|
Research talk: Is phrase retrieval all we need
Speaker: Danqi Chen, Assistant Professor, Princeton University DensePhrases is an extractive phrasesearch tool based on natural language input that achieves dense retrieval of billionscale phrases with extreme runtime efficiency. In this talk, Assistant Professor Danqi Chen of Princeton University will highlight some of the technical challenges that she and her research team encountered and the solutions of learning dense representations of phrases at scale. Shell demonstrate the strong performance on opendomain QA and slotfilling tasks, and shell show how phrase retrieval, the most finegrained retrieval unit, can also be used for passage or document retrieval tasks. Finally, shell cover how phrase filtering and vector quantization can make the phrase index much smaller, making dense phrase retrieval a practical and versatile solution in multigranularity retrieval. Learn more about the 2021 Microsoft Research Summit:
|
|
