Sentiment Analysis and Cognitive,Cross-Topic Models for Natural Language Representations (Talk)
- Nikos Athanasiou
First, a short analysis of the key components of my participation in SemEval 2018, an emotion analysis contest from tweets. Namely, a transfer learning approach used for emotion classification and a context-aware attention mechanism. In my second paper, I explore how brain information can improve word representations. Neural activation models that have been proposed in the literature use a set of example words for which fMRI measurements are available in order to find a mapping between word semantics and localized neural activations. I use such models to predict neural activations on a full word lexicon. Then, I propose a cognitive computational model that estimates semantic similarity in the neural activation space and investigates the relative performance of this model for various natural language processing tasks. Finally, in my most recent work I explore cross-topic word representations. In traditional Distributional Semantic Models -like word2vec- the multiple senses of a polysemous word are conflated into a single vector space representation. In my work, I propose a DSM that learns multiple distributional representations of a word based on different topics. Moreover, we project the different topic representations in a common space and apply a smoothing technique to group redundant topic vectors.
Biography: Nikos has done Electrical & Computer Engineering 5-year degree(NTUA). He has his Master thesis on cognition and natural language representations. He has worked for 1.5 year in SLP-NTUA laboratory as a researcher in the field of Natural Language Understanding and Emotion Recognition and worked also as a Machine Learning Engineer in DeepLab, Athens responsible for NLP infrastructure. He also collaborated in building and maintaining industrial deep learning software pipeline. He is interested in Machine Learning, Natural Language Understanding and Multimodal Perception.