The Language and Retrieval group focuses on bringing the right information to the right people, in the right context, and presenting it in the right way. We do this under the umbrella of IBM Research AI and for IBM Watson products. Our expertise combines natural language processing (NLP), natural language generation (NLG) and information retrieval (IR).
The technology behind these solutions stems first from the well-established computer science discipline of information retrieval (IR), which focuses on the representation, storage, organization, and retrieval of unstructured data, and specifically textual content.
In the Language area we wish to help users consume information in the right context. We do this by analyzing user behavior, for example, using emotions in conversations. We also consider transformations to the information by changing the tone or the emotion conveyed, or through simplification and compression. Another domain of our focus is content summarization, in particular selecting specific parts based on user interests and queries.
The problems we solve are central to AI, and are geared towards enhancing human intelligence and expertise.
Our work covers both long-term theoretical research, and shorter-term collaboration with product groups and IBM customers. The group's members actively participate in the academic community, publishing papers in leading conferences and journals, participating in program committees, and organizing workshops, tutorials and panels.