Talk: "Deep Learning Approaches to Text Production
July 19th, 2018, 11-12 AM in S1/01 A2
Text production is a key component of many NLP applications. While data-to-text approaches are used to generate dialogue turns from dialogue moves, to verbalise the content of Knowledge bases or to generate sentences from rich linguistic representations (e.g., dependency trees or Abstract Meaning Representations), text-to-text methods are needed for sentence compression, sentence fusion, paraphrasing, sentence (or text) simplification, text summarisation and end-to-end dialogue systems.
Claire Gardent is a senior researcher at the French National Center for Scientific Research (CNRS). Her research interests include executable semantic parsing, hybrid symbolic-statistical approaches to NLP and Natural Language Generation. She serves as the chair of SIGGEN, the ACL Special Interest Group in Natural Language Generation and is on the editorial board of Transactions of the Association for Computational Linguistics (TACL). She was for four years the chair of the Board of the European Chapter for the Association of Computational Linguistics (EACL) and acted as program chair for various international conferences, workshops and summer schools (EACL, ENLG, SemDIAL, SIGDIAL, ESSLLI). She has received funding from several international funding agencies including EU, DFG and ANR.