Untitled

Japanese Zero Anaphora Resolution Can Benefit from Parallel Texts Through Neural Transfer Learning

“…With neural transfer learning, we successfully revived the old idea that Japanese ZAR can benefit from parallel texts (Nakaiwa, 1999). Thanks to the astonishing flexibility of neural networks, we would probably be able to connect ZAR to other tasks through transfer learning.…”

“…Our use of parallel texts in ZAR is inspired by Nakaiwa (1999) andFurukawa et al (2017), who identify a multi-hop link from a Japanese zero pronoun to its Japanese antecedent via English counterparts. Their rule-based methods suffer from accumulated errors and syntactically non-transparent correspondences.…”

“…Previous attempts to overcome this limitation exploit orders-of-magnitude larger parallel texts of Japanese and English, a non-pro-drop language (Nakaiwa, 1999;Furukawa et al, 2017). The key idea is that Japanese zero pronouns can be recovered from parallel texts because they are usually mentioned explicitly in English, as in Figure 1(b).…”

The Review of Discourse-Based Machine Translation Evaluation

“…The 1990s saw an intensification of research efforts aimed at endowing RMT-translated texts with the same document and discourse properties as their source texts (Webber, 2014). This included work on stylistics (Dimarco and Mah, 1994), discourse relations (Mitkov, 1993) and referring forms (Wada, 1990) (Bond and Ogura, 1998) and pronoun translation (Chan and T'sou, 1999) (Ferrández et al, 1999) (Nakaiwa, 1999). Discourse was widely investigated and demonstrated promising results in different aspects including language modelling (Foster et al, 2010), discourse connectives (Meyer and Poláková, 2013) (Meyer and Webber, 2013), lexical cohesion (Xiong et al, 2013), anaphora resolution (Le Nagard and Koehn, 2010) (Taira et al, 2012) and topic adaption (Su et al, 2012) (Hasler et al, 2014) in SMT development and researches.…”