Speaker: Danqi Chen, Assistant Professor, Princeton University
DensePhrases is an extractive phrase-search tool based on natural language input that achieves dense retrieval of billion-scale 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. She’ll demonstrate the strong performance on open-domain QA and slot-filling tasks, and she’ll show how phrase retrieval, the most fine-grained retrieval unit, can also be used for passage or document retrieval tasks. Finally, she’ll cover how phrase filtering and vector quantization can make the phrase index much smaller, making dense phrase retrieval a practical and versatile solution in multi-granularity retrieval.
Learn more about the 2021 Microsoft Research Summit:
9 views
21
5
1 month ago 01:25:57 1
Praveen Mohan On Dark Truth Of Indian Temples, Secrets Of Pyramid & More | The Ranveer Show 270
2 months ago 03:46:53 1
Gypsy Rose’s TikTok Hacked Is Fake IMO. The Signs Are All There - Blake Lively Astroturfing Lawsuit
2 months ago 00:03:43 1
Utilization of Prefabricated Vertical Drains (PVDs) in Railway Embankment Construction on Soft Soil
2 months ago 00:16:04 1
How Immigrants Shape(d) the United States | Nalini Krishnankutty | TEDxPSU
3 months ago 00:08:38 1
Can Curiosity Heal Division? | Scott Shigeoka | TED
3 months ago 00:00:32 1
…but the people are retarded
4 months ago 01:04:12 1
Depravity of Power: USA & Co Trying To KILL International Law | Dr. Binoy Kampmark
4 months ago 00:11:44 1
Apple CEO’s High Stake Visit To China For Apology & Request To Market Share
4 months ago 00:39:26 1
Bob Laramee - Visualizing the Signal From the Noise: Keynote Talk for the ICINC 2024 Conference