Title: Semantic Alignment at Various Context Sizes

Speaker: Dr. Yeon Seonwoo, Applied Scientist @ Amazon

Time : 2022 Nov 8th 14:00 ~ 15:00

Location: Hybrid

- In-person: 26421

- Online:  https://us02web.zoom.us/j/85894805725 ( Passcode 1108)

Language: Korean (speech), English (slides)

After the talk, we will have an informal Q&A session with Dr. Yeon Seonwoo. Please leave any questions about your research or career.

Abstract: 

Semantic matching has been a core task in many NLP fields, such as machine reading comprehension (MRC), document retrieval, and semantic textual similarity. However, this task has been defined differently in each field depending on the text sources' complexity and scale. In this talk, I will introduce 1) how semantic matching has been defined in each NLP sub-field, 2) what problems have occurred, and 3) how these problems have been alleviated. I will first talk about a weakly supervised method that enhances the context prediction performance of MRC models. Then, I will talk about a weakly supervised multi-hop document retriever that correctly predicts a combination of documents that semantically aligns with a given question. Finally, I will talk about an unsupervised sentence embedding method that leverages a corpus-level context to alleviate the imprecise sentence embedding problem in semantic textual similarity.

Bio:

Yeon Seonwoo is an applied scientist at Amazon. He was an intern at Amazon Alexa and Adobe Research. He received his Ph.D. degree in Computer Science from KAIST, where he was advised by Alice Oh. His primary research interests are question answering, document retrieval, and sentence representation learning. He received his M.S degree in Computer Science from KAIST.