Thursday, 8th September 2022 - 10am - Chris Welty: Seminar Title: Addressing Label Sparsity With Class-Level Common Sense Abstract: The vast majority of business problems are prevented from deploying machine learning solutions due to label sparsity -- the lack of labeled data to train large models. This major problem is overshadowed by continued successes in problems that, often, naturally have a lot of data (for example, Netflix has millions of examples of what movies people watch). At Google, we recently launched a new enhancement to search that allows product and dish queries, such as "Milk", "12 string guitar", or "spaghetti bolognese" to return local results - places on maps, nearby, that sell the product or serve the dish. The problem had remained unsolved at Google for more than 10 years because of label sparsity: 70% of stores and restaurants worldwide - and 40% in the US - do not have a web page, Google's primary data source for search. To overcome this challenge and extend our understanding of small-medium sized brick & mortar shops and restaurants, we used a unique combination of Knowledge Graphs, AI and Human Common Sense [1][2], that demonstrates both the promises and limitations of AI in solving practical business problems. Bio: Dr. Chris Welty is a Sr. Research Scientist at Google in New York. His main area of interest is the interaction between structured knowledge (e.g. knowledge graphs such as freebase), unstructured knowledge (e.g. natural language text), and human knowledge (e.g. crowdsourcing). His latest work focuses on understanding the continuous nature of truth in the presence of a diversity of perspectives, and he has been working with the google maps team to better understand user contributions that often disagree. He is most active in the Crowdsourcing and Human Computation community, as well as The Web Conf, AKBC, Information and Knowledge Management, and AAAI. His first project at Google was launched as Explore in Google Docs, and then on improving the quality and expanding the coverage of price level labels on maps using user signals. Before Google, Dr. Welty was a member of the technical leadership team for IBM's Watson - the question answering computer that defeated the all-time best Jeopardy! champions in a widely televised contest. He appeared on the broadcast, discussing the technology behind Watson, as well as many articles in the popular and scientific press. His proudest moment was being interviewed for StarTrek.com about the project. He is a recipient of the AAAI Feigenbaum Prize for his work. [1] https://ojs.aaai.org/index.php/HCOMP/article/view/18947 [2] https://www.frontiersin.org/articles/10.3389/frai.2022.830299/full Add to your calendar vCal iCal Sep 08 2022 10.00 - 11.00 Thursday, 8th September 2022 - 10am - Chris Welty: Seminar This event is co-organised by ILCC, SIGKG (Special Interest Graph of Knowledge Graph) and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk G.03, Informatics Forum Contact
Thursday, 8th September 2022 - 10am - Chris Welty: Seminar Title: Addressing Label Sparsity With Class-Level Common Sense Abstract: The vast majority of business problems are prevented from deploying machine learning solutions due to label sparsity -- the lack of labeled data to train large models. This major problem is overshadowed by continued successes in problems that, often, naturally have a lot of data (for example, Netflix has millions of examples of what movies people watch). At Google, we recently launched a new enhancement to search that allows product and dish queries, such as "Milk", "12 string guitar", or "spaghetti bolognese" to return local results - places on maps, nearby, that sell the product or serve the dish. The problem had remained unsolved at Google for more than 10 years because of label sparsity: 70% of stores and restaurants worldwide - and 40% in the US - do not have a web page, Google's primary data source for search. To overcome this challenge and extend our understanding of small-medium sized brick & mortar shops and restaurants, we used a unique combination of Knowledge Graphs, AI and Human Common Sense [1][2], that demonstrates both the promises and limitations of AI in solving practical business problems. Bio: Dr. Chris Welty is a Sr. Research Scientist at Google in New York. His main area of interest is the interaction between structured knowledge (e.g. knowledge graphs such as freebase), unstructured knowledge (e.g. natural language text), and human knowledge (e.g. crowdsourcing). His latest work focuses on understanding the continuous nature of truth in the presence of a diversity of perspectives, and he has been working with the google maps team to better understand user contributions that often disagree. He is most active in the Crowdsourcing and Human Computation community, as well as The Web Conf, AKBC, Information and Knowledge Management, and AAAI. His first project at Google was launched as Explore in Google Docs, and then on improving the quality and expanding the coverage of price level labels on maps using user signals. Before Google, Dr. Welty was a member of the technical leadership team for IBM's Watson - the question answering computer that defeated the all-time best Jeopardy! champions in a widely televised contest. He appeared on the broadcast, discussing the technology behind Watson, as well as many articles in the popular and scientific press. His proudest moment was being interviewed for StarTrek.com about the project. He is a recipient of the AAAI Feigenbaum Prize for his work. [1] https://ojs.aaai.org/index.php/HCOMP/article/view/18947 [2] https://www.frontiersin.org/articles/10.3389/frai.2022.830299/full Add to your calendar vCal iCal Sep 08 2022 10.00 - 11.00 Thursday, 8th September 2022 - 10am - Chris Welty: Seminar This event is co-organised by ILCC, SIGKG (Special Interest Graph of Knowledge Graph) and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk G.03, Informatics Forum Contact
Sep 08 2022 10.00 - 11.00 Thursday, 8th September 2022 - 10am - Chris Welty: Seminar This event is co-organised by ILCC, SIGKG (Special Interest Graph of Knowledge Graph) and by the UKRI Centre for Doctoral Training in Natural Language Processing, https://nlp-cdt.ac.uk
