Grounded Unsupervised Semantic Parsing | arrivaLt ime ). |
Grounded Unsupervised Semantic Parsing | departure_t ime or ticket price fare . |
Grounded Unsupervised Semantic Parsing | departure_t ime , and so the node state P : flight . |
Introduction | (O’Donovan et al., 2005; Schulte im Walde, 2006; Erk, 2007; Preiss et al., 2007; Van de Cruys, 2009; Reisinger and Mooney, 2011; Sun and Korhonen, 2011; Lippincott et al., 2012). |
Introduction | Schulte im Walde et al. |
Previous Work | K—means and spectral) algorithms (Schulte im Walde, 2006; Joanis et al., 2008; Sun et al., 2008; Li and Brew, 2008; Korhonen et al., 2008; Sun and Korhonen, 2009; Vlachos et al., 2009; Sun and Korhonen, 2011). |
Previous Work | Finally, the model of Schulte im Walde et a1. |
Methodology | 0 Character 3-gram: Cka+1Ck+2(i — 3 < k< i+m |
Methodology | o Ime ;n(i—4 < m < n < z’+4,0 < nm < 5) matches one entry in the Peking University dictionary: |
Methodology | o (*) Ime ;n(i—4 < m < n < z’+4,0 < n — m < 5) matches one entry in the informal word list: |
Conclusion | SVM-DA: and um Im not sure about the buttons being in the shape of fruit though. |
Introduction | A: and um I’m not sure about the buttons being in the shape of fruit though. |
Introduction | D: Um like I’m just thinking bright colours. |
Conclusion | This work was funded by the DFG Research Project Distributional Approaches to Semantic Relatedness (Marion Weller), the DFG Heisenberg Fellowship SCHU-25 80/ 1-1 (Sabine Schulte im Walde), as well as by the Deutsche Forschungsge-meinschaft grant Models of Morphosyntax for Statistical Machine Translation (Alexander Fraser). |
Experiments and evaluation | (2013); the newspaper data (HGC - Huge German Corpus) was parsed with Schmid (2000), and subcategorization information was extracted as described in Schulte im Walde (2002b). |
Using subcategorization information | Briscoe and Carroll (1997) for English; Sarkar and Zeman (2000) for Czech; Schulte im Walde (2002a) for German; Messiant (2008) for French. |