We are people from academia and industry that are passionate about Natural Language Processing, Machine Learning, Language Technology and Computational Linguistics.
The group is intended to keep each other updated about NLP-related events in the Copenhagen area. This includes talks, workshops, conferences and the like. We'd also like to establish and maintain contacts within and across companies and academic groups.
Title: Bidirectional Sequence Generation and Graph AI
The talk is structured in two parts. First, we introduce a method that improves sequence generation for NLP, demonstrated on two chatbot dialogue tasks. Second, we look at various AI research projects ongoing at NEC Labs Europe, centering around using graphs to solve real-world problems.
Neural sequence generation is typically performed token-by-token and left-to-right. Whenever a token is generated only previously produced tokens are taken into consideration. In contrast, for problems such as sequence classification, bidirectional attention, which takes both past and future tokens into consideration, has been shown to perform much better. We propose to make the sequence generation process bidirectional by employing special placeholder tokens. Treated as a node in a fully connected graph, a placeholder token can take past and future tokens into consideration when generating the actual output token. We verify the effectiveness of our approach experimentally on two conversational tasks where the proposed bidirectional model outperforms competitive baselines by a large margin.
Many real-world problems are naturally suited to be represented as graphs. In our lab, we developed two core graph AI algorithms. The first, KBlrn, can be used for knowledge base completion and we have applied it to tasks such as insurance fraud detection or multimodal knowledge graph prediction. The second, Embedding Propagation (EP), learns vector representations of nodes in a graph, with which we can tackle problems such as patient outcome prediction or personalized vaccine selection.
Carolin Lawrence (https://carolinlawrence.github.io/) is a research scientist at NEC Labs Europe (https://uk.nec.com/en_GB/emea/about/neclab_eu), where she works on natural language processing, graph-structured data and reinforcement learning. A special interest of hers is researching ways to create explainable AI that makes a difference in praxis for real human users. Before joining NEC, she received her PhD in computational linguistics from the University of Heidelberg, where she worked in the statistical NLP group supervised by Prof. Stefan Riezler.
This meetup is part of the University of Copenhagen AI Centre Seminar Series (https://ai.ku.dk/events/). The talk will be from 13:00-13:45, followed by 15 minutes for questions and informal networking after the talk.