8th Symposium on Corpus Approaches to Lexicogrammar (LxGr2022)
The symposium will take place online on 6-8 July 2023.
The programme and registration details are here: https://sites.edgehill.ac.uk/lxgr/lxgr2023
For more information, contact lxgr(a)edgehill.ac.uk<mailto:lxgr@edgehill.ac.uk>.
________________________________
Edge Hill University<http://ehu.ac.uk/home/emailfooter>
Modern University of the Year, The Times and Sunday Times Good University Guide 2022<http://ehu.ac.uk/tef/emailfooter>
University of the Year, Educate North 2021/21
________________________________
This message is private and confidential. If you have received this message in error, please notify the sender and remove it from your system. Any views or opinions presented are solely those of the author and do not necessarily represent those of Edge Hill or associated companies. Edge Hill University may monitor email traffic data and also the content of email for the purposes of security and business communications during staff absence.<http://ehu.ac.uk/itspolicies/emailfooter>
Dear colleagues,
We are happy to invite you to join the *Arabic NER SharedTask 2023*
<https://dlnlp.ai/st/wojood/> which will be organized as part of the WANLP
2023. We will provide you with a large corpus and Google Colab notebooks to
help you reproduce the baseline results.
دعوة للمشاركة في مسابقة استخراج الكيونات المسماه من النصوص العربية. سنزود
المشاركين بمدونة وبرمجيات للحصول على نتائج مرجعية يمكنهم البناء عليها.
*INTRODUCTION*
Named Entity Recognition (NER) is integral to many NLP applications. It is
the task of identifying named entity mentions in unstructured text and
classifying them to predefined classes such as person, organization,
location, or date. Due to the scarcity of Arabic resources, most of the
research on Arabic NER focuses on flat entities and addresses a limited
number of entity types (person, organization, and location). The goal of
this shared task is to alleviate this bottleneck by providing Wojood, a
large and rich Arabic NER corpus. Wojood consists of about 550K tokens (MSA
and dialect, in multiple domains) that are manually annotated with 21
entity types.
*REGISTRATION*
Participants need to register via this form (
*https://forms.gle/UCCrVNZ2LaPviCZS6* <https://forms.gle/UCCrVNZ2LaPviCZS6>).
Participating teams will be provided with common training development
datasets. No external manually labelled datasets are allowed. Blind test
data set will be used to evaluate the output of the participating teams.
Each team is allowed a maximum of 3 submissions. All teams are required to
report on the development and test sets (after results are announced) in
their write-ups.
*FAQ*
For any questions related to this task, please check our *Frequently Asked
Questions*
<https://docs.google.com/document/d/1XE2n89mFLic2P9DO_sAD51vy734BOt0kgtZ6bFf…>
*IMPORTANT DATES*
- March 03, 2023: Registration available
- May 25, 2023: Data-sharing and evaluation on development set Avaliable
- June 10, 2023: Registration deadline
- July 20, 2023: Test set made available
- July 30, 2023: Evaluation on test set (TEST) deadline
- Augest 29, 2023: Shared task system paper submissions due
- October 12, 2023: Notification of acceptance
- October 30, 2023: Camera-ready version
- TBA: WANLP 2023 Conference.
** All deadlines are 11:59 PM UTC-12:00 (Anywhere On Earth).*
*CONTACT*
For any questions related to this task, please contact the organizers
directly using the following email address: *NERShare...(a)gmail.com
<https://groups.google.com/>* or join the google group:
*https://groups.google.com/g/ner_sharedtask2023*
<https://groups.google.com/g/ner_sharedtask2023>.
*SHARED TASK*
As described, this shared task targets both flat and nested Arabic NER. The
subtasks are:
*Subtask 1:* *Flat NER*
In this subtask, we provide the Wojood-Flat train (70%) and development
(10%) datasets. The final evaluation will be on the test set (20%). The
flat NER dataset is the same as the nested NER dataset in terms of
train/test/dev split and each split contains the same content. The only
difference in the flat NER is each token is assigned one tag, which is the
first high-level tag assigned to each token in the nested NER dataset.
*Subtask 2:* *Nestd NER*
In this subtask, we provide the Wojood-Nested train (70%) and development
(10%) datasets. The final evaluation will be on the test set (20%).
*METRICS*
The evaluation metrics will include precision, recall, F1-score. However,
our official metric will be the micro F1-score.
The evaluation of shared tasks will be hosted through CODALAB. Teams will
be provided with a CODALAB link for each shared task.
-*CODALAB link for NER Shared Task Subtask 1 (Flat NER)*
<https://codalab.lisn.upsaclay.fr/competitions/11594>
-*CODALAB link for NER Shared Task Subtask 2 (Nestd NER)*
<https://dlnlp.ai/st/wojood/>
*BASELINES*
Two baseline models trained on Wojood (flat and nested) are provided:
*Nested NER baseline:* is presented in this *article*
<https://aclanthology.org/2022.lrec-1.387/>, and code is available in
*GitHub* <https://github.com/SinaLab/ArabicNER>. The model achieves a micro
F1-score of 0.9059 (note that this baseline does not handle nested entities
of the same type).
