Author Archives: antske

PhD Position on LANGUAGE MODELS FOR NEWS RECOMMENDATION @CLTL

Leave a reply

Are you highly motivated and enthusiastic with expertise in computational linguistics? Are you interested in news recommendation systems and how to improve them by making their suggestions more divers? Would you like to investigate language models that can establish similarity and diversity and see how they can be used best in an interdisciplinary team?  Then please consider applying for this position.

Rethinking News Algorithms

In this project, an interdisciplinary team consisting of experts from Law, Computational Linguistics, Computer Science and Communication Science will study how recommendations and presentation choices can optimize the diversity of consumed news. Will you help us fix the way news is spread in the 21st century?

Specifically, in this project you will work on applying NLP technologies that can identify similarities and differences between news articles.

See http://ccs.amsterdam/projects/rethinking-news-algorithms/ for more details on the project. When contacting us with questions (see below for contacting details), please name the project in the subject of your email.

Where current algorithms mainly aim for finding things that are similar to prior consumption, we envision algorithms that optimize between sufficient diversity to keep users well informed and sufficient similarity so that the user is triggered to read (and be satisfied with) the offer. Together with law (ethics) and communication science experts, you will dive various dimensions of diversity (ranging from a different view on a specific event or political decision to diversity in topics in general) and aim to design language models that can identify articles that strike the desired balance between diversity and connection.

Your duties

  • conduct reproducible computational linguistic experiments on language models for diversifying recommendation systems
  • write research articles and present your work, which is to culminate in a successful dissertation, at international conferences 
  • collaborate with the other junior and senior researchers on the team experience in or affinity with working in an interdisciplinary team
  • organize small events such as workshops and colloquia

REQUIREMENTS

  • master degree in computational linguistics or a related field (e.g. Artificial Intelligence or Computer Science with focus on NLP)
  • solid programming skills
  • experience in or affinity with working in an interdisciplinary team
  • fluent verbal communication and good writing skills in English
  • knowledge of Dutch is an advantage (but not strictly necessary) 

WHAT ARE WE OFFERING?

The research will be carried in a great interdisciplinary team containing experts from computational linguistics, philosophy, law, computer science and communication science. You will become part of a renown computational linguistics lab (www.cltl.nl), headed by Spinoza laureat Prof. dr. Piek Vossen. The lab is embedded in the gravity project Hybrid Intelligence offering plenty of opportunity to collaborate with reseachers of various universities across the Netherlands on fundamental aspects around collaborate, adaptive, responsible and explainable AI. In this context, you will receive joint supervision by dr. Antske Fokkens (VU) and dr. Suzan Verberne (Leiden University).

For more information on employment conditions, please visit the advertisement on the VU-site

APPLICATION

Are you interested in this position? Please apply via the application button on the VU-site and upload

  • your curriculum vitae (including code repository, if available)
  • academic transcripts (including grades)
  • a cover letter with motivation for your application 

until June 1, 2020.

The job interviews are currently planned to take place in the second half of June 2020, most likely they will take place online.

Applications received by e-mail will not be processed.

Vacancy questions
If you have any questions regarding this vacancy, you may contact:

Name: dr. Antske Fokkens
Position: Associate Professor
E-mail: antske.fokkens@vu.nl

Please mention `news recommender project’ explicitly in the subject line of your email when asking questions about this position

VENI grant for Antske Fokkens

Leave a reply

Antske Fokkens received a VENI grant for her proposal Reading between the lines. The project aims at identifying so-called implicit perspectives in text.

Perspectives are conveyed in many ways. Explicit opinions or highly subjective terms are easily identified. However, perspectives are also expressed more subtly. For instance, Nick Wing argues that media describe white suspects (e.g. brilliant, athletic) more positively than black victims (e.g. gang member, drug problems). Ivar Vermeulen (p.c.) observes in a small Dutch corpus that Moroccan perpetrators are easily called thieves (implying generic behavior), where other perpetrators from Dutch only stole something (implying incidental behavior). These observations are anecdotal, but reveal how choices concerning what information to include or how to describe someone’s role may display a specific perspective.

This project will investigate how linguistic analyses may be used to identify these more implicit ways of expressing perspectives in text. This research will be carried out in three stages: First, large scale corpus analyses will be applied to identify distributions of semantic roles (what entities do) and other properties assigned to them (their characteristics). In the second stage, generic participants will be linked to the semantic role they imply (e.g. a thief will be linked to the perpetrator of stealing). With these links, we can investigate whether thieves are described differently from people who steal. In the third stage, emotion and sentiment lexica will be used to identify the sentiment associated with descriptions of people enabling research that investigates whether people are depicted positively or negatively.

The research is carried out in the context of digital humanities and social sciences. Evaluation and experimental setup will be guided towards identifying differences in perspective between sources. In addition to correctness of linguistic analyses (intrinsic evaluation), the possibility of using the method for identifying changes in perspective over time (historic research) or differences in perspective between sources (communication science) will be investigated.