SIGUL March 2020

sigul@list.elra.info

3 participants
3 discussions

[2003.07082] Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
by Laurent Besacier 17 Mar '20

17 Mar '20

hi i thought some of you might be interested by this online paper best laurent ==== > > https://arxiv.org/abs/2003.07082 <https://arxiv.org/abs/2003.07082> > > Stanza: A Python Natural Language Processing Toolkit for Many Human Languages > > (Submitted on 16 Mar 2020) > We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages. Compared to existing widely used toolkits, Stanza features a language-agnostic fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech and morphological feature tagging, dependency parsing, and named entity recognition. We have trained Stanza on a total of 112 datasets, including the Universal Dependencies treebanks and other multilingual corpora, and show that the same neural architecture generalizes well and achieves competitive performance on all languages tested. Additionally, Stanza includes a native Python interface to the widely used Java Stanford CoreNLP software, which further extends its functionalities to cover other tasks such as coreference resolution and relation extraction. Source code, documentation, and pretrained models for 66 languages are available at this https URL <https://stanfordnlp.github.io/stanza>.

1 0

Information about SLTU-CCURL 2020
by Laurent Besacier 17 Mar '20

17 Mar '20

Dear All, As a consequence of the COVID-19 pandemic LREC has been suspended. As a satellite event SLTU-CCURL 2020 is thereby also suspended. We, as workshop organizers, will adhere to the policy and decisions that will be taken by the LREC 2020 organizers. The Workshop Proceedings will be published as planned in early May. Acceptance notifications will be sent out by Wednesday, 18 March. The SLTU/CCURL 2020 Organizers

2 1

Last CfP: 1st Joint SLTU-CCURL Workshop @ LREC2020
by Claudia Soria 02 Mar '20

02 Mar '20

Apologies for cross-postings ============== Last Call for Papers 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop SLTU-CCURL 2020 is endorsed by SIGUL, ELRA and ISCA. Date: 11-12 May 2020 Venue: Palais du Pharo, Marseille, France Website: http://sltu-ccurl-2020.ilc.cnr.it Submission Deadline: 14 February 2020 - no extension will be granted Submission page: https://www.softconf.com/lrec2020/SLTUCCURL2020/ ============== Workshop Description and Objectives The first joint SLTU-CCURL workshop, organized by SIGUL, a joint Special Interest Group of the European Language Resources Association (ELRA) and of the International Speech Communication Association (ISCA), will gather researchers working on speech processing and NLP for less-resourced languages. We solicit papers and posters related to all areas of NLP , speech and computational linguistics, as well as those at the intersection with digital humanities and documentary linguistics, provided that they address less-resourced languages. The intention of this joint SLTU-CCURL workshop is not only to provide a forum for the presentation of research, but also to offer a venue where researchers in different disciplines and from varied backgrounds can fruitfully explore new areas of intellectual and practical development while honoring their common interest of sustaining less-resourced languages. Topics of interest Topics include but are not limited to: -Language resource development, acquisition and representation -Linguistic theories, corpus development and resources -Linguistic and cognitive studies -Unsupervised discovery of linguistic units -Code switched lexical modeling -Multi-lingual and cross-lingual (spoken, text) language processing -Speech-to-text, text-to-speech and speech-to-speech processing -Machine translation and dialogue systems -NLP and speech technologies for under-resourced languages Submission & Publication Papers need to address less-resourced languages. They can contain an analysis and insight into existing methods and problems; a description of resources; an overview of the literature or of current initiatives, or a combination of the above. Authors must declare if part of the paper contains material previously published elsewhere. We accept submission of long papers (up to 8 pages, to be presented as long presentations) and short papers (up to 4 pages, to be presented as posters or demos). The program committee reserves the right to decide whether a paper submitted as a long paper is better suited for a poster presentation. Page limits exclude references. The papers of the workshop will be published in online proceedings. Papers must strictly comply with the LREC stylesheet (https://lrec2020.lrec-conf.org/en/submission2020/authors-kit/) and be submitted in PDF unprotected format. Submission page: https://www.softconf.com/lrec2020/SLTUCCURL2020/ Each submission will be reviewed by three programme committee members. In compliance with the LREC rules, papers must not be anonymized. Important Dates - Paper submission deadline: 14 February 2020 - Notification of acceptance: 13 March 2020 - Camera-ready paper: 2 April 2020 - Workshop date: 11-12 May 2020 Invited speakers Alan Black, Carnegie Mellon University, USA Teresa Lynn, ADAPT Centre, Dublin City University, Ireland Tutorials On May 10th, SLTU-CCURL is pleased to offer two tutorials (held at Université Aix-Marseille, near the LREC venue). T1: Jan Trmal, John Hopkins University: Building ASR systems using the Kaldi toolkit T2: Achim Rabus, University of Freiburg : Introduction to Handwritten Text Recognition with Transkribus More details will be announced on the workshop web page. Attendance to tutorials will be free of charge but registration will be required for organisational purposes (and number of attendees will be limited to 25 per tutorial). Organizing Committee * Dorothee Beermann, NTNU, Norway   * Laurent Besacier, LIG-Univ. Grenoble Alpes, France  * Sakriani Sakti, NAIST, Japan  * Claudia Soria, CNR-ILC, Italy  To contact the organizers, please mail Claudia.soria(a)ilc.cnr.it or Laurent.Besacier(a)univ-grenoble-alpes.fr (Subject: [SLTUCCURL@LREC2020]). Programme Committee Adrian Doyle (University of Galway, Ireland) Alexey Karpov (SPIIRAS, Russian Federation) Alexis Palmer (University of North Texas, USA) Amita Dev (IGDTUW, India) Amir Aharoni (Wikimedia Foundation) Andras Kornai (Hungarian Academy of Sciences, Hungary) Angelo Mario Del Grosso (CNR-ILC, Italy) Antti Arppe (University of Alberta, Canada) Anupam Shukla (IIITM, India) Charl Van Heerden (Saigen, South Africa) Daan Van Esch (Google) Dafydd Gibbon (Bielefeld University, Germany) Delyth Prys (Bangor University, UK) Dewi Bryn Jones (Bangor University, UK) Dorothee Beermann (NTNU, Norway) Emily Le Chen (University of Illinois, USA) Federico Boschetti (CNR-ILC, Italy) Francis Tyers (Moscow Higher School of Economics, Russia) Gerard Bailly (GIPSA Lab, CNRS) Gilles Adda (LIMSI/IMMI CNRS, France) Hemant Patil (DA-IICT, India) Jeff Good (University at Buffalo, USA) John Judge (ADAPT DCU, Ireland) Jonas Fromseier Mortensen (Google) Jordan Lachler (University of Alberta, Canada) Joseph Mariani (LIMSI-CNRS, France) Kepa Sarasola (University of the Basque Country, Spain) Kevin Scannell (Saint Louis University, Missouri, USA) Klara Ceberio (Elhuyar, Spain) Lane Schwartz (University of Illinois at Urbana-Champaign, USA) Laurent Besacier (LIG-IMAG, France) Maite Melero (Barcelona Supercomputing Center, Spain) Miikka Silfverberg (University of Helsinki, Finland) Mikel Forcada (Universitat d’Alacant, Spain) Mohammad A. M. Abushariah (The University of Jordan, Jordan) Nick Thieberger (University of Melbourne / ARC Centre of Excellence for the Dynamics of Language, Australia) Omar Farooq (AMU, India) Pierric Sans (Google) Pradip K Das (IIT, India) Sakriani Sakti (NAIST, Japan) Satoshi Nakamura (NAIST, Japan) Sebastian Stüker (KIT, Germany) Shyam S Agrawal (KIIT, India) Steven Bird (Charles Darwin University, Australia) Tanja Schultz (Uni-Bremen, Germany) Thang Vu (Uni-Stuttgart, Germany) Teresa Lynn (ADAPT Centre, Ireland) Trond Trosterud (Tromsø University, Norway) Tunde Adegbola (African Languages Technology Initiative, Nigeria) Vera Ferreira (CIDLeS - Interdisciplinary Centre for Social and Language Documentation, Portugal) Win Pa Pa (UCS Yangon, Myanmar) Acknowledgments The 1st joint SLTU-CCURL Workshop is endorsed by SIGUL (http://www.elra.info/en/sig/sigul/), ISCA (https://www.isca-speech.org/iscaweb/), and SIGEL and sponsored by Google. Identify, Describe and Share your LRs! Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). To continue the efforts initiated at LREC 2014 about “Sharing LRs” (data, tools, web-services, etc.), authors will have the possibility, when submitting a paper, to upload LRs in a special LREC repository. This effort of sharing LRs, linked to the LRE Map for their description, may become a new “regular” feature for conferences in our field. This will contribute to creating a common repository where everyone can deposit and share data. As scientific work requires accurate citations of referenced work so as to allow the community to understand the whole context and also to allow the replication of the experiments conducted by other researchers, LREC 2020 endorses the need to uniquely Identify LRs through the use of the International Standard Language Resource Number (ISLRN, www.islrn.org), a Persistent Unique Identifier to be assigned to each Language Resource. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time. -- Claudia Soria Researcher Istituto di Linguistica Computazionale "A. Zampolli" Consiglio Nazionale delle Ricerche Via Moruzzi 1 56124 Pisa Italy Tel. +39 050 3153166 Skype clausor

2 1

2024

2023

2022

2021

2020

2019

2018

2017

SIGUL March 2020