*Flat NER baseline:* same code repository for nested NER (*GitHub*
<https://github.com/SinaLab/ArabicNER>) can also be used to train flat NER
task. Our flat NER baseline achieved a micro F1-score of 0.8785.
*GOOGLE COLAB NOTEBOOKS*
To allow you to experiment with the baseline, we authored four Google Colab
notebooks that demonstrate how to train and evaluate our baseline models.
[1] *Train Flat NER*
<https://gist.github.com/mohammedkhalilia/72c3261734d7715094089bdf4de74b4a>:
This notebook can be used to train our ArabicNER model on the flat NER task
using the sample Wojood data found in our repository.
[2] *Evaluate Flat NER*
<https://gist.github.com/mohammedkhalilia/c807eb1ccb15416b187c32a362001665>:
this notebook will use the trained model saved from the notebook above to
perform evaluation on unseen dataset.
[3] *Train Nested NER*
<https://gist.github.com/mohammedkhalilia/a4d83d4e43682d1efcdf299d41beb3da>:
This notebook can be used to train our ArabicNER model on the nested NER
task using the sample Wojood data found in our repository.
[4] *Evaluate Nested NER*
<https://gist.github.com/mohammedkhalilia/9134510aa2684464f57de7934c97138b>:
this notebook will use the trained model saved from the notebook above to
perform evaluation on unseen dataset.
*ORGANIZERS*
- Mustafa Jarrar, Birzeit University
- Muhammad Abdul-Mageed, University of British Columbia & MBZUAI
- Mohammed Khalilia, Birzeit University
- Bashar Talafha, University of British Columbia
- AbdelRahim Elmadany, University of British Columbia
- Nagham Hamad, Birzeit University
- Alaa Omer, Birzeit University
*The 5th Financial Narrative Processing Workshop (FNP 2023)*
To be held at the 2023 IEEE International Conference on Big Data (IEEE
BigData 2023), Sorrento, Italy, from 15 to 18 December 2023.
FNP 2023: http://wp.lancs.ac.uk/cfie/fnp2023/
*Submission page:*
https://wi-lab.com/cyberchair/2023/bigdata23/scripts/submit.php?subarea=S14…
*Important Dates:*
1st Call for workshop papers: June 1, 2023
2nd Call for workshop papers: August 15, 2023
Final Call for workshop papers: October 1, 2023
Due date for workshop papers submission: October 30, 2023 (anywhere in the
world)
Notification of paper acceptance to authors: November 12, 2023
Camera-ready of accepted papers: November 20, 2023
Workshop date: 1 day event: December 15-18, 2023 (exact date to be
announced)
Other dates for shared tasks will be advertised separately
*Workshop Description:*Financial narrative processing is an emerging field
that combines natural language processing (NLP) and machine learning (ML)
techniques to extract, summarise, and analyse both qualitative and
quantitative financial data.
As the amount of financial data continues to grow exponentially, this data
is increasingly considered as big data, which presents challenges and
opportunities for data scientists.
The 5th Financial Narrative Processing Workshop (FNP 2023) aims to bring
together researchers and industry practitioners to share their latest
research results and practical experiences in financial narrative
processing, which is a key aspect of big data.
In particular, the workshop will focus on three shared tasks: Financial
Narrative Summarization, Financial Table of Content Extraction, and
Financial Causality Detection.
These tasks will challenge participants to apply state-of-the-art
techniques in NLP and ML to extract meaningful insights from financial
documents.
The workshop will provide an informal and vibrant forum for discussion and
collaboration, with the goal of advancing the field of financial narrative
processing within the context of big data.
We welcome submissions from researchers and practitioners in academia and
industry.
FNP 2023 workshop is organised by a team of experts who have been at the
forefront of financial NLP research for the past five years.
We have organised more than 7 international events, introduced NLP and AI
shared tasks, and provided big datasets and methodologies needed to push
forward the emerging field of financial NLP.
Our workshop series has contributed significantly to the field of financial
NLP, as evidenced by our proceedings on ACL anthology and citations in
Google Scholar.
*Previous Proceedings:*All FNP proceedings across the years are on ACL
Anthology: https://aclanthology.org/venues/fnp/.
The 1st FNP was associated with LREC 2018
http://lrec-conf.org/workshops/lrec2018/W27/pdf/book_of_proceedings.pdf
FNP Google Scholar:
https://scholar.google.com/citations?hl=en&user=8Qn7yJ8AAAAJ
*Motivation:*Financial narrative disclosures represent a significant
portion of firms’ overall financial communications with investors.
Textual commentaries help to clarify issues that may be obscured by complex
accounting methods and footnote disclosures.
In addition, narratives summarise corporate strategy, contextualise
results, explain governance arrangements, describe corporate social
responsibility policy, and provide forward-looking information for
investors.
However, financial narratives may also provide management with an
opportunity to obfuscate accounting results and manipulate readers’
perceptions of underlying economic performance.
