PhD: Tensor Factorization Models for Creative Language Generation

Descrizione

PhD: Tensor Factorization Models for Creative Language Generation Sintesi in italiano (traduzione automatica): L'organizzazione internazionale offre una posizione di dottorato nell'ambito del progetto ERC TENACITY, che si concentra sulla generazione creativa del linguaggio attraverso modelli di fattorizzazione tensoriale. La sede è presso il Centro di Linguistica Computazionale. Il candidato ideale possiede una laurea magistrale in linguistica computazionale, intelligenza artificiale, informatica, matematica o un'istruzione equivalente, con una solida preparazione in machine learning e algebra lineare. È richiesta esperienza nella programmazione, preferibilmente in Python, e un forte interesse per la linguistica, in particolare per la semantica lessicale e il linguaggio figurato. La posizione è a tempo pieno per un anno, con possibilità di estensione fino a quattro anni, e offre l'opportunità di partecipare a conferenze internazionali e ricevere formazione accademica. Creativity pervades human language use, yet the mechanisms behind it are poorly understood, and current language technology shows little true creativity. The ERC project TENACITY develops computational models of language that exhibit creativity, combining interpretable tensor factorization methods with neural language models. This PhD position focuses on the tensor-based strand of the project. Tensor factorization models induce latent semantic dimensions from multi-way word co-occurrences; these latent dimensions can be interpreted and manipulated (e.g. as mappings between semantic domains) in order to generate creative language expressions. A PhD researcher within the project is currently applying this approach to metaphor; the new position will extend this line of research. Possible topics include efficient factorization algorithms for large-scale, sparse language data (such as tensor train decomposition), the automatic induction of semantic domain mappings, and the application of latent semantic structure to a broader range of creative language phenomena. The precise focus will be determined in function of the candidate’s background and interests. You will join the TENACITY team of PhD researchers and postdocs at the Centre for Computational Linguistics. You hold a Master’s degree in computational linguistics, artificial intelligence, computer science, mathematics, or equivalent education. You have a solid background in machine learning and an affinity with linear algebra; experience with tensor methods is a plus. You have excellent programming skills (preferably Python, including the NumPy/SciPy ecosystem). You have a keen interest in language and linguistics, in particular lexical semantics and figurative language. You exhibit excellent proficiency in English and good oral and written communication skills. We offer a full-time PhD position for 1 year, extendable to 4 years after initial positive evaluation. You will be able to conduct scientific research within a high-level research environment, leading to a doctoral degree. You will work within an ERC-funded project team, with access to ample computing infrastructure and funding for conference travel. You will have the opportunity to participate in international conferences, and benefit from academic training and workshops. For more information please contact Prof. dr. Tim Van de Cruys, mail: tim.vandecruys@kuleuven.be . Annuncio in inglese. Fonte: Euraxess (Commissione europea).