Using Universal Linguistic Knowledge to Guide Grammar Induction

By Tahira Naseem, Harr Chen, Regina Barzilay, Mark Johnson. 2010

149 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Variational Inference: A Review for Statisticians (2016, methodology): “…has been used for solving problems such as parsing (Liang et al. 2007; Liang, Jordan, and Klein 2009), grammar induction (Kurihara and Sato 2006; Naseem et al. 2010; Cohen and Smith 2010), models of streaming text (Yogatama et al. 2014), topic modeling (Blei, Ng, and Jordan 2003), and hidden…”
Learning Structured Embeddings of Knowledge Bases (2011, background): “Most work of this kind regards natural language processing (NLP), either to improve word-sense disambiguation (McRoy 1992), co-reference resolution (Ng and Cardie 2002) (using WordNet) or grammar induction (Naseem et al. 2010) (using a small base of linguistic knowledge).”
Mapping to Declarative Knowledge for Word Problem Solving (2017, background): “…recent approaches tried to incorporate knowledge in the form of constraints or expectations from the output (Roth and tau Yih, 2004; wei Chang et al., 2007; Chang et al., 2012; Ganchev et al., 2010; Smith and Eisner, 2006; Naseem et al., 2010; Bisk and Hockenmaier, 2012; Gimpel and Bansal, 2014).”
Distributed Word Representation Learning for Cross-Lingual Dependency Parsing (2014, methodology): “The linguistic constraints may either come from manually constructed universal dependency parsing rules (Naseem et al., 2010) or manually speciﬁed typological features (Naseem et al., 2012), or be learned from parallel sentences (Ganchev et al., 2009).”
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features (2014, background): “The NLP community has developed a range of statistical algorithms for building unsupervised parsers (Klein and Manning 2002, 2004; Smith 2006; Blunsom and Cohn 2010; Naseem et al. 2010; Spitkovsky, Alshawi, and Jurafsky 2010; Cohen 2011).”
Unsupervised Recurrent Neural Network Grammars (2019, background): “However Li et al. (2019) ﬁnd that it is possible use a transition-based parser as the inference network for dependency grammar induction, if the inference network is constrained via posterior regularization (Ganchev et al., 2010) based on universal syntactic rules (Naseem et al., 2010).”
A Universal Part-of-Speech Tagset (2011, methodology): “ent treebanks to evaluate POS tagging accuracy on a single tagset. Second, we combine the cross-lingual projection part-of-speech taggers of Das and Petrov (2011) with the grammar induction system of Naseem et al. (2010) – which requires a universal tagset – to produce a completely unsupervised gram”
Learning Syntax from Naturally-Occurring Bracketings (2021, background): “…Klein, 2005) along with carefully designed inductive biases on parameter priors (Liang et al., 2007; Wang and Blunsom, 2013), language universals (Naseem et al., 2010; Martínez Alonso et al., 2017), cross-linguistic (Snyder et al., 2009; BergKirkpatrick and Klein, 2010; Cohen and Smith, 2009;…”
Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections (2011, background): “Syntactic universals are a well studied concept in linguistics (Carnie, 2002; Newmeyer, 2005), and were recently used in similar form by Naseem et al. (2010) for multilingual grammar induction.”