Abstract | We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations . |
Conclusions | Although in this work we focused primarily on improving performance for each individual language, crosslingual semantic representation could be extracted by a simple postprocessing step. |
Inference | 5This has been explored before for shallow semantic representations (Lang and Lapata, 2011a; Titov and Klementiev, 201 1). |
Introduction | The goal of this work is to show that parallel data is useful in unsupervised induction of shallow semantic representations . |
Introduction | Though syntactic representations are often predictive of semantic roles (Levin, 1993), the interface between syntactic and semantic representations is far from trivial. |
Related Work | However, most of this research has focused on induction of syntactic structures (Kuhn, 2004; Snyder et al., 2009) or morphologic analysis (Snyder and Barzilay, 2008) and we are not aware of any previous work on induction of semantic representations in the crosslingual setting. |
Related Work | Learning of semantic representations in the context of monolingual weakly-parallel data was studied in Titov and Kozhevnikov (2010) but their setting was semi-supervised and they experimented only on a restricted domain. |
Related Work | Semi-supervised and weakly-supervised techniques have also been explored for other types of semantic representations but these studies again have mostly focused on restricted domains (Kate and Mooney, 2007; Liang et al., 2009; Goldwasser et al., 2011; Liang et al., 2011). |
Experiment and Results | The surface realisation algorithm extends the algorithm proposed in (Gardent and Perez—Beltrachini, 2010) and adapts it to work on the SR dependency input rather than on flat semantic representations . |
Related Work | Typically, the input to surface realisation is a structured representation (i.e., a flat semantic representation , a first order logic formula or a dependency tree) rather than a string. |
Related Work | Approaches based on reversible grammars (Carroll et al., 1999) have used the semantic formulae output by parsing to evaluate the coverage and performance of their realiser; similarly, (Gardent et al., 2010) developed a tool called GenSem which traverses the grammar to produce flat semantic representations and thereby provide a benchmark for performance and coverage evaluation. |