Seminar: Big Data and NLP at Trivago (Min Fang, 2016-06-08)

Kepa Sarasola — Tue, 07 Jun 2016 11:50:29 +0000

Talk: Big Data and NLP at Trivago

Speaker: Min Fang

………..2013 – 2015: Master Erasmus Mundus Language and Communication Technologies, summa cum laude

………..2015-… : (Trivago, hotel metasearch)

When: Wed, 8 June, 10pm – 11pm

Where: Faculty of informatics, room 3.2 gelan map

Abstract:

I’m interested in getting insights from data by applying natural language processing, machine learning and statistical analyses. Ideally, those insights can then be turned into useful applications or facilitate higher level decisions.

Together with our software engineers I take care of our NLP capabilities: We work on improving and maintaining a highly flexible and scalable pipeline that is geared towards aspect-based sentiment analysis (and more in the future). Extracting knowledge from a large number of natural language texts allows us to understand our domain better and enhance the experience for our users.

Our technology stack includes:
– Python and Java
– R for analysis
– AWS for infrastructure

NewsReader Project winner of the 4th edition of the Enlighten Your Research (EYR4) competition

Kepa Sarasola — Fri, 08 Nov 2013 08:58:08 +0000

NewsReader project, in which IXA Group is a partner, won the 4th edition of the Enlighten Your Research (EYR4) competition with his proposal ’Recording history in large news streams‘, using big data in analyzing large news streams.

CONGRATULATIONS to German, Aitor, Eneko, Itziar, Egoitz, Piek and to all researchers in NewsReader!

4th edition of the Enlighten Your Research (EYR4)

Jury quote: ’This proposal pushes the boundaries of the available infrastructure using an innovative way of analysing big data streams. A new way of dealing with the news.’

“Every day thousands of news articles are published, presenting new events or providing updates to events reported earlier. With current technology it is impossible to keep track of the vast amount of information coming in daily. The purpose of this project is to develop the optimal architecture capable of processing as many daily news items as fast as possible, utilizing the most advanced semantic processing techniques available in Natural Language Processing (NLP) today. One of the main challenges in this project lies in scaling up existing linguistic processing to maximize the usage of available computational resources in order to manage the daily stream of incoming information. The resulting infrastructure will provide the basis to build a ‘history recorder’ that follows the news, stores it and can automatically relate new events to events that took place in the past. It will provide the complete story line to decision makers, pointing out forgotten details and possibly even finding new links between current situations and historic events”.

Big data – Ixa Group. Language Technology.

Seminar: Big Data and NLP at Trivago (Min Fang, 2016-06-08)

NewsReader Project winner of the 4th edition of the Enlighten Your Research (EYR4) competition