[CaCL] Reading for 1/26

[Clark, Christian]

Hi CaCL members,

For our meeting on Thursday, we will read "Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars" by Yang et al. (2022).

Link: https://arxiv.org/pdf/2212.09140.pdf

Abstract:
We study grammar induction with mildly context-sensitive grammars for unsupervised discontinuous parsing. Using the probabilistic linear context-free rewriting system (LCFRS) formalism, our approach fixes the rule structure in advance and focuses on parameter learning with maximum likelihood. To reduce the computational complexity of both parsing and parameter estimation, we restrict the grammar formalism to LCFRS-2 (i.e., binary LCFRS with fan-out two) and further discard rules that require O(n6) time to parse, reducing inference to O(n5). We find that using a large number of nonterminals is beneficial and thus make use of tensor decomposition-based rank-space dynamic programming with an embedding-based parameterization of rule probabilities to scale up the number of nonterminals. Experiments on German and Dutch show that our approach is able to induce linguistically meaningful trees with continuous and discontinuous structures.

----
Christian Clark
Ph.D. Student
Department of Linguistics
The Ohio State University
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osu.edu/pipermail/cacl/attachments/20230121/8d835846/attachment.html>