This work highlights a new application of unsupervised grammar induction and demonstrates several approaches to SRL in the absence of supervised syntax.

To better understand the effect of the low-resource grammars and features used in these models, we further include comparisons with (1) models that use higher-resource versions of the same features; (2) state-of-the-art high resource models; and (3) previous work on low-resource grammar induction .

0 New application of unsupervised grammar induction : low-resource SRL.

o Constrained grammar induction using SRL for distant-supervision.

Our work builds upon research in both semantic role labeling and unsupervised grammar induction (Klein and Manning, 2004; Spitkovsky et a1., 2010a).

There has not yet been a comparison of techniques for SRL that do not rely on a syntactic treebank, and no exploration of probabilistic models for unsupervised grammar induction within an SRL pipeline that we have been able to find.

Train Time, Constrained Grammar Induction : Observed Constraints

A key feature of this approach is that grammar induction is driven by the extended domain of locality principle of TAG (Tree Adjoining Grammar); and that it takes into account both syntactic and semantic information.

We compare the results obtained with those obtained by two other systems participating in the KBGen challenge, namely the UDEL system, a symbolic rule based system developed by a group of students at the University of Delaware; and the IMS system, a statistical system using a probabilistic grammar induced from the training data.

A key feature of this approach is that grammar induction is driven by the extended domain of locality principle of TAG (Tree Adjoining Grammar) and takes into account both syntactic and semantic information.

They induce a probabilistic Tree Adjoining Grammar from a training set aligning frames and sentences using the grammar induction technique of (Chiang, 2000) and use a beam search that uses weighted features learned from the training data to rank alternative expansions at each step.

We use a simple mainly symbolic approach whereas they use a generative approach for grammar induction and a discriminative approach for sentence generation.

We report the first steps of a novel investigation into how a grammar induction algorithm can be modified and used to identify salient information structures in a corpus.

Thus, we propose to use a grammar induction algorithm to identify the most salient information structures in a corpus and take these as representations of important semantic content.

the use of grammar induction to elucidate semantic content for text mining purposes shows promise.

Here we report our first attempt to apply grammar induction to text mining.

Our approach is to induce information structures from an unannotated corpus by modifying and applying the ADIOS grammar induction algorithm (Solan et al., 2005): the modifications serve to focus the algorithm on what is typically written about key-terms (Section 3).

“PGI” is the phylogenetic grammar induction model of Berg-Kirkpatrick and Klein (2010).

This led to a vast amount of research on unsupervised grammar induction (Carroll and Chamiak, 1992; Klein and Manning, 2004; Smith and Eisner, 2005; Cohen and Smith, 2009; Spitkovsky et al., 2010; Blun-som and Cohn, 2010; Marecek and Straka, 2013; Spitkovsky et al., 2013), which appears to be a natural solution to this problem, as unsupervised methods require only unannotated text for training parsers.

Unfortunately, the unsupervised grammar induction systems’ parsing accuracies often significantly fall behind those of supervised systems (McDonald et al., 2011).