What's Wrong With My NLP? is visualizer and graphical diff for natural language processing problems. It can display syntactic and semantic dependencies and bilingual alignments as well as all types of chunk information such as NP, NER, or SRL chunks. It also allows you to compare your system output to a gold standard in order to find the mistakes your system makes. There are numerous ways to filter the graph and only display what is needed. It is also possible to search a corpus for sentences with certain properties using Lucene search expressions.
|Tags||Scientific/Engineering Artificial Intelligence|
|Operating Systems||OS Independent|
Release Notes: This version allows you to provide additional information about edges and spans in your predictions. For example, for first order dependency parsing models, you can show feature vectors associated with false positive or negative edges. This can be a very helpful feature when debugging probabilistic models of language. The release also contains minor bugfixes for loading data.
Release Notes: This release fixed a bug regarding the loading of UTF-8 files and a bug with reading tab files that contain square brackets.
Release Notes: This version fixes a bug that caused the file loading progress monitor to remain open after the data had been completely loaded.
Release Notes: This version supports the data format of the BioNLP 2009 Shared Task and jointly displays proteins, cites, events, their arguments, and event clues. Moreover, version 0.2.0 is now built with maven.
Release Notes: This is an alpha version that enables users to also visualize bilingual alignments. Under the hood, the code has been refactored to completely support different renders for different file formats.