{"id":89,"date":"2018-10-07T09:16:32","date_gmt":"2018-10-07T09:16:32","guid":{"rendered":"http:\/\/cleopatra-project.eu\/?page_id=89"},"modified":"2026-01-29T09:42:35","modified_gmt":"2026-01-29T09:42:35","slug":"individual-esr-projects","status":"publish","type":"page","link":"https:\/\/cleopatra-project.eu\/index.php\/early-stage-researchers\/individual-esr-projects\/","title":{"rendered":"ESR projects"},"content":{"rendered":"

Individual Research Projects<\/b><\/p>\n

There were 15 Early Stage Researchers in the CLEOPATRA programme. There are details of their projects below:<\/p>\n

1. Fact extraction and cross-lingual alignment (Gottfried Wilhelm Leibniz University Hannover, LUH)<\/a>
\n2. Interactive user access models to cross-lingual information (Gottfried Wilhelm Leibniz University Hannover, LUH)<\/a>
\n3. Crowd quality and training in hybrid multilingual information processing and analytics (King’s College London, KCL)<\/a>
\n4. Incentives design for hybrid multilingual information processing and analytics (King’s College London, KCL)<\/a>
\n5. Fact validation across multilingual text corpora (Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn,\u00a0<\/span>UBO)<\/a>
\n6. Interactive multilingual question answering (Rheinische Friedrich-Wilhelms-Universit\u00e4t Bonn,\u00a0<\/span>UBO)<\/a>
\n7. Relations of textual and visual information (TIB Hannover – German National Library of Science and Technology, TIB)<\/a>
\n8. Contextualisation of images in multilingual sources (TIB Hannover – German National Library of Science and Technology, TIB)<\/a>
\n9. National and transnational media coverage of European parliamentary elections, 2004-2014 (University of London, UoL)<\/a>
\n10. Nationalism, internationalism and sporting identity: the London and Rio Olympics\/Paralympics (University of London, UoL)<\/a>
\n11. Information propagation with barriers (Institut Jo\u017eef Stefan ,<\/span>JSI)<\/a>
\n12. Cross-lingual news reporting bias (Institut Jo\u017eef Stefan,\u00a0<\/span>JSI)<\/a>
\n13. Multilingual Wikipedia as ‘first draft of history’ (University of Amsterdam, UvA)<\/a>
\n14. NLP for under-resourced languages (Sveuciliste u Zagrebu Filozofski Fakultet – University of Zagreb,\u00a0<\/span>FFZG)<\/a>
\n15. Cross-lingual sentiment detection (Sveuciliste u Zagrebu Filozofski Fakultet – University of Zagreb,\u00a0<\/span>FFZG)<\/a>
\n18. Multi Modal Fact Validation (TIB Hannover – German National Library of Science and Technology, TIB)<\/a>
\n19. Cross Cultural Comparison of Russian State Controlled and Independent Media (University of Amsterdam, UvA)<\/a><\/p>\n

 <\/p>\n\n\n\n\n\n\n\n
ESR1: Tin Kuculo<\/a>\u00a0 \u00a0 \u00a0 \u00a0<\/b><\/td>\n\"\"<\/td>\nPhD enrolment: LUH<\/b><\/a><\/td>\n<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
Project Title: Fact extraction and cross-lingual alignment <\/b>(WP4<\/a> –\u00a0Event-centric cross-lingual Information processing)<\/span><\/a><\/td>\n<\/tr>\n
Objectives: <\/b>Extract and interlink mentions of related facts and their multilingual context and establish their semantic and temporal relations in comparable corpora by leveraging hybrid computational methods while utilizing NLP and ML-based technologies.<\/td>\n<\/tr>\n
Impact: <\/b>QuoteKG was developed, a multilingual knowledge graph of quotes, containing nearly a million quotes across 55 languages from over 69,000 public figures, to aid in understanding world history and influencing societal discourse. Wikiquote was used as a primary source to address the challenges of context scarcity in quote collections, language variation, and quote alignment, and a language-agnostic transformer model for cross-lingual alignment was employed. <\/span>QuoteKG, with its rich metadata and context for each quote, facilitates cultural and historical research, demonstrated by its application in curating event quote collections and conducting event-centric analyses.<\/span><\/td>\n<\/tr>\n
Future research: <\/strong>The Semantic Web and NLP communities have developed different methods for event-centric information extraction and representation. Knowledge graphs focus on named events, while NLP-based approaches focus on finer-grained, self-contained events. FollowUp work aims to incorporate the strengths of both Semantic Web and NLP perspectives and presents a new approach, Ontology-Guided Event Extraction (O-GEE), to address challenges associated with event ontologies, the extraction of relevant event relations, and the alignment of event ontologies in NLP and the Semantic Web.<\/span><\/p>\n

