Factorising AMR generation through syntax
- π€ Speaker: Kris Cao, DeepMind
- π Date & Time: Friday 10 May 2019, 12:00 - 13:00
- π Venue: FW26, Computer Laboratory
Abstract
Generating from Abstract Meaning Representation (AMR) is an underspecified problem, as many syntactic decisions are not constrained by the semantic graph. To explicitly account for this underspecification, we break down generating from AMR into two steps: first generate a syntactic structure, and then generate the surface form. We show that decomposing the generation process this way leads to state-of-the-art single model performance generating from AMR without additional unlabelled data. We also demonstrate that we can generate meaning-preserving syntactic paraphrases of the same AMR graph, as judged by humans.
Series This talk is part of the NLIP Seminar Series series.
Included in Lists
- All Talks (aka the CURE list)
- bld31
- Cambridge Centre for Data-Driven Discovery (C2D3)
- Cambridge Forum of Science and Humanities
- Cambridge Language Sciences
- Cambridge talks
- Chris Davis' list
- Computer Education Research
- Computing Education Research
- Department of Computer Science and Technology talks and seminars
- FW26, Computer Laboratory
- Graduate-Seminars
- Guy Emerson's list
- Interested Talks
- Language Sciences for Graduate Students
- ndk22's list
- NLIP Seminar Series
- ob366-ai4er
- PMRFPS's
- rp587
- School of Technology
- Simon Baker's List
- Trust & Technology Initiative - interesting events
- yk449
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)

Kris Cao, DeepMind
Friday 10 May 2019, 12:00-13:00