Voice-based POI Search
At NAVER LABS, we consider that human-centric search and recommendation interfaces are key to enabling a world of Ambient Intelligence. In this new world where location and context are understood, digital technologies will proactively propose and recommend activities, places and things to people, helping them interact and navigate in the physical environment. Such digital recommendation and guidance should be as seamless and natural as possible. The main objective of the Search and Recommendation team at NAVER LABS Europe is to translate this ambition into the design of context-aware, personalised and anticipatory search and recommendation modules.
In this internship you will explore an Automatic Speech Recognition (ASR) toolkit and customize it for a specific vertical application, namely contextualised search for Points of Interest. More precisely, you will investigate :
- how to adapt some modules of the ASR by exploiting linguistic and ontological resources that underpin the domain and the task;
- how to exploit word lattice representations to improve the query undestanding component (if time permits).
At Naver Labs Europe you will interact with researchers working in the latest developments of machine learning, information retrieval and natural language processing, apply them to our data using our GPU cluster . We regularly publish in top conferences, release data-sets and otherwise interact with our academic collaborators.
- be enrolled in a graduate program, at the Master or PhD level, with a focus on Information Retrieval or Speech Processing
- strong mathematical and programming skills
- autonomous, proactive and highly motivated.