Language understanding and misunderstanding

Michael Roth (Universität Stuttgart)

Abstract When we use language, we usually assume that the meaning of our statements is clear and that others can understand precisely this meaning. However, that this may not always be the case is for example demonstrated by vague statements in polit [mehr…]

When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it

Sebastian Schuster (Universität des Saarlandes)

Understanding longer narratives or participating in conversations requires tracking of discourse entities that have been mentioned. Indefinite noun phrases (NPs), such as ‘a dog’, frequently introduce discourse entities but this behavior is modulated [mehr…]

Caring about data before it was cool – language data between computational linguistics and real-world applications

Alessandra Zarcone (Hochschule Augsburg)

Computational linguists have cared about data “before it was cool”. In the community of ML/AI practitioners, however, “model work” gets more love than the “data work”. Small and medium business, while not immune to the AI hype, often (1) do not have [mehr…]

Five sources of bias in NLP — and what to do about them

Dirk Hovy (Bocconi University, Milan)

Natural Language Processing is one of the core areas of artificial intelligence. Currently, the majority of the research efforts in this area are mostly opting for better performance on major benchmarks and downstream tasks. However, it is vital to a [mehr…]

What about em?

Anne Lauscher (Bocconi University, Milan)

This is the second part of a two-part talk, in which Dr. Anne Lauscher will discuss their latest research centering around the current modeling of 3rd person pronouns in NLP as a concrete example. Biography Anne Lauscher is a postdoctoral researche [mehr…]

Challenges on social NLP Dataset Annotation

Seid Muhie Yimam (University of Hamburg)

The development of natural language processing and AI applications require a gold standard dataset. Data is the pillar of those intelligent applications, and an annotation is a way to acquire it. In this talk, I will first discuss the main components [mehr…]

The statistical analysis of cooccurrences: From collocations to arbitrary structures

Thomas Proisl (FAU Erlangen-Nürnberg)

The study of cooccurrences, i. e. the analysis of linguistic units that occur together, has had a profound impact on our view of language. In this talk, I will discuss how we can generalize established methods for the statistical analysis of two-word [mehr…]

Computational Models of Abstractness and Figurative Language

Sabine Schulte im Walde (Universität Stuttgart)

The distinction between abstract and concrete words (such as “dream” in contrast to “banana”) is considered a highly relevant semantic categorisation for Natural Language Processing purposes. For example, previous studies have identified distribution [mehr…]

Compositional semantic parsing

Alexander Koller (Universität des Saarlandes)

There are many technical approaches to mapping natural-language sentences to symbolic meaning representations. The current dominant approach is with neural sequence-to-sequence models which map the sentence to a string version of the meaning represen [mehr…]

The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation.

Richard Eckart de Castilho (TU Darmstadt)

Let the computer actively help you to enrich your texts with annotations and to link your texts to knowledge bases – this is what the INCEpTION text annotation platform helps you with. No matter if you work alone or in a team or if you want to provi [mehr…]

Text Annotation

Annemarie Friedrich (Bosch Center for Artificial Intelligence)

Important: If you are new to text annotation, this tutorial is a great preparation for our tutorial about the INCEpTION platform! This tutorial guides you through the steps for manual annotation with the aim of text corpus construction for machine l [mehr…]

Overcoming Data Sparsity in Machine Translation

Alexander Fraser (Ludwig-Maximilians-Universität München)

Data-driven Machine Translation is an interesting application of machine-learning-based natural language processing techniques to multilingual data. Particularly with the recent advent of powerful neural network models, it has become possible to inco [mehr…]

Weakly supervised machine learning for text analysis

Benjamin Roth (University of Vienna)

Deep learning relies on massive training sets of labeled examples to learn from – often tens of thousands to millions to reach peak predictive performance. However, large amounts of training data are only available for very few standardized learning [mehr…]

Rule Induction and Reasoning over Knowledge Graphs

Daria Stepanova (Bosch Center for Artificial Intelligence)

Advances in information extraction have enabled the automatic construction of large knowledge graphs (KGs) like DBpedia, Freebase, YAGO and Wikidata. Learning rules from KGs is a crucial task for KG completion, cleaning and curation. This tutorial pr [mehr…]

When Speech Enhancement Turned Neural – an Overview of Recent Trends

Friedrich Faubel (Cerence Inc.)

This talk will take you on a journey into the world of speech enhancement, a realm that exists only to separate an acoustic target speech signal from noise, interfering speech or music. While classical approaches were typically quite heavy on the mat [mehr…]

Dialogue and Robots for Understanding Understanding

Casey Redd Kennington (Boise State University)

Hallmarks of intelligence include the ability to acquire, represent, understand, and produce natural language. Although recent efforts in data-driven, machine learning, and deep learning methods have advanced natural language processing applications, [mehr…]