In a previous FNP workshop, we organised a panel of experts to discuss the
future of Financial NLP and data leaders from AI firms in France and London.
The consensus was that financial data has increased exponentially in recent
years due to the increase in regulations.
This has led to an increase in the number of financial news surrounding the
events of releasing such disclosures.
Therefore, state-of-the-art methodologies are necessary to understand and
analyse huge and sensitive financial data in a short amount of time.
We believe that the FNP 2023 workshop will continue to contribute to the
field of Financial NLP by providing a platform for researchers and industry
practitioners to share their research results and practical development
experiences in Big Data research, development, and practice.
In addition, our workshop will help participants gain a better
understanding of the challenges posed by big data and its 5 V’s (velocity,
volume, value, variety, and veracity) in financial text analysis.
*Topics of Interest in relation to Financial NLP:*We encourage research on
topics related to analysing financial narratives using state-of-the-art NLP
techniques, including but not limited to morphological analysis,
disambiguation, tokenization,
part-of-speech tagging, named entity recognition, chunking, parsing,
semantic role labelling, sentiment analysis, document quality, and advanced
readability metrics.
The use of NLP and machine learning in the financial domain has encouraged
studies around gender and ethnicities imbalance, as well as mental health
and well-being research.
Given the focus of the IEEE Big Data 2023 conference, we also encourage
research on under-resourced languages and under-represented financial
markets.
In recent years, FNP has included research on Arabic, Spanish, and
Portuguese financial markets.
Our collaboration with the MultiLing workshop (
http://multiling.iit.demokritos.gr) has highlighted the importance of
summarization across domains and sources that are related to finance (e.g.,
company blogs, product reviews, market briefs, etc.).
This includes financial multilingual and cross-lingual summarization using
single-document summarization, multi-document summarization, summarization
evaluation, headline generation, and cross-domain/cross-topic summarization.
Given the international nature of the event, we particularly welcome FNP
papers reporting non-English and multilingual research, describing the
different regulatory regimes within which companies operate internationally.
*The FNP2023 shared tasks* will be announced separately and are expected to
be:
Financial Narrative Summarisation (FNS 2023)
Financial Table of Content Extraction (FinTOC 2023)
Financial Causality Detection (FinCausal 2023)
For the latest details about the shared tasks please visit:
http://wp.lancs.ac.uk/cfie/shared-tasks/
*Call For Papers for the Main Workshop:*
We invite papers describing original, completed or ongoing, unpublished
research in Financial Natural Language Processing and Financial Text
Analysis.
As financial data is increasingly considered as big data, we encourage
submissions that address the five main and innate characteristics of big
data (velocity, volume, value, variety, and veracity) in the context of
financial narrative processing.
We encourage submissions on topics that include, but are not limited to,
the following:
- Applying core technologies on financial narratives within the context
of big data: morphological analysis, disambiguation, tokenization,
part-of-speech tagging, named entity recognition, chunking, parsing,
semantic role labelling, sentiment analysis, document quality and advanced
readability metrics, etc.
- Using NLP to detect misreporting in relation to diversity and
wellbeing on issues related to gender, ethnicity, women at work as well as
employee mental health and stability, in the context of big data.
- Financial narrative resources and tools for managing and analysing
large-scale financial data.
- Summarization techniques across domains and sources that are related
to finance (e.g. company blogs, product reviews, market briefs, etc.), this
includes financial multilingual and cross-lingual summarization using
single-document summarization, multi-document summarization, summarization
evaluation, headline generation, cross-domain/cross-topic summarization.
- Analysis of Online Social Networks for detection of public opinions
towards financial events.
- Multilingual analysis, describing the different regulatory regimes
within which companies operate internationally.
- Ongoing research and preliminary results that explore the intersection
of financial narrative processing and big data.
- Negative results, for example techniques and methodologies that work
for certain languages but not on others. Other venues could be showing that
state-of-the-art technologies such as BERT could fail on certain tasks or
languages.
All papers accepted will be included in the conference proceedings
published by the IEEE Computer Society Press. We follow IEEE submission
format.
Please submit a full paper (up to 10 page IEEE 2-column format) or short
paper (up to 4 page IEEE 2-column format) through the online submission
system.
*Organising Committee:*
Dr Mo El-Haj, Lancaster University, UK (General Chair)
Dr Houda Bouamor, CMU, Qatar (FNP Program Chair)
Prof Paul Rayson, Lancaster University, UK (FNP Program Chair)
Blanca Carbajo Coronado, UAM, Madrid, Spain (FNP coordinator, Publication
Chair)
Nikiforos Pittaras, NCSR Demokritos (Publicity Chair)
Dr George Giannakopoulos, NCSR Demokritos (FNS Shared Task Organiser)
Dr Marina Litvak, Shamoon Academic College of Engineering (FNS Shared Task
Organiser)
Prof Antonio Moreno Sandoval, UAM, Madrid, Spain (FinCausal Shared Task
Organizer)
Dr Doaa Samy, UAM, Madrid, Spain (FinCausal Shared Task Organizer)
Dr Juyeon KANG, Fortia Financial Solution (FinTOC Shared Task Organiser)
Dr Ismail El Maarouf, Imprevicible (FinTOC Shared Task Organiser)
--
Best regards,
Marina Litvak
2nd Call for Papers
The 1st Workshop on Counter Speech for Online Abuse:
A workshop for creating, investigating and improving tools for producing and evaluating counter speech.
