End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely ...
Here we look at incorporating development education into classroom life and professional practice by examining the issue of teachers who teach development education but who do not have a strong knowledge base in global development issues. Where will they l ...
Social media (SM) platforms have demonstrated their ability to facilitate knowledge sharing on the global scale. They are increasingly often employed in educational and humanitarian domains where, despite their general benefits, they expose challenges pecu ...
Machine-readable semantic knowledge in the form of taxonomies (i.e., a collection of is-a edges) has proved to be beneficial in an array of NLP tasks including inference, textual entailment, question answering and information extraction. Such widespread ut ...
Remote areas are becoming a topic of increasing international interest as they can provide insights in the transition towards a more sustainable energy future. Being geographically isolated and distant from different services (e.g. energy, health and educa ...
Villigen PSI, World Resources Forum, printed by Paul Scherrer Institute2015
Advances in remote sensing technologies have allowed us to send an ever-increasing number of satellites in orbit around Earth. As a result, Earth Observation data archives have been constantly increasing in size in the last few years, and have become a val ...
We propose an automated image selection system to assist photo editors in selecting suitable images for news articles. The system fuses multiple textual sources extracted from news articles and accepts multilingual inputs. It is equipped with char-level wo ...
While artificial intelligence is successful in many applications that cover specific domains, for many commonsense problems there is still a large gap with human performance. Automated sentiment analysis is a typical example: while there are techniques tha ...
Non-Governmental Organizations in the humanitarian field are particularly knowledge intensive structures. However, they often fail to manage this knowledge efficiently and thus waste resources repeating avoidable mistakes. Providing adequate incentives for ...
New product development today is a knowledge-heavy process, but very often this knowledge is not adequately handled, it’s not made readily available to the actors, or is lost within or between similar projects. Furthermore, different legacy tools and data ...
