Language Technology: Research and Development Workshop
The final workshop will mainly take place on Campus. There will be two Zoom sessions (3a and 4a), which will be broadcast in a room, as well as available directly on Zoom. The Zoom link is avaiable in Studium. (If anyone else is interested in attending the Zoom session, please contact Sara Stymne (sara.stymne@lingfil.uu.se) for the link.)
We welcome guests who are not attending the course. However, due to restrictions, we might need to limit access to the class rooms. In that case, priority is of course given to students taking the course.
Note that this schedule is preliminary, and it is subject to change. A few more talks might have to be given on Zoom, which will then affect also other talks, to keep the Zoom talks to specific sessions.
Each student will have 12 minutes for presentation, followed by 3 minutes for questions.
Geijersalen 6-1023 | 7-0043 | |||
9.00 | Sara | Welcome and introduction | ||
Plenary session 1: Sara | ||||
9.05 | Kätriin | Finding the best language model - approach combination: cross-lingual methods for intent detection in Estonian | ||
9.20 | Lingqing | Evaluating Recurrent Neural Network Semantics: Presupposed Taxonomies | ||
9.35 | Martina | Authorship Attribution for Swedish Novels | ||
9.50 | Wenwen | How Spelling Normalization Affects Historical Text Classification | ||
10.05 | Oreen | Multilingual Named Entity Recognition via Data Augmentation | ||
10.20 | BREAK with coffee in Matikum | |||
Session 2a, Zoom talks: Paola | Session 2b: Eva | |||
10.50 | Chuchu | Investigating the Chinese-English Shared Translation Effect on GPT2 | Claire | POS tagging for historical Swedish using KB-BERT |
11.05 | Paloma | Is Chile a country or a pepper? Spanish Pre-Trained BERT semantic understanding of polysemous words | Emma | Lexical Semantic Change Detection for Historical Swedish Using Topic Modelling |
11.20 | Yongchao | A systematic comparison between BERT and ConceptNet Numberbatch on word association properties | Jae Eun | Swedish Grammar Error Correction Using Neural Networks And Data Supplement Methods |
11.35 | Eva | The Age of Context-Aware Language Embeddings: BERTje and mBERT | Flor | Patronizing and Condescending Language (PCL) Detection Across Machine Learning Models Using Frequency Based and Word Embedding Representations |
11.50 | LUNCH BREAK | |||
Session 3a, Zoom talks: https://uu-se.zoom.us/j/65488119762: Eva | Session 3b: https://uu-se.zoom.us/j/63103088868: Sara | |||
13.00 | Chen | Implementation and evaluation cross three methods in Automated Cognate Judgement | Zhe | Comparative analysis of effectiveness of transfer learning and meta learning in automatic Chinese sarcasm detection |
13.15 | Ziming | Temporal Classification Based on Supervised Learning | Angeliki | Towards a POS-Tagger for Griko using Transfer Learning from Greek and Italian |
13.30 | Kai Yan | Improving Extremely Low-Resource Neural Machine Translation via Unsupervised Bitext Mining: A Case Study of Cantonese | James | There Is Something About Czech |
13.45 | SHORT BREAK | |||
Session 4a, Campus+Zoom: https://uu-se.zoom.us/j/65488119762: Eva | Session 4b, Zoom talks: https://uu-se.zoom.us/j/63103088868: Sara | |||
13.55 | Nikolina (Campus) | Machine Learning techniques and Stylometric features on Medieval Greek Text Classification | Yifan | Multilingual Idiomaticity Detection: Transfer Learning with English and German for Portuguese Idiom Detection Task with mBERT |
14.10 | Klaudia (Zoom) | Evaluating Neural Network Semantics: Detecting Taxonomy with Embeddings | Siyi | Using Entity Annotation Projection for Multilingual Complex Named Entity Recognition |
14.25 | Viktorija (Zoom) | The Impact of Morphological Richness on Word Association Norms in Word Embeddings | Kris | Maltese Named Entity Recognition with Cross-Lingual Conditional Random Fields |
14.40 | BREAK with coffee in Matikum | |||
Plenary session 5, Zoom talks: https://uu-se.zoom.us/j/63103088868: Paola | ||||
15.10 | Jiayi | Syntactic Behaviour of Chinese Neural Network Language Models | ||
15.25 | Laura | OCR Quality Evaluation for Natural Language Processing Tasks on Historical Swedish Newspapers | ||
15.40 | Rafal | Using Unaligned Monolingual Data to Build Multilingual and Improve Monolingual Reverse Dictionaries | ||
15.55 | Sara | Wrapping up | ||