Category Archives: Conferences

COLING 2020 workshops

RGCL are pleased to announce that one of our PhD students – Hadeel Saadany – has had two papers accepted at COLING 2020 workshops. Congratulations! We look forward to the conference in December.

First paper:

‘Is it Great or Terrible? Preserving Sentiment in Neural Machine Translation of Arabic Reviews’

Accepted in: The Fifth Arabic Natural Language Processing Workshop – COLING’2020, Barcelona, Spain, 12 Dec. 2020

Team: Hadeel Saadany and Constantin Orasan

Summary:

The paper investigates the challenges involved in translating User Generated Content from Arabic into English with particular focus on the errors that lead to incorrect translation of sentiment polarity. It shows that fine-tune an NMT model with respect to sentiment polarity can significantly help in correcting sentiment errors detected in the online translation of Arabic UGC.

Second paper:

‘Fake or Real? A Study of Arabic Satirical Fake News

Accepted in: 3rd International Workshop on Rumours and Deception in Social Media – COLING’2020, Barcelona, Spain, 12 Dec. 2020

Team: Hadeel Saadany, Emad Mohamed, and Constantin Orasan.

 Summary:

This paper conducts several exploratory analyses to identify the linguistic properties of Arabic fake news with satirical content. It shows that although it parodies real news, Arabic satirical news has distinguishing features on the lexico-grammatical level. It also builds a number of machine learning models capable of capturing satirical fake news with an accuracy of up to 98.6\%.

Omid Rohanian: My visit to LxMLS summer school

I recently participated in the LxMLS summer school in Lisbon, Portugal. This is an annual event that focuses on theory and application of machine learning with a focus on natural language processing. The lectures followed a linear progression, starting from the fundamentals of traditional machine learning and later covered developments in deep learning. Each day in the morning, there was a lecture on some aspect of machine learning and then after the lunch students were assembled into groups to participate in the practical programming sessions. In the afternoons there was a talk on some application of machine learning in an actual research project.

In total there were more than 230 participants and the summer school lasted for 8 days. The lecturers are accomplished researchers in the field and the presentations were usually engaging and informative. I particularly enjoyed the talks given by Noah Smith, Chris Dyer, and Kyunghyun Cho. The event also included a poster presentation and a demo day where regional IT companies showcased their work and did recruitment advertising.

During the summer school I got the opportunity to get to know several PhD students working in the field from universities around the world and the networking was very valuable. The practical coding sessions could have been organised better with more supervision but overall I consider the experience as positive and worthwhile. I also found a bit of time during the day off to explore Lisbon and its surrounding areas. I enjoyed the historical delights and the amazing seafood and look forward to revisiting Portugal again soon.

Dr Michael Oakes attends the LingPhil Summer School

dav

The LingPhil summer school is an annual event primarily for the training of Ph.D. students in linguistics and philosophy in Norway, but students from other countries can come as well. This year it was held at the Solstrand Hotel and Spa, near Bergen in Norway which is a beautiful old hotel built in 1896.

The school opened on Monday June 4th with a session by Ewa Dąbrowska highlighting the “Seven Deadly Sins of Cognitive Linguistics”, which include excessive reliance on introspective evidence.

The following day Paul Kerswill from the University of York spoke on sociolinguistics – demography, social structure and identity in language change. As case studies, he talked about contact varieties of English which grew up in the Industrial Revolution, and recent developments in London English. Languages which are in contact become simplified, while languages which are isolated grow more complex. Steve Mann from Warwick University gave a training session on the research interview – how to collect data and analyse it, and the pros and cons of individual interviews and focus groups.

Wednesday was eventful, starting with a session on Corpus Pragmatics.  Our excursion was in the afternoon, a boat trip along the Bjørner Fjord to the island of Lysøen, which was once owned by Ole Bull, a world famous violinist. He had built an ornately carved wooden house there, with a main room that could be used as a small concert hall.  One of the organisers, Gisle Andersen, came with his choir to sing songs composed by Ole Bull and Edvard Grieg.

On the Thursday, I gave my sessions on “Statistics for Linguistics”, using Chris Butler’s book of the same name as the basis of the course. It was a busy day for me, as in the evening, I led a discussion group with students who are using statistics in their Ph.D. studies. Agnes Marie Bamford, who runs her own consultancy, and Claudia F. Hegrenæs from the Norwegian School of Economics, ran the career workshop. They pointed out that many transferrable skills can be gained from studying for a Ph.D., such as writing, networking, time management, analytic skills, critical thinking, problem solving, processing information quickly, endurance, grant writing skills, presentation skills, organising and coordinating, teaching experience even outside your comfort zone, and how to pitch your project. In fact, there was a special session devoted to the students all preparing “elevator pitches” to describe their work in two or three minutes.

On the final day, Åsta Haukås from the University of Bergen gave a session on multilingualism, and strategies that people, who are already at least bilingual, use to learn new languages. Many of these had been discovered using questionnaires based on SILL, the Strategy Inventory of Language Learning. As an illustration, we were given an article about Juliette Binoche in Dutch, and guessed the origins of each word in the text.