LING 573 - Natural Language Processing Systems and Applications
Spring 2016
Software

NLP Toolkits and Collections

• NLTK: An extensive suite of Natural Language Processing components, written in Python.
• GATE: A large-scale NLP framework integrating many components.
• LingPipe: a highly professional suite of NLP tools, with Java API as well as batch components.
• Stanford NLP Suite: Suite of mostly Java NLP tools
• Stanford NLP links: Collection of links to diverse NLP tools
• UIUC software tools: Includes chunkers, NE Taggers, SRL, coref, etc

Corpora

• A Repository of Machine Summaries for Generic News Summarization on DUC 2004, Hong & Nenkova, LREC 2014
• New York Times Annotated corpus: On cluster at: /corpora/LDC/LDC08T19

Sentence Splitters

• NIST splitter: Used in summarization evaluations

POS Taggers

• Stanford POS Tagger: Java tagger
• MaxEnt POS Tagger
• Brill Tagger
• TreeTagger: Probabilistic decision tree POS tagger

Stemmers

• Porter stemmers implemented in a variety of languages

Parsers

Constituency Parsers

• Stanford Parser
• ACL Wiki links to parsers
• Charniak Parser

Dependency Parser

• Stanford Dependencies
• MALT parser
• MST parser

Semantic Analyzer and Shallow Semantic Parsers

• Shalmaneser
• Illinois Semantic Role Labeller
• Semafor: Dipanjan Das's semantic role labeling system

Discourse (RST) Parsers

• Feng & Hirst, 2014 - Toronto
• Document-level Discourse Parser
• NUS PTDB-style discourse parser (Lin et al., 2014)

Word Sense Disambiguation

• WordNet::Similarity and other WSD tools

Machine Learning Toolkits

• Mallet
• Weka Broad Java machine learning toolkit
• scikit-learn (Python machine learning toolkit)
• LibSVM

• WordNet
• FrameNet
• PropBank
• Abstract Meaning Representations (AMR)