Enhancing Quality Assessment Using Perspective Detection

Call for Network Institute Research Assistants

Network Institute > Academy Assistants > Academy Projects 2017

We, Chantal van Son (CLTL group) and Davide Ceolin (Web & Media group), are looking for two talented Master students to be hired as research assistants for 10 months for 1 day a week in the Network Institute project “Enhancing Quality Assessment Using Perspective Detection”. This project is part of the Academy Assistants programme.

Project description
As humans, we assess Web documents on two dimensions. On the one hand, we evaluate their quality by judging how precise, accurate or neutral the information contained in documents is, or how reliable their sources are based on their reputation. On the other hand, we consider which perspectives are represented in documents. Do the authors present information from their own or someone else’s perspective? How (un)certain are sources about the truth of statements? In turn, perspectivization of information may affect our quality assessments.

In this interdisciplinary project, the two students will collaborate to improve and enrich the output of an existing tool for assessing the quality of Web documents along two lines. First, the current coarse-grained quality assessment scores are accompanied by more fine-grained predictions over specific quality dimensions like precision, accuracy, and neutrality of the information. Second, we will make use of NLP technologies to integrate information on attribution (who says what) in text.

Responsibilities and Requirements
We are looking for one student from Computer Science/Artificial Intelligence (CS/AI) and one student from (Computational) Linguistics (CL).

The CS/AI student will be responsible for:

  • developing and extending the existing quality assessment tool, providing an interface for lay users to access the tool, and integrating the quality assessment and perspective detection components developed within the project;
  • extending the set of quality dimensions predicted, i.e., automating the prediction of the quality of Web documents for qualities like precision, accuracy, neutrality, completeness. Training data for such qualities is already available;
  • testing a range of machine learning algorithms for predicting the quality of Web documents.

Preferred knowledge and skills of the CS/AI student are:

  • programming skills;
  • knowledge of Web/Semantic Web technologies;
  • machine learning.

The CL student will be responsible for:

  • applying NLP technology to detect attributions in text;
  • analysing the output of the attribution detection tool and identifying potential useful features for quality assessment;
  • annotating texts with relevant attribution types (to be defined by the student).

Preferred knowledge and skills of the CL student are:

  • strong background in linguistics and affinity with technology (programming skills are a plus), or;
  • strong technological background and an interest in language technology.

Why you should apply:

  • You will be working on a complete research project, from beginning to end;
  • You will be collaborating with a fellow student from another faculty and learn how to do interdisciplinary research;
  • The work hours are flexible;
  • This is an excellent opportunity to boost your CV.

If you are interested, send us your CV (with course list and grades) and a short motivation letter before Monday July 31, 9:00 to Davide Ceolin (d.ceolin@vu.nl) and Chantal van Son (c.m.van.son@vu.nl). Of course, also feel free to contact us for more information.

Chantal Davide

Enhancing Quality Assessment Using Perspective Detection: Network Institute Academy Assistants Projects 2017 (2017-2018)