Unsupervised Grammar Induction with Depth-bounded PCFG. Jin, L., Schuler, W., Doshi-Velez, F., Miller, T., A., & Schwartz, L. Transactions of the Association for Computational Linguistics (TACL), 2018.
Unsupervised Grammar Induction with Depth-bounded PCFG [link]Website  abstract   bibtex   
There has been recent interest in applying cognitively or empirically motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016). This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchic sequence models, and therefore more fully exploits the space reductions of depth-bounding. Results for this model on grammar acquisition from transcribed child-directed speech exceed those of other models when evaluated on parse accuracy. Moreover, grammars acquired from this model demonstrate a consistent use of category labels, something which has not been demonstrated by other acquisition models.
@article{
 title = {Unsupervised Grammar Induction with Depth-bounded PCFG},
 type = {article},
 year = {2018},
 websites = {https://github.com/lifengjin/db-pcfg},
 id = {ab8a36a2-c477-3584-8bfe-4994095f8d21},
 created = {2018-01-07T19:31:31.144Z},
 file_attached = {false},
 profile_id = {51f2e139-307e-3ab5-a624-9fe1e6e8d1a8},
 last_modified = {2018-09-14T03:54:22.111Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Jin2018},
 folder_uuids = {08b123d6-904c-4e7a-a8b1-21a19f2d735d},
 private_publication = {false},
 abstract = {There has been recent interest in applying cognitively or empirically motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016). This work extends this depth-bounding approach to probabilistic context-free grammar induction (DB-PCFG), which has a smaller parameter space than hierarchic sequence models, and therefore more fully exploits the space reductions of depth-bounding. Results for this model on grammar acquisition from transcribed child-directed speech exceed those of other models when evaluated on parse accuracy. Moreover, grammars acquired from this model demonstrate a consistent use of category labels, something which has not been demonstrated by other acquisition models.},
 bibtype = {article},
 author = {Jin, Lifeng and Schuler, William and Doshi-Velez, Finale and Miller, Timothy A and Schwartz, Lane},
 journal = {Transactions of the Association for Computational Linguistics (TACL)}
}

Downloads: 0