Betreuer: Mehwish Alam, Yiyi Chen
Forschungsgruppe: Information Service Engineering
Partner: FIZ Karlsruhe
Beginn: 01. April 2021
Objective of this thesis:
Since 2015, the topic of migration and refugee “crisis” has been brought into the spotlight, partly due to the massive coverage of the media and its exposure in social networks. Metaphors are pervasive in these reports and dialogues, which use conceptual mapping to represent one thing as another. For example, “The refugees are flooding into Germany”  invokes the natural phenomena of “flood” which expresses the negative sentiment of the migration movement by implying its forcefulness. Processing metaphors is therefore essential to capture the authentic meaning and sentiment of migration related documents in natural language processing.
The objective of this thesis is to detect metaphors in the news articles collected based on the topic of migration spanning from 2013 to 2020. There are existing metaphor corpora such as VU Amsterdam Metaphor Corpus covering about 190,000 lexical units from academic texts, conversation, fiction, and news texts , which can be used as our training set. The thesis will focus on exploiting deep learning based methods for sequence labeling as well as classification.
 Photo Source: Migrants and the media: what shapes the narratives on immigration in different countries
 Immigration fuels rising tension in Germany
 The VU Amsterdam Metaphor Corpus Online
The thesis will be supervised by Yiyi Chen and Dr. Mehwish Alam, Information Service Engineering at Institute AIFB, KIT, in collaboration with FIZ Karlsruhe.
Keywords: Natural Language Processing, Machine Learning
Pre-requisites: Knowledge of Programming with Python.
Please send your CV and questions (if any) to the following e-mail address.
Yiyi Chen, yiyi chen∂partner kit edu
Dr. Mehwish Alam, mehwish alam∂kit edu
Ausschreibung: Download (pdf)