Language Technology: Research and Development Workshop

The final workshop will take place on Zoom. Students and staff will get information about the Zoom rooms via email. If anyone else is interested in attending this workshop, please contact Sara Stymne ( for details.

Each student will have 12 minutes for presentation, followed by 3 minutes for questions.
Zoom room 1 Zoom room 2
9.30SaraWelcome and introduction
Embeddings: gender bias and grammar: Ali
9.45ZiyangHave Attention Heads in BERT Learned Phrase Grammar?
10.00MeichunInvestigating Gender Bias Hidden Behind Chinese Adjectives in Word Embeddings
10.15Maria-ElenaReducing gender bias in NMT with debiased word embeddings
Parsing and readability: SaraBERT and sentiment: Daniel
11.00BjarkiCross-lingual dependecy parsing methods for Icelandic past and presentXiGenerating knowledge graph embedding using KG-BERT on the DrugBank with probablistic negative sampling
11.15YifeiImpact of Language Distances and Data Sizes on cross-lingual ParsingPochunMethod Exploration: Relation Extraction Using BERT
11.30Antonia Investigation of Transfer Languages for Parsing Latin: Italic Branch vs. Hellenic BranchGiacomoSteam game reviews sentiment analysis with a CNN Twitter-enriched model
11.45Gustav A New Readability Measure Based on Genre ClassificationXindiA Comparative Study of Neural Network Models for Chinese Movie Reviews: In the Aspect of Data Classification and Segmentation Method
WSD, NE, offensive language: Sara
13.00HuilingEvaluating Contextualized Multilingual Language Models in Word-in-Context Disambiguation
13.15XingranCross-lingual Word Sense Disambiguation using mBERT Embeddings with Syntactic Dependencies
13.30AhmedArabic Named Entity Recognition using contextualized word embeddings
13.45SebastianPreprocessing and the Detection of Offensive Language in German Tweets: an Exploration How Different Methods Interact with Different Classifiers
Cross-lingual sentiment and tagging: Daniel
14.30SijiaWhat Multilingual BERT Learns from Back-Translation for Sentiment Classification Tasks
14.45NaomiYou Can Take Your Complaint to a Different Language: Sentiment Analysis Using Cross-Lingual Data and Convolutional Neural Networks in a Low Resource Situation
15.00MelvinSentimix Dataswitch: Comparing Diferente Spanglish Data Sets on Models
15.15HarmWhit's the Richt Pair o Speech: PoS tagging for Scots
15.30SaraWrapping up