“…In order to tackle this issue, recent work relies on the supervision-lighter framework of multilingual probabilistic topic modeling (MuPTM) (Mimno, Wallach, Naradowsky, Smith, & McCallum, 2009;Boyd-Graber & Blei, 2009;De Smet & Moens, 2009;Ni, Sun, Hu, & Chen, 2009;Zhang, Mei, & Zhai, 2010;Fukumasu, Eguchi, & Xing, 2012) or other similar models for latent structure induction (Haghighi, Liang, Berg-Kirkpatrick, & Klein, 2008;Daumé III & Jagarlamudi, 2011).…”