The ACC Lab hosts and is involved in multiple internal and cooperation projects funded by FNR and other agencies. This is the short list of the most recent projects.
Conversation Analysis and Conversational Interfaces
Despite all difficulties in the beginning, a lot of research effort has been invested to bring various insights gained from Conversation analysis (CA) into Dialogue Processing. Several attempts have been made to involve CA in dialogue-based human-machine interaction. In this internal cross-faculty collaboration project we explore further involvement of CA methods in all sorts of conversational interfaces and chatbots. Partners: Béatrice Arend (University of Luxembourg, Education, Culture, Cognition and Society Research Unit).
Artificial Conversation Companion
Practicing foreign language conversation with a machine may have multiple advantages: a machine does not judge, a machine is always available and accessible from everywhere. In this project we focus on language understanding and generation for German as a communication language for non-native speakers. A chatbot called Coco Müller will be deployed on Facebook Messenger soon. Stay tuned!
QuizBot: Conversational Interfaces for E-Assessment
In this proof-of concept project we investigate the opportunities and limitations of using conversational interfaces for e-assessment. We are working on connecting the open-source assessment software TAO with various instant messengers. This project is a continuation of the master thesis project by Bharathi Vijayakumar who successfully finished her thesis in September 2018.
Robo-Chat: Using Conversational Interfaces for Communication with Complex Systems (Internal)
In this internal research cooperation between the ACC Lab and SnT, we focus on using conversational interfaces for communication with complex technical systems in order to foster the explainability of their decisions, facilitation of the maintenance and a better understanding of human needs for such interfaces. We chose a data-driven approach for building a rule-based system, for which we analyse a dataset from Wizard-of-Oz experiments. This research is grounded in Conversation Analysis which allows dialogue modelling from small datasets and small number of examples. Cooperation partner: Nico Hochgeschwender (SnT).
PERSEUS: Personalized concept-based Sentiment Analysis
In the research project PERSEUS, we aim at discovering individualities in expressing sentiments in text. To study the diversity between individuals and the consistency in each individual, we have build a personalized framework that takes user-related text from social platforms, such as Twitter and Facebook, and investigates and improves sentiment categorisation by applying Deep Learning techniques. This project researches beyond purely understanding the meaning of text, and focuses on integrating the preference and tendency of users to provide user-sensitive predictions. Aspects of sentiment analysis in chatbots are analysed. Cooperation Partners: Lenovo AI Research Beijing.
Contact: Siwen Guo
Approaching Indigenous Australian History With Text Mining Methods
Despite their remarkable value, autobiographies appear to remain one of the most under-utilized historical resources. The proposed research project in digital humanities will apply computational Distant Reading-methods (natural language processing in general and topic modeling in particular) as a complement to traditional ”close reading” of Indigenous Australian autobiographies, aiming to identify meaningful language use patterns in the context of social environment and historical events. Cooperation Partner: C2DH.
Contact: Katya Kamlovskaya
STRIPS: A Semantic Search Toolbox for the Retrieve of Similar Patterns in Luxembourgish Documents
The aim of STRIPS is to develop a toolbox of semantic search algorithms for Luxembourgish. We want to implement search algorithms to retrieve and to monitor, e.g., temporal patterns of named entities in Luxembourgish texts. The term ‘semantic’, hereby, does not only refer to the usage of keywords or Bag-of-Words (for example: names, geographic identifiers), but fosters also on more complex structures like, for example, on concepts (e.g., topics or themes) and a document’s sentiment (e.g., a positive or a negative polarity of the document). The main focus of STRIPS lies in the linguistic processing of texts written in Luxembourgish (particularly stemming, use of phonetic dictionaries and tagged word list for Luxembourgish; Part-of-speech-tagged text corpus), in similarity learning aspects to allow fuzziness in search queries, and in the identification of temporal cross-dependencies inside the Luxembourgish text corpus. To validate the project, we have given heterogeneous text sources (official news items and user-contributed comments). Cooperation Partner: RTL.
Watch the Luna Toolset tutorial on YouTube
Contact: Dr. Josh Sirajzade