Humanist Discussion Group

Humanist Archives: June 3, 2021, 5:58 a.m. Humanist 35.62 - events: computational linguistics; AI in fiction; historical networks

              Humanist Discussion Group, Vol. 35, No. 62.
        Department of Digital Humanities, University of Cologne
                      Hosted by DH-Cologne
                Submit to:

    [1]    From: Stan Szpakowicz <>
           Subject: Second Call for Papers: The 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (138)

    [2]    From: Willard McCarty <>
           Subject: AI Fictions conference: June 3-5 live sessions + a game + an online exhibition + 30 prerecorded talks (19)

    [3]    From: Marten Düring <>
           Subject: Now online: conference programme Historical Networks – Réseaux Historiques – Historische Netzwerke Inbox (134)

        Date: 2021-06-02 21:12:53+00:00
        From: Stan Szpakowicz <>
        Subject: Second Call for Papers: The 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature

LaTeCH-CLfL 2020:
The 5th Joint SIGHUM Workshop on Computational Linguistics for
Cultural Heritage, Social Sciences, Humanities and Literature

to be held on-line on 11 November 2021 in conjunction with EMNLP 2021

Second Call for Papers (with apologies for cross-posting)

Organisers: Stefania Degaetano-Ortlieb, Anna Kazantseva, Nils Reiter,
Stan Szpakowicz

LaTeCH-CLfL 2021 is the fifth in a series of meetings for NLP
researchers who work with data from the broadly understood arts,
humanities and social sciences, and for specialists in those disciplines
who apply NLP techniques in their work. The workshop continues a long
tradition of annual meetings. The SIGHUM Workshops on Language
Technology for Cultural Heritage, Social Sciences, and Humanities
(LaTeCH) ran from 2007 to 2016. The ACL Workshops on Computational
Linguistics for Literature (CLfL) took place from 2012 to 2016. The
first four joint workshops (LaTeCH-CLfL) were held from 2017 to 2020.

Topics and Content

In the Humanities, Social Sciences, Cultural Heritage and literary
communities, there is increasing interest in, and demand for, NLP
methods for semantic and structural annotation, intelligent linking,
discovery, querying, cleaning and visualization of both primary and
secondary data. This is even true of primarily non-textual collections,
given that text is also the pervasive medium for metadata. Such
applications pose new challenges for NLP research: noisy, non-standard
textual or multi-modal input, historical languages, vague research
concepts, multilingual parts within one document, and so no. Digital
resources often have insufficient coverage; resource-intensive methods
require (semi-)automatic processing tools and domain adaptation, or
intense manual effort (e.g., annotation).

Literary texts bring their own problems, because navigating this form of
creative expression requires more than the typical information-seeking
tools. Examples of advanced tasks include the study of literature of a
certain period, author or sub-genre, recognition of certain literary
devices, or quantitative analysis of poetry.

NLP methods applied in this context not only need to achieve high
performance, but are often applied as a first step in research or
scholarly workflow. That is why it is crucial to interpret model results
properly; model interpretability might be more important than raw
performance scores, depending on the context.

More generally, there is a growing interest in computational models
whose results can be used or interpreted in meaningful ways. It is,
therefore, of mutual benefit that NLP experts, data specialists and
Digital Humanities researchers who work in and across their domains get
involved in the Computational Linguistics community and present their
fundamental or applied research results. It has already been
demonstrated how cross-disciplinary exchange not only supports work in
the Humanities, Social Sciences, and Cultural Heritage communities but
also promotes work in the Computational Linguistics community to build
richer and more effective tools and models.

Topics of interest include, but are not limited to, the following:

     •    adaptation of NLP tools to Cultural Heritage, Social Sciences,
          Humanities and literature;
     •    automatic error detection and cleaning of textual data;
     •    complex annotation schemas, tools and interfaces;
     •    creation (fully- or semi-automatic) of semantic resources;
     •    creation and analysis of social networks of literary characters;
     •    discourse and narrative analysis/modelling, notably in literature;
     •    emotion analysis for the humanities and for literature;
     •    generation of literary narrative, dialogue or poetry;
     •    identification and analysis of literary genres;
     •    linking and retrieving information from different sources,
          media, and domains;
     •    modelling dialogue literary style for generation;
     •    modelling of information and knowledge in the Humanities,
          Social Sciences, and Cultural Heritage;
     •    profiling and authorship attribution;
     •    search for scientific and/or scholarly literature;
     •    work with linguistic variation and non-standard or historical
          use of language.