A two-step approach is planned to extract fine-grained event locations from large-scale knowledge graphs, such as Wikidata, DBpedia, and YAGO. The method first integrates a geographic knowledge graph into an event knowledge graph to counteract the lack of detailed location information, and then employs a graph neural network on the combined event knowledge graph to extract precise event locations.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n\n\n\n\n\n\n\n
ESR2:\u00a0Sara Abdollahi<\/a><\/b><\/td>\n\"\"<\/td>\nPhD enrolment: LUH<\/b><\/a><\/td>\n<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
Project Title: Interactive user access models to cross-lingual information <\/b>(WP5 –\u00a0<\/a>Hybrid computation, user interaction and<\/span> question answering<\/span><\/a>)<\/td>\n<\/tr>\n
Objectives: <\/b>Develop user interaction models that enable users to efficiently and effectively access extracted event-centric multilingual information and its context and analyse language-specific differences.<\/td>\n<\/tr>\n
Impact: The LaSER language-specific event recommendation algorithm was developed to help users (mostly researchers and journalists) supporting cross-language exploration, Web navigation and exploratory search.<\/span><\/b><\/td>\n<\/tr>\n
Future research: <\/strong>Document retrieval for events using query expansion and knowledge graphs; and building event-centric collections from web archives, as the result of my research during my secondment at the British Library.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n\n\n\n\n\n\n\n
ESR3:\u00a0Gabriel Amaral<\/a><\/b><\/td>\n\"\"<\/b><\/i><\/u><\/td>\nPhD enrolment: SOTON<\/a>\u00a0\/ KCL<\/a><\/b><\/td>\n<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
Project Title: Crowd quality and training in hybrid multilingual information processing and analytics <\/b>(WP5 –\u00a0<\/a>Hybrid computation, user interaction and question answering<\/a>)<\/td>\n<\/tr>\n
Objectives: <\/b>Design a mixed-crowdsourcing workflow to produce high-quality multilingual data for knowledge graphs.<\/td>\n<\/tr>\n
Impact:<\/b> The research has made great strides in the Wikidata Research community in uncovering the impact that the quality of references (for Wikidata claims) has on the perceived quality of the information itself. We explored how humans perceive the quality of such references, how to best measure it, what is the current state of such quality metrics in current Wikidata, and direct steps that could be done to improve it. This section of our research was extremely well received by the community, being granted a Wikimedia Foundation Research Award of the Year. We followed this up by constructing an automated pipeline to assist in the maintenance of Wikidata (or any KG) references. We also explored how such a model can be explained in order to gain the trust and understanding of its users.<\/span><\/td>\n<\/tr>\n
Future research:<\/strong> Follow-ups for this research would look into other ways to automate fully or partially the measurement of relevant metrics for reference quality. This could focus on the main metrics we have established (relevance, authoritativeness, and ease of use), or others. NLP models are making huge advancements (e.g. ChatGPT), so applying these techniques to this task seems like a natural next step.<\/span><\/strong><\/b><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\u00a0<\/strong><\/p>\n\n\n\n\n\n\n\n
ESR4: Elisavet Koutsiana<\/a><\/b><\/td>\n\"\"<\/td>\nPhD enrolment: KCL<\/a><\/td>\n<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
Project Title: Incentives design for hybrid multilingual information processing and analytics <\/b>(WP5<\/a>\u00a0– \u00a0<\/b>Hybrid computation, user interaction and question answering<\/a>)<\/td>\n<\/tr>\n
Objectives:\u00a0<\/b>Understand what motivates people to engage in knowledge graph creation and curation activities, across language contexts, and devise incentive mechanisms to foster useful knowledge graph contributions.<\/td>\n<\/tr>\n
Impact: <\/b><\/b>The contribution investigated how members of the community work and interact through their discussions providing valuable inputs to peer production communities, particularly the collaborative knowledge graph communities.\u00a0The research study confirmed how important discussions are as a source of insights regarding members’ collaboration and provided frameworks for studying online discussions in collaborative knowledge graph projects, like qualitative analysis coding schemes for investigating the main topics discussed, as well as for identifying argumentation patterns and the role of discussion participants in controversial discussions. <\/span>An overview of the complete corpus of Wikidata discussions was provided, as well as publicly available code for descriptive statistical analysis of the corpus. <\/span>The research suggests design improvements and topics for follow-up studies in knowledge graph quality and editor engagement.<\/span><\/td>\n<\/tr>\n
Future research: <\/strong>Future directions of this research could investigate: <\/span>how decisions are made and how they impact the knowledge graph construction; and <\/span>how discussions and members’ interaction impact the quality of the knowledge graph<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n\n\n\n\n\n
ESR5: Jason Armitage<\/b><\/td>\n\"\"<\/td>\nPhD enrolment (2019-20): UBO <\/b><\/a><\/td>\n<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
Project Title: Fact validation across multilingual text corpora <\/b>(WP4 –\u00a0\u00a0<\/b><\/a>Event-centric cross-lingual Information processing<\/a>)<\/td>\n<\/tr>\n
Objectives: <\/b>Develop hybrid methods for cross-lingual fact validation and leverage multilingual distributed sources to provide a more complete set of source candidates in order to validate the facts.<\/td>\n<\/tr>\n
Expected Results: <\/b>Methods for hybrid cross-lingual fact validation using heterogeneous information sources.<\/td>\n<\/tr>\n
Unimodal systems that process natural language predominate in research on fact validation – but reporting on events are rarely comprised of text alone. The co-existence of multiple modalities creates an opportunity to implement machine learning systems that retrieve, combine, and model diverse inputs. Fact validation systems that process multiple modalities are able to assess additional evidence, learn rich representations, and conduct supplementary analyses on source data.\u00a0<\/span><\/p>\n

