讲座主题:
Transfer learning of distributional semantic models for argumentative discourse structures
主讲人姓名及介绍:
João Rodrigues is a PhD Student of Informatics Engineering at the University of Lisbon who is undertaking its doctoral research at the NLX-Natural Language and Speech Group under the supervision of António Branco. He completed his Masters thesis on the topic of machine translation, with the title “Speech-to-speech Translation to Support Medical Interviews”. Since then he continued enrolled as a research assistant, contributing to different research projects on natural language processing, in the scope of which he published 25 co-authored papers.
报告摘要:
Automatic computation of argumentation can assist in querying different points of view or opinions, second language learners improving their essays writing or a decision-making process, among others. We describe the development and evaluation of an automatic argumentative discourse classifier for English that identifies argument and non-argument structures in a written text.
We start by replicating the state-of-the-art resorting to a machine learning neural network classifier and then proceed to improve the results using transfer learning techniques. Transfer learning is a machine learning technique that leverages knowledge from multiple classification tasks to improve an algorithm generalization and thus obtaining better results. The training of the machine learning models uses the knowledge shared among tasks.
We report on the results from the knowledge transfer of language modeling tasks. We also report on the results from the transfer learning of a natural language inference task. The experimentation space included different neural network architectures and hiper-parameterization.