Information for Authors

We invite papers on original, unpublished work in the topic areas of the
workshop. In addition to long papers, we will consider short papers and
system descriptions (demos). We also welcome position papers.

     •    Long papers, presenting completed work, may consist of up to
eight (8) pages of content plus additional pages of references; final
camera-ready versions of accepted long papers will be given one
additional page of content (up to 9 pages) so that reviewers’ comments
can be taken into account.
     •    A short paper / demo can present work in progress, or the
description of a system, and may consist of up to four (4) pages of
content plus additional pages of references. Upon acceptance, short
papers will be given five (5) content pages in the proceedings.
     •    A position paper — clearly marked as such — should not exceed
six (6) pages including references.

All submissions are to use the EMNLP stylesheets (for LaTeX / Overleaf
and MS Word), to be announced soon at Papers should be submitted
electronically, in PDF, via the LaTeCH-CLfL2021 submission website at

Reviewing will be double-blind. Please do not include the authors’ names
and affiliations, or any references to Web sites, project names,
acknowledgements and so on — anything that immediately reveals the
authors’ identity. Self-references should be kept to a reasonable
minimum, and anonymous citations cannot be used. Please see for the
official EMNLP policy (except that our anonymity period starts later).

Accepted papers will be published in the workshop proceedings, and later
available in the ACL Anthology.

Important Dates

Anonymity period begins on July 1, 2021.
Paper submission deadline:    August 5, 2021
Notification of acceptance:    September 5, 2021
Camera-ready papers due:    September 15, 2021
Workshop date:            December 11, 2021

More on the organisers

Stefania Degaetano-Ortlieb, Language Science and Technology, Saarland
Anna Kazantseva, National Research Council of Canada
Nils Reiter, Department for Digital Humanities, University of Cologne
Stan Szpakowicz, School of Electrical Engineering and Computer Science,
University of Ottawa


        Date: 2021-06-02 12:54:53+00:00
        From: Willard McCarty <>
        Subject: AI Fictions conference: June 3-5 live sessions + a game + an online exhibition + 30 prerecorded talks

IA Fictions
3-5 June 2021

IA Fictions est le premier colloque jamais organisé sur le thème de
l’intelligence artificielle (IA) dans la fiction (littérature, séries,
films, bande dessinée, jeux vidéo, arts plastiques) : on s’intéressera
aux représentations de l’IA et à leurs significations ainsi qu’aux
usages créatifs de l’IA pour produire et comprendre la fiction en
textes, en sons, en images fixes et animées, comme en jeux vidéo.

AI Fictions is the first conference ever organized on the theme of
Artificial Intelligence in fiction (literature, series, films, comics,
video games): the focus will be on representations of AI and their
meanings, as well as the creative uses of AI to produce and understand

Programme and Zoom invitation available from the sites.

        Date: 2021-06-02 07:56:00+00:00
        From: Marten Düring <>
        Subject: Now online: conference programme Historical Networks – Réseaux Historiques – Historische Netzwerke Inbox

Dear all,

The conference „Historical Networks – Réseaux Historiques – Historische
Netzwerke“ co-organised by the Historical Network Research
( group and Réseaux et Histoire
( will take place from Wednesday, June 30th
until Friday, July 2nd, 2021. The complete programme is now online and
registration is open. For more information about the programme, registration and
more details about the conference, please visit our conference website

Questions, suggestions, notes regarding the conference? Write us at 


On Wednesday, June 30th, HNR+ResHist 2021 will offer four workshops for
beginners as well as advanced network researchers:

Analysis of Two-Mode Networks with Python
Demival Vasques Filho

Exponential Random Graph Models: Theory and Applications on Historical Networks
Antonio Fiscarelli

From historical source to network data
Claire Lemercier

Introduction to Social Network Analysis: Basics and Historical Specificities
Martin Grandjean

Registration ( for the
workshops takes place through EventBrite. Please note that the number of
participants per workshop is limited and that the deadline for registering is 23
June (23:30 pm CEST).


