for its first edition in Out of the 114 accepted proposals, 32 were included 2014, from 4th to 6th December 2024. in the program as oral presentations (divided into 6 oral Concerning the scientific organization of the confer- sessions) and the remaining 82 were assigned to one of ence, two types of submissions were possible: regular the three poster sessions dedicated to the regular papers. papers, describing substantial, original, completed, and As usual, the criterion for assigning a proposal to an oral unpublished work, and short research communications or a poster session was based on the contents and not on of outstanding papers accepted in both 2023 and 2024 by the quality of the proposal. An additional poster session major publication venues, such as the major international was organized for the 19 research communications that Computational Linguistics conferences (workshops ex- are not published in the proceedings. cluded) or international journals. These latter contribu- An important novelty of this edition is the organization tions are not published in the conference proceedings but of the special event CALAMITA (Challenge the Abilities are aimed to promote the dissemination of high-quality of LAnguage Models in ITAlian) which took place on research within the Italian community. the afternoon of December 6th. The aim of CALAMITA, Like in the previous edition, the conference was not or- that collected 20 tasks, is the collaborative creation of a ganized into separate tracks. Submissions were assigned dynamic benchmark to evaluate Large Language Models to area chairs (thirteen program committee members) supporting the Italian language. according to a set of topics chosen by the authors at sub- In addition to the technical program, this year the mission time. This way we were able to achieve a better conference hosted an interview with Oliviero Stock (Fonbalance of papers for each area chair, while respecting dazione Bruno Kessler, Trento) and Nicoletta Calzolari their research interests. Paper assignment to reviewers (CNR-ILC, Pisa) on the past, present, and future of comwas also managed globally, with a single pool of 140 putational linguistics in Italy, in relation to the wider reviewers, to better monitor the whole process. international landscape. In addition, we were honored to We have received a record number of submissions for have as invited speakers two internationally recognized regular papers: 133 compared to 86 in 2023 (+47). This researchers: result demonstrates the vitality and growth of the Italian Computational Linguistics community. In addition we received 19 submissions for short research communications. During the reviewing process, each regular paper submission was reviewed by three independent reviewers in single-blind fashion. At the end of the process, 114 proposals were accepted for presentation at the con-</p>
      </abstract>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>• Giosuè Baggio (Norwegian University of Science
and Technology, Trondheim), with a keynote
entitled “Meaning and grammar in a parallel
architecture for language processing”: This talk introduces
a novel cognitive and computational architecture
for human language processing. The architecture
features parallel streams for meaning and
grammar, drawing from a shared mental lexicon and
contributing concurrently to incremental updates
of a discourse model. Intermediate representations
are generated independently within each stream,
resulting in a range of possible interactions between
meaning and grammar — from dominance and
redundancy to competition and conflict.
Linguistic phenomena illustrating these diferent
interactions and present experimental results
corroborating the architecture’s processing consequences are
presented. Then a computational model that aligns
with experimental results and that demonstrates and Talia4 (Silver), aequa-tech5, Almawave6 and ELRA7
the importance of intermediate representations is (Bronze), Translated8 (Iron), and Meta9 that supported
described. Some considerations on how the theory the trip of Dieuwke Hupkes.
reconciles two key principles in linguistics — com- Finally, we want to thank very much the Associazione
positionality and context — and the traditions that Italiana di Linguistica Computazionale (AILC), all the
build on them conclude the talk.. members of the Association Board who supported and
• Dieuwke Hupkes (Meta AI Research, Paris, guided us in organizing the conference.</p>
      <p>France), with a keynote entitled “Generalisation
in LLMs – and beyond”: “Good generalisation” is Pisa, December 2024
often mentioned as a desirable property for NLP
models. For LLMs, in the light of the sheer train- Conference Chairs
ing corpora, among other things, it becomes more
and more challenging to understand if our models • Felice Dell’Orletta, CNR-Institute for
Computageneralise, and how important that still is. In this tional Linguistics "A. Zampolli"
presentation, I briefly discuss generalisation in NLP • Alessandro Lenci, University of Pisa
on a higher level, and then move on to discussing it • Simonetta Montemagni, CNR-Institute for
specifically for LLMs. What types of generalisation Computational Linguistics "A. Zampolli"
are still important, how would we evaluate it, and
is it possible to evaluate it independently from the • Rachele Sprugnoli, University of Parma
training corpus? I will – hopefully – answer some
of your questions, but also raise a lot more!.</p>
    </sec>
    <sec id="sec-2">
      <title>CALAMITA Chairs</title>
      <p>In the first morning of the Conference, Bernardo
Magnini and Giovanni Bonetta (FBK, Trento) gave a
tutorial entitled "You Are what You Eat: Processing Data
for Training and Evaluating LLMs".</p>
      <p>This year we received 9 candidate theses for the
“Emanuele Pianta Award for the Best Master
Thesis”. This special prize for the best Master Thesis (Laurea
Magistrale) in Computational Linguistics, submitted at
an Italian University, commemorates the late lamented
Emmanuele Pianta and is endorsed by AILC. The
candidate theses have been evaluated by a jury composed
by Gianluca Lebani (Ca’ Foscari University of Venice),
Rachele Sprugnoli (University of Parma) and Sara Tonelli
(Fondazione Bruno Kessler, Trento). The winner was
awarded during the closing session of the conference by
the members of the jury.</p>
      <p>We thank all the people and institutions involved
in the organization of the conference, all area chairs,
reviewers, and all participants, who contributed to the
success of the event. Chairs and reviewers are named in
the following pages. We are grateful to the CNR-Institute
for Computational Linguistics "A. Zampolli" that made
CLiC-it 2024 possible by hosting the event and supporting
us greatly in the processes of local organization, and to
the University of Pisa1 that endorsed our event.</p>
      <p>We would like to thank our supporters, who
generously provided funds and services that are crucial for
the realization of this event: Aptus.AI2, CLARIN-IT3
1https://www.unipi.it/
2https://www.aptus.ai/
3https://www.clarin-it.it/
• Pierpaolo Basile, University of Bari Aldo Moro
• Danilo Croce, University of Rome, Tor Vergata
• Malvina Nissim, University of Groningen
• Viviana Patti, University of Turin
CALAMITA Data and Evaluation
Team
• Giuseppe Attanasio, Instituto de
Telecomunicações, Lisbon
• Federico Borazio, University of Rome, Tor
Vergata
• Maria Francis, University of Groningen &amp;
University of Trento
• Jacopo Gili, University of Turin
• Elio Musacchio, University of Bari Aldo Moro
• Matteo Rinaldi, University of Turin
• Daniel Scalena, University of Groningen &amp;
University of Milan Bicocca
Local Organization Committee
• Chiara Alzetta, CNR-Institute for
Computational Linguistics "A. Zampolli"
• Serena Auriemma, University of Pisa
4https://talia.cloud/
5https://aequa-tech.com/
6https://www.almawave.com/it/
7https://www.elra.info/
8https://translated.com/
9https://www.meta.com/
Registration System Management</p>
    </sec>
    <sec id="sec-3">
      <title>Area Chairs</title>
    </sec>
    <sec id="sec-4">
      <title>Proceedings Chairs</title>
    </sec>
    <sec id="sec-5">
      <title>Webmasters</title>
    </sec>
    <sec id="sec-6">
      <title>Publicity Chair</title>
    </sec>
    <sec id="sec-7">
      <title>Booklet</title>
      <p>Reviewers</p>
    </sec>
  </body>
  <back>
    <ref-list />
  </back>
</article>