FieldWorks is a suite of software tools for language and cultural data, with support for complex scripts.

Mining Argument Structures with Expressive Inference (Linear and LSTM Engines)

Extension of the SentenceSimplification project

An annotated corpus of discussion forum threads from Massive Open Online Courses.

Attention mechanism in CNNs to extract events of interest

End-to-end shallow discourse parser

A collection of various discourse segmenters

Sense Disambiguation of Connectives for PDTB-Style Discourse Parsing

Mining Discourse Markers for Unsupervised Sentence Representation Learning

Supplementary materials and replication data for: Ehret, Katharina and Maite Taboada (2020). The interplay of complexity and subjectivity in opinionated discourse. (version 1.0)

Taking a corpus of text-based documents, we can now run doc2vec, kmeans clustering, and topic models to learn about entire discourses in just a few minutes. This gives valuable insight into the information present in a discourse from a high level using deep learning

Retrieves and distributes Discourse forum stats

Rezonator: Dynamics of human engagement

The RST-LSTM module refines predictions of the sequential text classifier (BERT) on documents with complex discourse

rst-workbench enables the hassle-free installation of RST parsers. It lets you visually compare their results in your browser.

FieldWorks help files and training material

Discourse

Measure the civility of posts on your Discourse forum using Google Perspective API

Heuristic-guided learning using Uncertainty-aware Self-training with Uncertainty Sampled Training (UST).

A web app for a German climate change glossary