=Paper=
{{Paper
|id=Vol-2693/xpreface
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-2693/xpreface.pdf
|volume=Vol-2693
}}
==None==
<pdf width="1500px">https://ceur-ws.org/Vol-2693/xpreface.pdf</pdf>
<pre>
                                                 Preface

   There have been spectacular advances in many tasks of natural language processing (NLP) by making use
of artificial intelligence (AI) techniques such as machine/deep learning (M/DL). However, these
improvements do not affect all NLP tasks, specifically those that require deep linguistic knowledge, natural
language understanding, semantic inference and reasoning. In hybrid architectures, M/DL approaches co-exist
with symbol-manipulation as symbolic models seem to play an important role in inference and reasoning
about abstract knowledge.
   We call hybrid intelligence (HI) those architectures that integrate symbolic information into statis-tical or
neural-based models so as to allow machines to learn new knowledge in a more ‘intelligent’ way by endowing
them with common sense and deep understanding. The main aim of HI in NLP is to inject deep and structured
linguistic knowledge (not just annotated text) into M/DL models to develop hybrid architectures for NLP
tasks. In more general terms, the concept of HI consists of combining machine and human intelligence to
overcome the shortcomings of existing AI systems. Abstract and structured knowledge from specialists can be
used not just as training data to learn uninterpretable black-box models, but also to design the models
themselves by making them more transparent, easy to interpret by humans, and more efficient for specific
purposes.
   HI4NLP workshop has provided a forum for discussing about exciting research on HI methodology for
NLP tasks, with a representative example of the most recent work on this field. The resulting program
consists of 6 papers accepted for presentation over 9 submissions. In addition, two keynote talks have been
included, by Cesar Gonzalez-Perez (Incipit, CSIC) and Carlos Gómez-Rodríguez (Universidade da Coruña).
   In this edition, two prizes have been awarded. The best paper award was to TALES: Test Set of Portuguese
Lexical-Semantic Relations for Assessing Word Embeddings by Hugo Gonçalo Oiveira, Tiago Sousa and Ana
Alves; the second-best paper prize was to The Semantics of Historical Knowledge. Labelling Strategies for
Interdisciplinary and Digital Research in History by Esther Travé Allepuz, Pablo Del Fresno Bernal, Alfred
Mauri Martí and Sonia Medina Gordo. Both papers will receive and invitation to submit an extended version
to prestigious international journals.

HI4NLP organisers,
Pablo Gamallo, CiTIUS, Univ. de Santiago de Compostela
Marcos Garcia, LyS, Univ. da Corunha
Patricia Martín-Rodilla, IRLab, Univ. da Corunha
Martín Pereira-Fariña, Faculty of Philosophy, Univ. de Santiago de Compostela

Program Committee
Livy Real (IBM)                                           Carlos Ramisch (Aix Marseille University)
Sara Tonelli (Fondazione Bruno Kessler)                   Luísa Coheur (IST/INESC-ID)
Paulo Quaresma (Universidade de Évora)                    Thiago Pardo (University of São Paulo)
Renata Vieira (PUCRS)                                     Arkaitz Zubiaga (Queen Mary University of London)
Gaël Dias (Normandie University)                          Miguel A. Alonso (Universidade da Coruña)
Nelleke Oostdijk (Radboud University)                     Daniela Claro (Federal University of Bahia)
Aline Villavicencio (University of Sheffield)             Manuel Vilares Ferro (University of Vigo)
Jesús Vilares (Universidade da Coruña, CITIC)             Cesar Gonzalez-Perez (Incipit, CSIC)

</pre>