=Paper=
{{Paper
|id=Vol-2521/preface
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-2521/preface.pdf
|volume=Vol-2521
}}
==None==
<pdf width="1500px">https://ceur-ws.org/Vol-2521/preface.pdf</pdf>
<pre>
    Proceedings of the 3rd Workshop on Natural
    Language for Artificial Intelligence co-located
                 with AIxIA 2019

               Mehwish Alam1 , Valerio Basile2 , Felice Dell’Orletta3
                       Malvina Nissim4 , Nicole Novielli5
         1
             FIZ Karlsruhe – Leibniz Institute for Information Infrastructure,
                      Karlsruhe Institute of Technology Germany
                           mehwish.alam@fiz-karlsruhe.de
                              2
                                 University of Turin, Italy
                               valerio.basile@unito.it
                 3
                   Istituto di Linguistica Computazionale, Pisa, Italy
                           felice.dellorletta@ilc.cnr.it
                        4
                          University of Groningen, Netherlands
                                   m.nissim@rug.nl
                        5
                          University of Bari “Aldo Moro”, Italy
                              nicole.novielli@uniba.it



Preface

Natural Language Processing plays a fundamental role in current AI research,
as target of different scientific and industrial interests. At the same time, several
AI achievements have shown their beneficial impact on applications in linguis-
tic modelling, processing and generation. Especially the recent advancements
in deep learning are drastically changing the landscape of NLP, where the con-
tinuous performance improvement on well established tasks is happening at an
unprecedented speed. Therefore, Natural Language Processing is a rich research
topic, whose cross-fertilization with AI spans a number of independent areas such
as Cognitive Computing, Robotics as well as Human-Computer Interaction.
    We believe that new technological challenges and opportunities rise at the
boundary between NLP and AI. On the one hand, AI applications benefit from a
deeper understanding of problems related to Natural Language, and thus the in-
tegration of advanced NLP techniques. On the other hand, NLP benefits greatly
from being used in wider areas of AI where problems and methodologies related
to NL can be evaluated in new contexts.
    Given these premises, the workshop “Natural Language for Artificial Intelli-
gence” (NL4AI) aims at providing a meeting forum for stimulating and dissem-
inating research where researchers (especially those affiliated with Italian insti-
tutions) can network and discuss their results in an informal way6 . In particular,
the goal of the NL4AI workshop is to explore the role of Natural Language and
Natural Language Processing in Artificial Intelligence applications.
6
    http://sag.art.uniroma2.it/NL4AI


                                           1
    NL4AI 2019 was the 3rd edition of this workshop, taking place on November
19th and 20th in Rende, Italy. We thank the Italian Association of Computa-
tional Linguistics (AILC)7 , that supported the invitation of the speakers to the
workshop: Albert Gatt and Roberto Basili.
    We received 11 submissions, 8 of which were accepted after peer-review. In
terms of topics, the contributions to the workshop range from pure NLP works
to broader proposals bridging NLP with other AI applications.
    A common theme is that of under-resourced languages and domains. In
this direction, the paper by Arukgoda et al. employs deep learning to alleviate
the scarcity of resources for automatic translation of Sinhala-Tamil sentences,
while Kothalawala et al. propose an approach based on online learning to improve
Named Entity Recognition in the Sinhala language. Two papers (Gambino and
Pirrone; Polignano et al.) explore the application of the recently popular BERT
model to the Italian language.
    Two papers propose applications of NLP techniques to different tasks.
Frummet et al. introduce an annotation scheme and classification task to improve
conversational agents, by injecting knowledge about information needs into the
model. Monett and Winkler employ a NLP pipeline to support the creation of
an ontological resource on human intelligence.
    Finally, two works are focused on various Natural Language Processing
tasks. The first is verb semantic similarity, topic of the paper by Ravelli et al.
who introduce ontologically-informed word embeddings (Ref-Vectors) to improve
the performance. The second is predicting verb aspectual coding, for which Richter
and Yousef present the result of a pilot study on six slavic languages.
    As a final remark, the program co-chairs would like to thank all the members
of the Program Committee as well as the local organizers of the AIIA 2019
Conference8 .




7
    http://www.ai-lc.it/
8
    https://aiia2019.mat.unical.it/


                                        2

</pre>