Hate speech and abusive and toxic language are prevalent in online spaces. For example, a 2019 survey shows that in the UK 30-40% of people have experienced online abuse, and platforms like Facebook bring down millions of harmful posts every year, with the help of AI tools. While removal of such content can immediately reduce the quantity of harmful messages, it can bring about accusations of censorship and may not be effective at curbing hate in the long term. An alternative approach is to reply with counter speech, i.e. targeted responses aimed at refuting the hateful language using thoughtful and cogent reasons, and fact-bound arguments. This has been shown to be effective in influencing the behaviour of both the perpetrators of abuse and bystanders that witness the interactions, as well as providing support to victims.
The sheer amount of social media data shared online on a daily basis means that hate mitigation, using counter speech, requires reliable, efficient and scalable tools. Recently, efforts have been made to curate hate countering datasets and automate the production of counter speech. However, this research field is still in its infancy, and many questions remain open regarding the most effective approaches and methods to take, as well as how to evaluate them.
This first multidisciplinary workshop aims to bring together researchers from diverse backgrounds such as computer science and the social sciences, as well as policy makers and other stakeholders to attempt to understand how counter speech is currently used to tackle abuse by individuals, activists and organisations, how Natural Language Processing (NLP) and Generation (NLG) can be applied to produce counter narratives, and the implications of using large language models for this task. It will also address, but not be limited to, the questions of how to evaluate and measure the impacts of counter speech, the importance of expert knowledge from civil society in the development of counter speech datasets and taxonomies, and how to ensure fairness and mitigate the biases present in language models when generating counter speech.
Topics
We invite papers (long and short) on a wide range of topics, including but not limited to:
• Models and methods for generating counter speech;
• Dialogue agents employing counter speech to address hateful inputs, directed towards other people or the AI itself;
• Human and automatic evaluation methods of counter speech tools;
• Multidisciplinary studies including different perspectives on the topic such as from computer science, social science, NGOs and stakeholders;
• Development of datasets and taxonomy for counter speech;
• Potentials and limitations (e.g., fairness, biases) of using large language models for generating counter speech;
• Social impact and empirical studies of counter speech on social media, including investigating the effectiveness and consequences on users of employing counter speech to fight online hate;
• Proposals for future research on counter speech, and/or preliminary results of studies in this field
We accept three types of submissions:
* Regular research papers – long (8 pages) or short (4 pages);
* Non-archival submissions: like research papers, but will not be included in the proceedings;
* Research communications: 2-4 page abstracts summarising relevant research published elsewhere.
Submission link: https://softconf.com/n/cs4oa2023
Location: co-located with SIGdialxINLG, Prague, Czechia
Important dates
All deadlines are Anywhere on Earth (UTC-12)
* Submission deadline: Jun 26, 2023
* Notification of acceptance Jul 17, 2023
* Camera-ready deadline Aug 11, 2023
* Workshop date: September 11/12 2023
Format and Styling
Submissions should follow ACL Author Guidelines<https://www.aclweb.org/adminwiki/index.php?title=ACL_Author_Guidelines> and policies for submission, review and citation, and be anonymised for double blind reviewing. Please use ACL 2023 style files; LaTeX style files and Microsoft Word templates are available at https://2023.aclweb.org/calls/style_and_formatting/<https://2021.aclweb.org/downloads/acl-ijcnlp2021-templates.zip>.
Organising Committee:
* Yi-Ling Chung, The Alan Turing Institute
* Gavin Abercrombie, Heriot-Watt University
* Helena Bonaldi, Fondazione Bruno Kessler
* Marco Guerini, Fondazione Bruno Kessler
Contact
If you have any questions, please let us know at cs4oa(a)googlegroups.com
Website: https://sites.google.com/view/cs4oa
Twitter: @cs4oa_workshop<https://twitter.com/cs4oa_workshop>
________________________________
Founded in 1821, Heriot-Watt is a leader in ideas and solutions. With campuses and students across the entire globe we span the world, delivering innovation and educational excellence in business, engineering, design and the physical, social and life sciences. This email is generated from the Heriot-Watt University Group, which includes:
1. Heriot-Watt University, a Scottish charity registered under number SC000278
2. Heriot- Watt Services Limited (Oriam), Scotland's national performance centre for sport. Heriot-Watt Services Limited is a private limited company registered is Scotland with registered number SC271030 and registered office at Research & Enterprise Services Heriot-Watt University, Riccarton, Edinburgh, EH14 4AS.
The contents (including any attachments) are confidential. If you are not the intended recipient of this e-mail, any disclosure, copying, distribution or use of its contents is strictly prohibited, and you should please notify the sender immediately and then delete it (including any attachments) from your system.
Dear Sir/Ma'am,
I hope you are doing well and in good health. We are excited to announce a
call for a book chapter for an upcoming book titled "*Empowering
Low-Resource Languages With NLP Solutions.*"
Link: https://www.igi-global.com/publish/call-for-papers/call-details/6596
The objective of this book is to provide an in-depth understanding of
Natural Language Processing (NLP) techniques and applications specifically
tailored for low-resource languages. We believe that your valuable insights
and research in this domain would greatly enrich the content of this book.
To ensure a comprehensive and high-quality book, all submitted chapters
will undergo a rigorous peer-review process. The accepted book will be *indexed
in Scopus and Web of Science*, thereby enhancing the visibility and impact
of your work.
The book aims to cover a wide range of topics related to NLP in
low-resource languages. Some of the suggested topics, although not limited
to, include:
· Introduction to Low-Resource Languages in NLP
· Language Resource Acquisition for Low-Resource Languages
· Morphological Analysis and Morpho-Syntactic Processing
· Named Entity Recognition and Entity Linking for Low-Resource
Languages
· Part-of-Speech Tagging and Syntactic Parsing
· Machine Translation for Low-Resource Languages
· Sentiment Analysis and Opinion Mining for Low-Resource Languages
· Speech and Audio Processing for Low-Resource Languages
· Text Summarization and Information Retrieval for Low-Resource
Languages
· Multimodal NLP for Low-Resource Languages
· Code-switching and Language Identification for Low-Resource
Languages
· Evaluation and Benchmarking for NLP in Low-Resource Languages
· Applications of NLP in Low-Resource Language Settings
· Future Directions and Challenges in NLP
We encourage you to contribute a book chapter focusing on any of the
above-mentioned topics or related areas within the scope of NLP in
low-resource languages. The submission guidelines are as follows:
1. Please submit a chapter proposal (maximum 500 words) outlining the
objective, methodology, and expected outcomes of your proposed chapter by
July 3, 2023, to the submission portal:
https://www.igi-global.com/publish/call-for-papers/call-details/6596
2. Chapter proposals should include the title of the chapter,
author(s) name and their affiliations.
3. All submissions should be original and should not have been
previously published or currently under review elsewhere.
4. The chapters should be written in English and adhere to the
formatting guidelines provided after the acceptance of the proposal.
*Important Dates:*
July 3, 2023: Proposal Submission Deadline
July 17, 2023: Notification of Acceptance
September 17, 2023: Full Chapter Submission
October 31, 2023: Review Results Returned
December 12, 2023: Final Acceptance Notification
December 26, 2023: Final Chapter Submission
Thank you for considering this invitation, and we look forward to receiving
your valuable contribution to this book. If you have any further questions
or require additional information, please do not hesitate to contact us.
Best regards,
Editorial Team
Dr. Partha Pakray
National Institute of Technology Silchar
Email: partha(a)cse.nits.ac.in
Dr. Pankaj Dadure
University of Petroleum and Energy Studies Dehradun
Email: pankajk.dadure(a)ddn.upes.ac.in
Prof. Sivaji Bandyopadhyay
Jadavpur University, Kolkata
Email: sivaji.cse.ju(a)gmail.com
-----------------Apologies for cross-posting-------------------
Second Call for Papers
RANLP 2023 Student Research Workshop
4-6 September 2023
Varna, Bulgaria
https://sites.google.com/view/ranlp-stud-2023/
The International Conference RANLP 2023 (http://ranlp.org/) would like
to invite students at all levels (undergraduate, Master-, and
PhD-students) to present their ongoing or completed work at the Student
Research Workshop (https://sites.google.com/view/ranlp-stud-2023/).
SUBMISSIONS
We invite two types of student submissions:
Full Papers must describe original unpublished work of the student in
any topic area of the workshop. Full papers are limited to 8 pages for
content, with 2 additional pages for references.
Short Papers may describe either work in progress or a research
proposal. They may also be in the style of a position paper that surveys
and criticizes existing literature. Short papers must include clear
directions for future research. Submissions of this type are limited to
6 pages for content, with 2 additional pages for references.
All papers must be submitted in .pdf format through the START system
(https://softconf.com/ranlp23/ranlp20t23stud/) . The papers should
follow the format of the main conference, described at the RANLP website
(http://ranlp.org/), Submissions page.
All papers must have only student authors. Submissions with non-student
authors will not be considered for review. After eventual acceptance of
the paper, the authors could add their supervisor(s) in the
Acknowledgments Section. The submissions must specify the student’s
level (Bachelor-, Master-, or PhD) and the type of submission (Full or
Short).
Double submission Authors may submit the same paper at several
conferences. In this case, they must notify the organizers by filling in
the corresponding information in the submission form, as well as
notifying the contact organizer by email.
TOPICS OF INTEREST
The aim of this workshop is to facilitate the exchange of knowledge
between young researchers by providing an excellent opportunity to
present and discuss their work and to receive mentorship and valuable
feedback from an international research community. The research to be
presented can come from any topic within Natural Language Processing
(NLP) and Computational Linguistics, including but not limited to the
following:
Computational Social Science and Social Media;
Computer-aided Language Learning;
Dialogue and Interactive Systems;
Discourse and Pragmatics;
Ethics and NLP;
Information Extraction;
Information Retrieval and Text Mining;
Intent Recognition and Detection;
Interpretability and Analysis of Models for NLP;
Language and Vision;
Language Generation;
Language Resources and Corpora;
Linguistic Theories;
Machine Translation and Computer-aided Translation Tools;
Multilingual NLP;
Multimodal Systems;
NLP Applications – Biomedical, Educational, Healthcare, Financial,
Legal, Semantic Web, etc.;
Opinion Mining and Sentiment Analysis;
Phonetics, Phonology, and Morphology;
Question Answering;
Semantics;
Stylistic Analysis;
Sublanguages and Controlled languages;
Syntax: Tagging, Chunking, and Parsing;
Temporal Processing;
Text Categorization;
Text Simplification and Readability Estimation;
Text Summarisation;
Text-to-Speech Synthesis and Speech Recognition;
Textual Entailment.
All accepted papers will be presented at the Student Workshop sessions
(oral or poster) during the main conference days: 4-6 September 2023.
The articles will be issued in a special Student Session proceedings and
uploaded to the ACL Anthology.
IMPORTANT DATES
Submission deadline: 3 July 2023
Acceptance notification: 4 August 2023
Camera-ready deadline: 20 August 2023
Workshop: 4 - 6 September 2023
All deadlines are 11:59PM UTC-12:00 ("anywhere on Earth")
ORGANISERS
Momchil Hardalov (AWS AI Labs, Spain)
Zara Kancheva (Institute of Information and Communication Technologies,
Bulgarian Academy of Sciences, Bulgaria)
Boris Velichkov (Faculty of Mathematics and Informatics at Sofia
University “St. Kliment Ohridski”, Bulgaria)
Ivelina Nikolova-Koleva (Institute of Information and Communication
Technologies, Bulgarian Academy of Sciences, and Sirma AI, Bulgaria)
Milena Slavcheva (Institute of Information and Communication
Technologies, Bulgarian Academy of Sciences, Bulgaria)
Faculty of Science and Engineering Dean Research PhD Studentship
LASER - Large Language Models for Academic SEarch and Recommendation
Deadline: June 19, 2023
University of Wolverhampton, UK
Applications are invited for doctoral study in Computer Science, Information Retrieval and Natural Language Processing on the topic of Large Language Models for Academic Search and Recommendation.
Project Description
Scientific publications are an important vehicle for understanding the world around us; they contain scientific evidence that informs researchers and decision-makers, with a high impact on society. However, the rapid and large number of publications, in particular on preprint servers, causes an information overload for everybody struggling to keep up with developments in their field. This makes finding relevant information of high quality a challenging task, which requires advanced scholarly search and recommendation solutions. Recent developments in Large Language Models (LLMs) are having a huge impact on Artificial Intelligence (AI) and related fields. LLMs are a type of AI trained on huge amounts of text, with ChatGPT/GPT-4 and Bard as popular examples. LLMs combined with conversational AI provide exciting new possibilities for interactive search and recommendation, but they are also suffering from severe flaws. While there are efforts to combine LLMs with, e.g., neural search, the endeavour of utilising LLMs to tackle information overload in academia has only started and more research is needed.
This PhD studentship will explore how LLMs can be used to improve academic search and recommendation and what their benefits and limitations are. This may include integrating LLMs into search and recommendation services or utilising search to keep LLMs from "hallucinating". A further part of this project is to estimate the quality of publications.
The PhD project provides exciting opportunities for the successful candidate to work with and critically reflect on innovative technologies at the forefront of AI that will shape our digital future. As a further incentive, the PhD candidate will be able to participate in an EU Horizon Europe Staff Exchange project, providing the opportunity to go on fully funded secondments to collaborate with an international network of researchers and industry partners.
For further information regarding the project or an informal discussion please contact Director of Studies, Dr Ingo Frommholz <i.frommholz(a)wlv.ac.uk>.
To apply for one of the above PhD Research Studentship applicants must hold a first class/distinction at Master and/or Bachelor level of study.
Applications to include one identified project, a full CV (including 2 referee names and contact details), transcripts and a letter of application outlining the motivation for applying (maximum of 2 pages). Applicants from outside UK must provide evidence of English Language requirement as stated in https://www.wlv.ac.uk/research/research-degrees/
Application submission deadline is 10:00am BST 19 June 2023 to FSEPGR(a)wlv.ac.uk
A shortlist of candidates will be prepared from the pool of applicants, in line with Faculty of Science and Engineering Post Graduate Research (PGR) studentship selection criteria, who will be invited to attend an interview with a panel of academic staff, week commencing 26 June 2023.
Following this process, all successful candidates will be notified to enrol in July 2023 on a PhD degree programme. The studentship award will include tuition fees at home level for the first three years of full-time study including any write-up period fees and research support fees.
For further information on fees https://www.wlv.ac.uk/apply/funding-costs-fees-and-support/fees-and-costs/r…
Informal enquiries are welcome and should be directed to the individual Director of Studies mentioned above.
Further information: https://www.wlv.ac.uk/schools-and-institutes/faculty-of-science-and-enginee… (look for the LASER project)
--
Ingo Frommholz, PhD, FBCS, FHEA
Reader (~Associate Professor) in Data Science
Deputy Head Digital Innovations and Solutions Centre (DISC)
University of Wolverhampton, UK
Adjunct Professor, Bern University of Applied Sciences, Switzerland
Web: http://www.frommholz.org/ | Email: ifrommholz(a)acm.org
Twitter: @iFromm | Mastodon: @ingo@idf.social
PGP/GPG fingerprint: B74E A422 C7B2 A5BB 2BC2 523B 2790 216E F8F8 D166
http://pgp.mit.edu:11371/pks/lookup?op=get&search=0x2790216EF8F8D166
Dear colleagues,
We invite submissions of papers and talk proposals to
LongEval 2023 Workshop on Longitudinal Evaluation of Model Performance.
https://clef-longeval.github.io/
CLEF 2023 Conference and Labs of the Evaluation Forum<https://clef2023.clef-initiative.eu/index.php>
18-21 September 2023, Thessaloniki - Greece<https://clef2023.clef-initiative.eu/index.php><https://clef2023.clef-initiative.eu/index.php>
Topics of interest include (but not limited to):
• Evaluations of the temporal persistence of information retrieval (IR) systems and text classifiers for various tasks
• Challenges posed by the dynamic nature of language
• Time-aware longitudinal models
• Post-evaluation stage LongEval shared-task submissions.
Deadlines:
Papers: June 5th (to be included in the proceedings)
Submission format: https://drive.google.com/drive/folders/1r2lNOteMNoQrhQGUat6VHPUnwFAgR8Nz
Length: a maximum of 8 pages not including references and appendices).
Submission link: https://easychair.org/my/conference?conf=clef2023
Talk proposals: July 10th (not included in the proceedings)
Submission format: a maximum of 2 pages
Submission link: https://forms.gle/fU46Fb5zJufxF5NV8
Organisers: Alkhalifa, Rabab, Bilal, Iman, Borkakoty, Hsuvas, Camacho-Collados, Jose, Deveaud, Romain, El-Ebshihy, Alaa, Espinosa-Anke, Luis, Gonzalez-Saez, Gabriela, Galusakova, Petra, Goeuriot, Lorraine, Kochkina, Elena, Liakata, Maria, Loureiro, Daniel, Tayyar Madabushi, Harish, Mulhem, Philippe, Piroi, Florina, Popel, Martin, Servan, Christophe, Zubiaga, Arkaitz.
Feel free to reach out with any questions!
Best regards,
Elena Kochkina
On behalf of LongEval organisers
The 1st Workshop on Computational Terminology in NLP and Translation
Studies (ConTeNTs)
Varna, 7th-8th September, 2023
In conjunction with RANLP 2023 - International Conference "Recent
Advances in Natural Language Processing"
Third call for papers
Computational Terminology and new technologies applied to translation
studies have attracted the interest of researchers with very different
multidisciplinary backgrounds and motivations. Those fields cover a
range of areas in Natural Language Processing (NLP) such as information
retrieval, terminology extraction, question-answering systems, ontology
building, machine translation, computer-aided translation, automatic or
semi-automatic abstracting, text generation, etc.
Terminological identification, extraction and coinage of new terms are
essential for knowledge mining from texts, both in high and low
resources languages. Quick evolutions and new developments in
specialised domains require efficient and systematic automatic term
management. New terms need to be coined and translated to ensure the
equitable development of domains in all languages.
During the last decade, deep learning and neural methods have become the
state of the art for most NLP applications. Those applications were
shown to outperform previous methods on various tasks, including
automatic term extraction, language mining, assessment of quality in
machine translation, accessibility of terminology, etc. On the one hand,
NLP and computational linguistics try to improve the work of translators
and interpreters by developing Computer-Assisted Translation (CAT)
tools, Translation Memories (TMs), terminological databases and
terminology extraction tools, etc. On the other hand, the NLP field
still needs the efforts and knowledge of translators, interpreters and
linguists to provide better services and tools based on the real
necessities of those language professionals.
The aim of this workshop is to promote new insights into the ongoing and
forthcoming developments in computational terminology by bringing
together NLP experts, as well as terminologists and translators. By
uniting researchers with such diverse profiles, we hope to bridge some
of the gaps between these disciplines and inspire a dialogue between
various parties, thus paving the way to more artificial intelligence
applications based on mutual collaboration between language and
technology.
Topics of Interest
The ConTeNTs workshop invites the submission of papers reporting on
original and unpublished research on topics related to Computational
Terminology in NLP and Translation Studies, including but not limited
to:
* Automatic term extraction: monolingual and multilingual extraction
of terms from parallel and comparable corpora, including single and
multiword expressions;
* Extraction and acquisition of semantic relations between terms;
* Extraction and generation of domain specific definitions and
disambiguation of terms;
* Representation of terms, management of term variation and the
discovery of synonym terms or term clusters and its relation to NLP
applications;
* Extraction of terminological context, through the use of comparable
and parallel corpus;
* Accessibility of terminology in certain domains, relevant to
non-experts or to laypersons, and its relevance to NLP applications such
as, chatbots, automatic email generation or spoken language interface;
* The impact of terminology on MT (applying terminology constraints,
evaluation of MT in domain-specific settings, etc.);
* The creation of domain ontologies, thesaurus, terminological
resources in specialised domains;
* The use of new technologies in translation studies and research and
the use of terminological resources in specialised translation;
* Identification of key problems in terminology and new technologies
used in translation studies;
* Evaluation of terminological resources in various NLP applications
and the impact of these resources have on the performance of the
automatic systems;
* Emerging language technologies: how the increased reliance on
real-time language technologies would change the structure of language;
* Corpus based studies applied to translation and interpreting: the
use of parallel and comparable corpora for translating phraseological
units;
* Phraseology and multiword expressions in cross-linguistic studies;
* Translation and interpreting tools, such as translation memories,
machine translation and alignment tools;
* User requirements for interpreting and translation tools.
SUBMISSION GUIDELINES
Submissions must consist of full-text papers and should not exceed 7
pages excluding references, they should be a minimum of 5 pages long.
The accepted papers will be published as ConTeNTs workshop e-proceedings
with ISBN, will be assigned a DOI and will be also available at the time
of the conference. The papers should be in English.
Authors of accepted papers will receive guidelines regarding how to
produce camera-ready versions of their papers for inclusion in the
proceedings.
Each submission will be reviewed by at least two programme committee
members. Accepted papers will be presented orally as part of the
programme of the workshop.
Submissions
Link to START system: https://softconf.com/ranlp23/ConTeNTS
Website of the workshop: https://contents2023.kulak.kuleuven.be/
Should you require any assistance with the submission, please do not
hesitate to contact us at amalhaddad(a)ugr.es and
ayla.rigoutsterryn(a)kuleuven.be.
Important Dates
Deadline for paper submission: 10 July 2023
Acceptance notification: 5 August 2023
Final camera-ready version: 25 August 2023
Workshop camera-ready proceedings ready: 31 August 2023
ConTeNTs workshop: 7/8 September 2023
Workshop Chairs & Organising Committee
Ayla Rigouts Terryn, Katholieke Universiteit Leuven, Belgium
Amal Haddad Haddad, Universidad de Granada, Spain
Ruslan Mitkov, University of Wolverhampton, United Kingdom
Programme Committee
* Sophia Ananiadou (University of Manchester)
* Maria Andreeva Todorova (Bulgarian Academy of Sciences)
* Silvia Bernardini (University of Bologna)
* Melania Cabezas García (Universidad de Granada)
* Rute Costa (Universidade Nova de Lisboa)
* Esther Castillo Pérez (Universidad de Granada)
* Patrick Drouin (Université de Montréal)
* Pamela Faber (Universidad de Granada)
* Mercedes García de Quesada (Universidad de Granada)
* Dagmar Gromann (Centre for Translation Studies - University of
Vienna)
* Tran Thi Hong Hanh (L3i Laboratory, University of La Rochelle)
* Rejwanul Haque (National College of Ireland)
* Amir Hazem (Nantes University)
* Kyo Kageura (University of Tokyo)
* Barbara Karsch (BIK Terminology - USA)
* Dorothy Kenny (Dublin City University)
* Miloš Jakubíček (Sketch Engine)
* Hendrik Kockaert (KU Leuven)
* Philipp Koehn (Johns Hopkins University)
* Maria Kunilovskaya (Saarland University)
* Marie-Claude L'Homme (Université de Montréal)
* Hélène Ledouble (Université de Toulon)
* Pilar León-Araúz (Universidad de Granada)
* Rodolfo Maslias (former Head of TermCoord, European Parliament)
* Silvia Montero Martínez (Universidad de Granada)
* Emmanuel Morin (LS2N-TALN)
* Rogelio Nazar (Pontificia Universidad Católica de Valparaíso)
* Sandrine Peraldi (University College Dublin)
* Silvia Piccini (Italian National Research Council)
* Thierry Poibeau (CNRS)
* Senja Pollak (Jožef Stefan Institute)
* Maria Pozzi Pardo (El Colegio de México)
* Tharindu Ranasinghe (Aston University)
* Arianne Reimerink (Universidad de Granada)
* Andres Repar (Jožef Stefan Institute)
* Christophe Roche (Université Savoie Mont-Blanc)
* Antonio San Martín Pizarro (Université du Québec à Trois-Rivières)
* Beatriz Sánchez Cárdenas (Universidad de Granada)
* Vilelmini Sosoni (Ionian University)
* Irena Spasic (Cardiff University)
* Elena Isabelle Tamba (Romanian Academy, Iași Branch)
* Rita Temmerman (Vrije Universiteit Brussel)
* Jorge Vivaldi Palatresi (Universitat Pompeu Fabra)