Members of the Stanford NLP Group pursue research in a broad variety of topics:

Computational Semantics

• Extraction of meaning representations from text, ranging from shallow representations like named entities and thematic roles, to deep structures like quantification in logic and rich event structures. Research topics include:

  • Coreference Resolution
  • Natural Logic and Inference
  • Narratives and Event Representations
  • Detecting Contradictions in Text
  • Semantic Taxonomy Induction
  • Named Entity Recognition (NER) and Information Extraction (IE)

NLP applied to social meaning and the social sciences

• We are interested in using natural language processing to understand large-scale social phenomena, including intellectual history, the spread of ideas and innovations, and the nature of citation networks, as well as topics in the extraction of social meaning from text and speech.

  • Mimir Project: What Drives the Dynamics of Science
  • Extraction of Sentiment and Social Meaning from Text and Speech

Deep Learning in Natural Language Processing

• Algorithms that tackle various problems in natural language processing such as parsing, sentiment analysis or paraphrase detection. The methods that we explore are general in nature and can also be applied to vision problems.

  • Deep Learning in Natural Language Processing

Parsing & Tagging

• Algorithms for assigning part of speech and syntactic structure, emphasizing probabilistic and discriminative models. Research topics include:

  • Probabilistic Parsing

Machine Translation

• Language modeling, re-ordering models, phrase extraction techniques, syntactic methods, and better training for statistical machine translation:

  • Machine Translation

Dialog and Speech Processing

• Research in dialog modeling and speech processing

  • Dialog Modeling
  • Speech Recognition and Synthesis

Unsupervised and Semisupervised Learning of Linguistic Structure

• Probabilistic and other corpus-based algorithms for learning linguistic structures from corpora. Research topics include:

  • Unsupervised Parsing & Grammar Induction
  • Time Expressions
  • Morphology & Phonology Induction
  • Semantic Taxonomy Induction
  • Inducing Narratives and Event Representations

Multilingual NLP

• A variety of NLP investigations in Chinese, Arabic, and German, including tagging, segmentation, probabilistic syntactic parsing, and semantic role parsing, as well as work on speech processing. Research topics include:

  • Chinese NLP and Speech
  • Arabic NLP
  • German NLP

Past Work

• A number of projects have been worked on by members of the NLP group, but are no longer being actively developed. These include:

  • Personalized PageRank algorithms
  • Computational Lexicography: Kirrkirr
  • Text Categorization
  • The Stanford Edinburgh Entity Recognition (SEER) Project
  • The Edinburgh And Stanford Information Extraction (EASIE) Project
  • Shallow Semantic Parsing
  • Question Answering (QA)
  • Knowledge Representation from Text
    • The NLKR Project: solving natural-language logic puzzles
  • Word Sense Disambiguation (WSD)
  • Part-of-speech (POS) tagging

Links

Other groups at Stanford doing NLP-related research:

Other links: