The Natural Language Processing and Information Retrieval Group (NLP-IR) conducts cutting-edge research on man-machine interactions through natural language, as well as the extraction of meaning from text and other media sources.

Natural language understanding has captivated human imagination throughout generations. A central issue is how to discover and connect various meaningful concepts from human-generated content, such as text, speech and media. A key objective is to resolve the inherent ambiguities in natural languages. This research is tightly linked to statistical machine learning so that new natural language input can be smoothly incorporated into our current knowledge.

Research topics include, but are not limited to:

• Discourse and dialogue.
• Information retrieval and extraction from large-scale text sources.
• Semantics, lexicon and ontology development.
• Machine translation.
• Multimodal representation and processing.
• Social media related issues.
• Query resolution.
• Sentiment analysis and opinion mining.
• Summarization and generation.
• Syntax and parsing.
• Text classification, dimensionality analysis, and clustering.