Fact validation is composed of the sub-tasks of parsing inputs, retrieving evidence, and inferring relations between the two. In related applications, approaches that compose a design – after breaking problems down into steps – are better suited to tasks with composite structure. Learning on multiple modalities introduces an additional level of complexity for monolithic architectures. This research aims to implement and evaluate systems optimised to process diverse data and adapt to the multiple sub-tasks comprising the fact validation pipeline. <\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

\u00a0<\/strong><\/p>\n\n\n\n\n\n\n\n
ESR6:\u00a0Endri Kacupaj<\/a><\/strong><\/td>\n\"\"<\/td>\nPhD enrolment: UBO <\/b><\/a><\/td>\n<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
Project Title: Interactive multilingual question answering<\/b> (WP5 –\u00a0\u00a0<\/b><\/a>Hybrid computation, user interaction and question answering<\/a>)<\/td>\n<\/tr>\n
Objectives: <\/b>Train neural networks to convert natural language queries to a formal query language, which will then be answered using existing knowledge bases. Enable efficient user interaction and feedback to enhance results.<\/td>\n<\/tr>\n
Impact: <\/b><\/b>Conversational Question Answering over Knowledge Graphs with Answer Verbalization. The impact of the research can be summarised as follows:<\/span><\/p>\n
    \n
  • \n
      \n
    • We provided a semi-automated framework for generating multiple paraphrase responses for a question by utilizing methods such as back-translation. Furthermore, we release the first KGQA dataset with multiple paraphrased verbalized responses.<\/span><\/li>\n
    • We presented the first multi-task-based answer verbalization framework that employs questions and logical forms as inputs and simultaneously trains four modules for generating natural language answers.<\/span><\/li>\n
    • We developed two multi-task neural semantic parsing approaches for (complex) conversational question answering over knowledge graphs. We distinguish the works from the number of sub-tasks they perform and the different deep neural architectural modules they utilize.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n

      For Conversational QA, we studied whether the availability of entire dialog history, domain information, and verbalized answers can act as context sources in determining the ranking of KG paths while retrieving correct answers. We proposed an approach that models conversational context and KG paths in a shared space by jointly learning the embeddings for homogeneous representation.<\/span><\/td>\n<\/tr>\n

<\/b>Further research:<\/strong> The contributions of this research pave the way for a more extensive research agenda that will foster further research. A few of such directions are enumerated below:<\/p>\n
    \n
  • \n
      \n
    • There are empirical evaluations that for AI systems, the explanations regarding the retrieved answers improve trustworthiness, especially in wrong prediction. Hence, how an answer verbalization can be explained remains an important open research direction.<\/span><\/li>\n
    • For Conversational QA, path ranking is a relatively new method for approaching the task. While it is more difficult to comprehend the predictions compared to semantic parsing models, path ranking will be favored since it does not depend on any annotation process or data. We see an emergence of future ConvQA systems towards that direction; however, the explainability of ranking strategies remains a tough challenge and is eventually to be addressed.<\/span><\/li>\n
    • For the developed approaches, we employ multi-task learning via hard parameter sharing. Multi-task learning can be crucial for approaching complicated tasks such as question answering. We expect the development of massive and flexible multi-task learners able to perform numerous tasks. Question answering will be achieved by combining parts of them, and for any new knowledge learned, the model will update a comparatively small number of parameters. Likewise, we believe that multi-task learning is essential in developing artificial intelligence with more human-like qualities.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      \u00a0<\/strong><\/p>\n\n\n\n\n\n\n\n
      ESR7:\u00a0Gullal Singh Cheema<\/a><\/b><\/td>\n\"\"<\/td>\nPhD enrolment: TIB<\/b><\/a><\/td>\n<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
      Project Title: Relations of textual and visual Information\u00a0<\/b>(WP4 –\u00a0\u00a0<\/b><\/a>Event-centric cross-lingual Information processing<\/a>)<\/td>\n<\/tr>\n
      Objectives: <\/b>Develop and research (deep) learning systems that are able to 1.) find the paragraphs and sentences in a text which are relevant to image content, and 2.) predict the granularity and semantic level of text-image relations.<\/td>\n<\/tr>\n
      Impact:<\/b><\/p>\n
        \n
      • \n
          \n
        • A novel method for text-based claim detection was proposed, as well as a novel approach for hate speech detection in multimodal memes (a multi-task learning model).<\/span><\/li>\n
        • A new multimodal claim detection dataset was created including a multi-topic and diverse set of claims with annotations for multiple tasks.<\/span><\/li>\n
        • A theoretical framework was proposed for multimodal news analysis based on research in semiotics (image-text relations), journalism (news values) and computational science.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/td>\n<\/tr>\n
      Further research: <\/span><\/span><\/strong>A follow up on multimodal claims is already part of Checkthat! 2023 challenge on Check Worthiness, Subjectivity, Political Bias, Factuality, and Authority of News Articles and Their Sources. The new test dataset, part of the challenge, contains tweets from 2021 and 2022.\u00a0A few papers are planned for computational research on image-text relations, multimodal hate speech and analyzing large multimodal language models.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      \u00a0<\/strong><\/p>\n\n\n\n\n\n\n\n
      ESR8:\u00a0Golsa Tahmasebzadeh<\/a><\/b><\/td>\n\"\"<\/td>\nPhD enrolment:\u00a0TIB<\/a><\/b><\/td>\n<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
      Project Title: Contextualisation of images in multilingual sources <\/b>(WP4 –\u00a0\u00a0<\/b><\/a>Event-centric cross-lingual Information processing<\/a>)<\/td>\n<\/tr>\n
      Objectives: <\/b>Research how surrounding text information can be utilized to infer and refine spatial and temporal information about an image in multilingual Web sources to support cross-lingual alignment.<\/td>\n<\/tr>\n
      Impact: <\/b><\/b>Contextualization of news photos based on geolocation estimation and event type classification can impact the research field in various aspects such as:<\/p>\n
        \n
      • \n
          \n
        • Data enrichment: Contextualizing news documents helps researchers enrich their datasets with valuable information such as the geographic source of an event.<\/span><\/li>\n
        • Improved data analysis: Geolocation estimation and event type classification provide additional insights for analysing news photos. For instance researchers can explore the spatial and temporal patterns in news coverage.<\/span><\/li>\n
        • Verification and fact-checking: Geolocation estimation and event type classification can aid researchers in verifying the accuracy of news documents. By integrating these meta information researchers can further explore misinformation detection, and identification of manipulated images.\u00a0<\/span><\/li>\n
        • Multimedia representation: Geolocation-based image-text relations can help social scientists in analysing media content and representation. For instance they can investigate how different locations are depicted in images and the accompanying text. Furthermore they can explore cultural stereotypes, or media bias.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/td>\n<\/tr>\n
      Further research:<\/b> Possible follow-up research directions are:<\/p>\n