Language Technology: Research and Development Workshop

The final workshop will take place in 7-0042 and 7-0043 on January 15, 2020.

Each student will have 12 minutes for presentation, followed by 3 minutes for questions.

7-0042 7-0043

9.15 Sara Welcome and introduction

Authorship and questions: Sara

9.30 Shifei Bilingual Tweets Authorship Attribution

9.45 Giuseppe Universal Dependencies Based Question Generation from Narrative Texts for Foreign Language Teaching and Learning

Authorship: Mats MT/LM/Parsing: Sara

10.15 Luise Authorship Obfuscation Revisited: An Evaluation of Recent Approaches Jun Pivot Translation for Under-Resourced Language pair

10.30 Renfei Author Gender Prediction Using Logistics Regression and Neural Network Artur Do Neural Language Models Capture Surface or Deep Syntax?

10.45 Adam Authorship Attribution for Non-Standard Language Using Character Ngrams Elsa A Multilingual Approach to Dependency Parsing Low Resource Sámi Languages

UD Treebanks: Joakim Sentiment: Sara

11.15 Marsida A Universal Dependencies Treebank for Standard Albanian Evangelia Impact of Age on Product Review Sentiment

11.30 Camilla Detecting Errors in Universal Dependency Treebanks Xiajing Cross Lingual Aspect-Based Sentiment Classification Using Model Transfer

11.45 Rex Quantifying the informativeness of individual part of speech for parsing in the universal dependency tagset Ugo A Comparative Study of Neural Network models for Sentiment Analysis of Code-Mixed Tweets

Text analysis and embeddings: Mats

13.15 Anne Fleur Exploring the use of informal writings as input to classification algorithms identifying dementia

13.30 Drew Classifying Mass Shooter Manifestos with Deep Transfer Learning and Domain Adaptation Methods

13.45 Xuemei Fake News Detection using LSTM

14.00 Hartger An exploration of distance to nearest neighbor as a metric for the quality of cross-lingual word embeddings

14.15 Rizal Evaluating Word Embedding for Indonesian code-mixed (intra-sentential code-switched) sentences in Sentiment Classification Task

Parsing and tagging: Joakim

14.45 Natalia POS-tagging via projection annotation in a truly low-resource scenario: the case of Karelian Proper

15.00 Tiantian Cross-lingual Dependency Parsing with Treebank Translation Quality

15.15 Shorouq Parsing Low-Resource Levantine Arabic: Annotation Projection versus Small-Sized Annotated Data

15.30 Ivan Bridging Linguistic Distance via Transfer Learning: Multi-lingual Dependency Parsing with Belarusian

15.45 Sara Wrapping up

16.00- Social event, department lunch room

	7-0042		7-0043
9.15	Sara	Welcome and introduction
	Authorship and questions: Sara
9.30	Shifei	Bilingual Tweets Authorship Attribution
9.45	Giuseppe	Universal Dependencies Based Question Generation from Narrative Texts for Foreign Language Teaching and Learning
	Authorship: Mats		MT/LM/Parsing: Sara
10.15	Luise	Authorship Obfuscation Revisited: An Evaluation of Recent Approaches	Jun	Pivot Translation for Under-Resourced Language pair
10.30	Renfei	Author Gender Prediction Using Logistics Regression and Neural Network	Artur	Do Neural Language Models Capture Surface or Deep Syntax?
10.45	Adam	Authorship Attribution for Non-Standard Language Using Character Ngrams	Elsa	A Multilingual Approach to Dependency Parsing Low Resource Sámi Languages
	UD Treebanks: Joakim		Sentiment: Sara
11.15	Marsida	A Universal Dependencies Treebank for Standard Albanian	Evangelia	Impact of Age on Product Review Sentiment
11.30	Camilla	Detecting Errors in Universal Dependency Treebanks	Xiajing	Cross Lingual Aspect-Based Sentiment Classification Using Model Transfer
11.45	Rex	Quantifying the informativeness of individual part of speech for parsing in the universal dependency tagset	Ugo	A Comparative Study of Neural Network models for Sentiment Analysis of Code-Mixed Tweets
	Text analysis and embeddings: Mats
13.15	Anne Fleur	Exploring the use of informal writings as input to classification algorithms identifying dementia
13.30	Drew	Classifying Mass Shooter Manifestos with Deep Transfer Learning and Domain Adaptation Methods
13.45	Xuemei	Fake News Detection using LSTM
14.00	Hartger	An exploration of distance to nearest neighbor as a metric for the quality of cross-lingual word embeddings
14.15	Rizal	Evaluating Word Embedding for Indonesian code-mixed (intra-sentential code-switched) sentences in Sentiment Classification Task
	Parsing and tagging: Joakim
14.45	Natalia	POS-tagging via projection annotation in a truly low-resource scenario: the case of Karelian Proper
15.00	Tiantian	Cross-lingual Dependency Parsing with Treebank Translation Quality
15.15	Shorouq	Parsing Low-Resource Levantine Arabic: Annotation Projection versus Small-Sized Annotated Data
15.30	Ivan	Bridging Linguistic Distance via Transfer Learning: Multi-lingual Dependency Parsing with Belarusian
15.45	Sara	Wrapping up
16.00-	Social event, department lunch room