Language Technology: Research and Development Workshop

The final workshop will take place on Campus.

We welcome guests who are not attending the course.

Note that this schedule is preliminary, and it is subject to change.

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

7-0042 7-0043

9.30 Sara Welcome and introduction

Plenary session 1: Sara

9.35 Maya Cross-Lingual and Multilingual Speech Emotion Recognition on English and Chinese leveraging Self-Supervised Learning

9.50 Yaru Chinese NER with speech clues

10.05 Mathias Parsing the Old using the New: A study in parsing Icelandic

10.20 Ebba Top2Vec in the context of Swedish historical texts

10.35 BREAK

Session 2a: Johan Session 2b: Meriem

11.05 Yini Investigating the Impact of Modifying Open Domain Data with Artificial Tokens on Keyphrase Extraction Tasks Moa Af Somaali ma baran kartaa?

11.20 Yahui Pre-trained Abstractive Text Summarization model With Post-processing Hengyu Improving Low-resource NMT with Langauge-specific Tokenizers: A Case Study of Cantonese-Chinese Translation

11.35 Iliana Cross-Lingual POS-Tagging for Ancient Greek: Zero and Few-Shot Transfer Learning with Pre-Trained Models Alex Zero-shot sentiment classification for Nigerian Pidgin Tweets

11.50 LUNCH BREAK

Session 4: Bea

13.15 Jie Building a Multilingual Model for Low-resource Offensive Language Identification

13.30 Zharoui Bi-LSTM-CNN Model Based on GloVe Word Embedding for Multi-Domain Sentiment Classification

13.45 Matilde Language identificación of code-switching data: BiLSTM-CRF and combined code-switching datasets

14.00 Yiu Kei Additional Paraphrase Training Drives Language Models Closer to Human Behaviour on Natural Language Inference

14.15 BREAK

Session 3: Sara

14.45 Thea Cross Attention Fine Tuning vs Full Scale Fine Tuning for Somali NMT

15.00 Aleksandra A comparison of Machine Translation techniques for the very low-resource Faroese language

15.15 Ingrid Collecting and Aligning a Parallel Corpus for Innu-Aimun and French, with a Machine Translation Baseline

15.30 Micaella Bridging the Gap: Facilitating Translations Between Low-Resource Languages using NMT

15.45 Sara Wrapping up

16.00 SOCIAL EVENT -- DEPARTMENT STAFF ROOM

	7-0042		7-0043
9.30	Sara	Welcome and introduction
	Plenary session 1: Sara
9.35	Maya	Cross-Lingual and Multilingual Speech Emotion Recognition on English and Chinese leveraging Self-Supervised Learning
9.50	Yaru	Chinese NER with speech clues
10.05	Mathias	Parsing the Old using the New: A study in parsing Icelandic
10.20	Ebba	Top2Vec in the context of Swedish historical texts
10.35	BREAK
	Session 2a: Johan		Session 2b: Meriem
11.05	Yini	Investigating the Impact of Modifying Open Domain Data with Artificial Tokens on Keyphrase Extraction Tasks	Moa	Af Somaali ma baran kartaa?
11.20	Yahui	Pre-trained Abstractive Text Summarization model With Post-processing	Hengyu	Improving Low-resource NMT with Langauge-specific Tokenizers: A Case Study of Cantonese-Chinese Translation
11.35	Iliana	Cross-Lingual POS-Tagging for Ancient Greek: Zero and Few-Shot Transfer Learning with Pre-Trained Models	Alex	Zero-shot sentiment classification for Nigerian Pidgin Tweets
11.50	LUNCH BREAK
	Session 4: Bea
13.15	Jie	Building a Multilingual Model for Low-resource Offensive Language Identification
13.30	Zharoui	Bi-LSTM-CNN Model Based on GloVe Word Embedding for Multi-Domain Sentiment Classification
13.45	Matilde	Language identificación of code-switching data: BiLSTM-CRF and combined code-switching datasets
14.00	Yiu Kei	Additional Paraphrase Training Drives Language Models Closer to Human Behaviour on Natural Language Inference
14.15	BREAK
	Session 3: Sara
14.45	Thea	Cross Attention Fine Tuning vs Full Scale Fine Tuning for Somali NMT
15.00	Aleksandra	A comparison of Machine Translation techniques for the very low-resource Faroese language
15.15	Ingrid	Collecting and Aligning a Parallel Corpus for Innu-Aimun and French, with a Machine Translation Baseline
15.30	Micaella	Bridging the Gap: Facilitating Translations Between Low-Resource Languages using NMT
15.45	Sara	Wrapping up
16.00	SOCIAL EVENT -- DEPARTMENT STAFF ROOM