Introduction and Hands-on of the Open-Source NLP Framework Flair

Dies ist ein vergangenes Event

150 Personen haben teilgenommen

BMW IT-Zentrum (ITZ)

Bremer Str. 6 · München

Wie du uns findest

This time we will meet at the BMW IT-Centre at Bremer Strasse 6. Please enter the building through the main entrance and approach the registration desk right after the entrance. You will get a badge there to proceed to the conference center.

Bild des Veranstaltungsortes


Hi everyone,

we are very pleased to invite you to the forth NLP Meetup where we will hear two interesting presentations plus a super interesting hands-on experience learning about the state-of-the-art NLP framework Flair.

Please bring your laptop. A project maintainer and mentors will be around to support you :).

=== Agenda ===

18:00 - Welcome reception
18:30 - [Introduction] Agenda and Introduction
18:35 - [Presentation, incl. Q&A] Industrial NLP: Bridging Knowledge Graphs and Deep Learning for Industrial Applications
19:10 - [Presentation, incl. Q&A] Introduction of Flair
19:25 - [Break] Networking and refreshment
19:45 - [Project Working Groups] Participants join up with a project of their interest and start to work on challenges, project maintainers /mentors will be around to provide support
21:45 - Event ends

=== FIRST Presentation ===

• Dr. Ulli Waltinger: Siemens AG

• Topic: Industrial NLP: Bridging Knowledge Graphs and Deep Learning for Industrial Applications

Today’s enterprises make decisions on data – utilizing insights from structured and natural language knowledge repositories. Turning massive and heterogeneous data sources into tangible knowledge, by means of enabling human to understand it, requires turning strings into things and connecting these concepts by their semantic representations, represented as graphical structures of knowledge, such as industrial knowledge graphs. The (semi-) automated task of knowledge extraction and graph construction involves various NLP task, from named entity recognition and resolution, relation extraction and link prediction, to building trust in Industrial system. In this talk, I will review various industrial applications that leverage and set NLP at the core of its application, from Industrial-scale question answering for semi-structured knowledge graphs, Service-, IP- and Market Intelligence, to Deep Learning-based Knowledge Graph construction, from application, architecture, and methodology perspective.

• Bio:
Ulli Waltinger is the Head of the Machine Intelligence Research Group and the Founder and Technology-Head of the Siemens AI Lab at Siemens Corporate Technology, Siemens’ global research organization. Prior he worked at the AI department and the Center of Excellence of Cognitive Interaction Technology at the University of Bielefeld. He is specifically interested in methods that bridge the areas of connectionism and symbolic models applied to real-world AI and NLP applications.

=== SECOND Presentation ===

• Alan Akbik: Zalando Research

• Topic: Flair: A Natural Language Processing framework by Zalando Research (plus Hands-on session in working groups)

Flair is a very simple framework for state-of-the-art NLP developed by Zalando Research:

- A powerful NLP library. Flair allows you to apply our state-of-the-art NLP models to your text, such as named entity recognition (NER), part-of-speech tagging (PoS), sense disambiguation and classification.
- Multilingual. Thanks to the Flair community, we support a rapidly growing number of languages. We also now include 'one model, many languages' taggers, i.e. single models predicting PoS or NER tags in various languages.
- A text embedding library. Flair has simple interfaces that allow you to use and combine different word and document embeddings, including our proposed Flair embeddings, BERT embeddings and ELMo embeddings.
- A Pytorch NLP framework. Our framework builds directly on Pytorch, making it easy to train your own models.

• Bio:
Alan is a senior research scientist at Zalando Research, researching deep learning technologies for advanced text analytics capabilities over large-scale multilingual text data. Before this, Alan was a researcher at IBM Research Almaden in San Jose and research associate at the TU Berlin. His research lies at the intersection of natural language processing (NLP) and information extraction (IE), with a particular focus on multilingual data and models of crosslingual semantics.