This week at MCQLL (Wednesday 1:20-2:30), Emily Goodwin will present her ongoing work on systematic syntactic parsing. Abstract and bio are below. If you would like to join the mailing list and/or attend the meeting, please fill out this google form (as soon as possible).
ABSTRACT:
Recent work in semantic parsing, including novel datasets like SCAN (Lake and Baroni, 2018) and CFQ (Keysers et al., 2020) demonstrate that semantic parsers generalize well when tested on items highly similar to those in the training set, but struggle with syntactic structures that combine components of training items in novel ways. This indicates a lack of systematicity , the principle that individual words will make similar contributions to the expressions they appear in, independently of surrounding context. Applying this principle to syntactic parsing, we show similar problems plague state of the art syntactic parsers, despite achieving human or near-human performance on randomly sampled test data. Moreover, generalization is especially poor on syntactic relations which are crucial for the compositional semantics.
BIO:
Emily is an M.A. Student in the McGill linguistics department, supervised by Profs. Timothy J. O’Donnell and Siva Reddy, and by Dzmitry Bahdanau of ElementAI. She is interested in compositionality and systematic generalization in meaning representation.