HNR+ResHist2021 is proud to present two keynotes which will be delivered by
Marion Maisonobe (
(CNRS, Paris) and Matteo Valleriani (https://www.mpiwg- (MPIWG, Berlin). You can find their abstracts
here below. To attend the keynotes, please register for the conference
conference-2021-1-2-july-2021-tickets-156643959299) (deadline: 23 June, 23:30 pm




The lecture will first provide an overview of the corpus and of its historical
meaning from the perspective of the main research question of the project,
namely the question concerned with the mechanisms of knowledge homogenization in
the early modern time and, therefore, with those processes that allowed for the
emergence of a scientific identity of Europe.

Secondly, the major results concerned with the semantic analysis of the corpus
and based on a formalization of the data in terms of a multiplex network will be
shown. In particular it will be shown a) how a family of historical sources was
detected that then executed a hegemonic role all over Europe therefore greatly
contributing to the process of homogenization, b) how treatises, denominated
“great transmitters”, allowed for the perpetuation of traditional knowledge for
about 200 years however in the context of continuous innovation, and c) how
different treatises were identified that are the main responsible for the
impactful and enduring innovations.

Third, the lecture will present a new network model able to display the process
of knowledge transformation in its social and economic context. The lecture
therefore concludes by showing analyses conducted in order to understand
correlations between families of treatises (semantic knowledge) on one side and
societal groups on the other.



We identify three traditional ways of integrating places in network analysis.
Firstly, it is common to start from relationships between individuals, families
and businesses and to aggregate these relationships to consider the interactions
between places that they create (A). Secondly, places can be the instrument of
network construction. In other words, the co-presence in certain places makes it
possible to deduce relationships between entities (B). Thirdly, the network can
be immediately „spatial“ in the sense that the entities in relation as well as
their links are materially anchored in space (for example, a hydrographic
network, a metro map or a road network) (C). We will see that the sources,
analytical issues and methods, and types of visualisation associated with these
different networks vary. Our presentation will focus more specifically on type A
and B networks by taking up, detailing and updating the methodological proposals
of a collaborative research work on the visualization of scholarly worlds from
Antiquity to the present day (Andurand et al., 2015).


Nous distinguons trois manières classiques d’intégrer les lieux en analyse de
réseaux. Premièrement, il est fréquent de partir de relations entre individus,
familles, entreprises et d’agréger ces relations pour considérer les
interactions entre lieux qu’elles dessinent (A). Deuxièmement, les lieux peuvent
être l’instrument de la construction du réseau. Autrement dit, c’est la co-
présence en certains lieux qui permet de déduire des relations entre entités
(B). Troisièmement, le réseau peut être immédiatement « spatial » au sens où les
entités en relation ainsi que leurs liens sont matériellement ancrés dans
l’espace (par exemple, un réseau hydrographique, un plan de métro ou une trame
viaire) (C). Nous verrons que les sources, les enjeux et méthodes d’analyse
ainsi que les types de visualisation associées à ces différents réseaux varient.
Notre exposé se concentrera plus particulièrement sur les réseaux du type A et B
en reprenant, détaillant et actualisant les propositions méthodologiques d’un
travail de recherche collaboratif sur la visualisation des mondes savants de
l’Antiquité à nos jours à partir de différentes sources (Andurand et al., 2015).

We look forward to welcoming you online!

The Historical Networks – Réseaux Historiques – Historische Netzwerke 2021
Laurent Beauguitte (CNRS | Paris)
Aline Deicke (Academy of Sciences and Literature | Mainz)
Marten Düring (University of Luxembourg)
Antonio Fiscarelli (University of Luxembourg)
Claire Lemercier (CNRS | Paris)
Ingeborg van Vugt (University of Utrecht)

Unsubscribe at:
List posts to:
List info and archives at at:
Listmember interface at:
Subscribe at: