PROGRAMME
The International Conference on Agglutinative Language Technologies as a challenge of Natural Language Processing (ALTNLP) has established itself as a multidisciplinary conference in natural language processing and machine learning along with, Computational Optimization. ALTNLP provides an international online forum for the presentation of original multidisciplinary research results as well as a platform for the exchange and dissemination of innovative and practical development.
ALTNLP aims to explore and discuss modern issues and approaches of natural language processing and machine learning to agglutinative languages and other weakly formalized languages. ALTNLP’s main objective is to provide an opportunity for leading academic scientists, researchers, engineers, scholars and other professionals from all over the world to contribute to the development of these fields and exchange new ideas as well as research outcomes in related fields, in turn, establishing lasting partnerships for future collaboration.
We invite original work and contributions from both the NLP and ML domain. Topics of interest include, but are not limited to:
Natural Language Processing
● Specific standards, guidelines, tagsets, and terminology in NLP for morphologically-rich languages
● Resources, evaluation and other NLP Applications for agglutinative and other morphologically-rich Languages
● Text mining (classification, tagging, and parsing), information extraction and retrieval for agglutinative and other languages
● Machine learning and machine translation with a focus on agglutinative and morphologically rich languages
● Morphologically-rich corpora development for languages such as Turkic languages and more
● Methods and software to aid labour intensive tasks in the development of morphologically-aware resources and tools for NLP and ML tasks for Turkic and other languages
SCHEDULE
CEST-UTC+2h
June, 7
Session 1 (Jernej Vičič, University of Primorska, FAMNIT, Slovenia; Branko Kavšek, University of Primorska, FAMNIT, Slovenia)
9:00 AM Opening remarks and ALTNLP conference
9:15 AM Opening ceremony speech: Eneko Agirre, Director of the Hitz Center from the University of the Basque Country (Full Professor and a Doctor in Computer Science)
9:30 AM Opening ceremony speech: Prof. Štefko Miklavič, PhD, Vice Rector for Research and Development, University of Primorska, Koper, Slovenia
10:00 AM Invited speech: Eckhard Bick, University of Southern Denmark, Denmark: A Modular Machine Translation Pipeline for Greenlandic
11:00 AM Salih Furkan Akkurt, Büşra Marşan and Susan Uskudarli: BoAT v2 – A Web-Based Dependency Annotation Tool with Focus on Agglutinative Languages
11:30 AM Ulugbek Salaev, Elmurod Kuriyozov and Carlos Gómez-Rodríguez: A machine transliteration tool between Uzbek alphabets
12:00 PM Maksud Sharipov and Ogabek Sobirov: Development of a rule-based lemmatization algorithm through Finite State Machine for Uzbek language
12:30 PM Sabrina Tiun, Siti Noor Allia Noor Ariffin and Yee Dhong Chew: Pos Tagging Model for Malay Tweet Using New Pos Tagset And BiLTSM-CRF Approach
BREAK
Session 2 (Branko Kavšek, University of Primorska, FAMNIT, Slovenia; Jernej Vičič, University of Primorska, FAMNIT, Slovenia)
1:30 PM Deniz Zeyrek and Mustafa Erolcan Er: A description of Turkish Discourse Bank 1.2 and an examination of common dependencies in Turkish discourse
2:00 PM Sead Jahić and Jernej Vičič: Annotated lexicon for sentiment analysis in Bosnian language
2:30 PM Maksud Sharipov and Ollabergan Yuldashov UzbekStemmer: Development of a Rule Based Stemming Algorithm for Uzbek Language
3:00 PM Yiğit Bekir Kaya and A. Cüneyd Tantuğ: Finding the Optimal Vocabulary Size for Turkish Named Entity Recognition
3:30 PM Khabibulla Madatov, Shukurla Bekchanov and Jernej Vičič: Accuracy of the Uzbek stop words detection: a case study on “School corpus”
4:00 PM Karahan Şahin and Ümit Atlamaz: TransMorpher: A Phonologically Informed Transformer-based Morphological Analyzer
4:30 PM Invited speech: Katharina Kann: NLP for Indigenous Languages of the Americas: Transfer Learning Meets Translation
5:00 PM Closing Remarks
June, 8
Session 3 (Elmurod Kuriyzov, University of a Coruna, Spain; Jamolbek Mattiev, Urgench State University, Uzbekistan)
11:00 AM Opening ceremony speech: Zafar Ibragimov, Vice rector, Urgench State University
11:30 AM Invited speech: Mans Hulden, University of Arizona, USA
12:00 PM Büşra Marşan, Salih Furkan Akkurt, Muhammet Şen, Merve Gürbüz, Şaziye Betül Özateş, Suzan Üsküdarlı, Arzucan Özgür, Tunga Güngör and Balkız Öztürk: Enhancements to the BOUN Treebank Reflecting the Agglutinative Nature of Turkish
12:30 PM Sanatbek Matlatipov, Hulkar Rahimboeva, Jaloliddin Rajabov and Elmurod Kuriyozov: Uzbek Sentiment Analysis based on local Restaurant Reviews
1:00 PM Arup Das, Bibekananda Kundu, Lokasis Ghorai, Arjun Kumar Gupta and Sutanu Chakraborti Anwesha: A Tool for Semantic Search in Bangla
1:30 PM Kausthub Thekke Madathil, Neeraj Mirji, Charan R and Anand Kumar M: Fake News Detection for Hindi Language
2:00 PM Jamolbek Mattiev, Maksud Sharipov, Jasur Sobirov and Rustam Baltayev: Creating a morphological and syntactic tagged corpus for the Uzbek language
Break
Session 4 (Jernej Vičič, University of Primorska, FAMNIT, Slovenia; John E. Ortega, New York University, New York, USA)
3:00 PM Valeria Generalova and Simon Petitjean: A metagrammar of causatives in morphologically rich languages
3:30 PM Chih-Chen Chen and William Chen Benchmarking Azerbaijani: Neural Machine Translation
4:00 PM Mücahit Altıntaş and A. Cüneyd Tantuğ: Boosting Dependency Parsing Performance by Incorporating Additional Features for Agglutinative Languages
4:30 PM Closing of the Conference