Comparing HMMs and Bayesian Networks for Surface Realisation

2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 636–640, Montr´eal, Canada, June 3-8, 2012. c⃝2012 Association for Computational Linguistics Comparing HMMs and Bayesian Networks for Surface Realisation Nina Dethlefs Heriot-Watt University Edinburgh, Scotland n.s.dethlefs@hw.ac.uk Heriberto Cuay´ahuitl German Research Centre for Artificial Intelligence Saarbr¨ucken, Germany heriberto.cuayahuitl@dfki.de Abstract Natural Language Generation (NLG) systems often use a pipeline architecture for sequen- tial decision making. Recent studies how- ever have shown that treating NLG decisions jointly rather than in isolation can improve the overall performance of systems. We present a joint learning framework based on Hierar- chical Reinforcement Learning (HRL) which uses graphical models for surface realisation. Our focus will be on a comparison of Bayesian Networks and HMMs in terms of user satis- faction and naturalness. While the former per- form best in isolation, the latter present a scal- able alternative within joint systems. 1 Introduction NLG systems have traditionally used a pipeline ar- chitecture which divides the generation process into three distinct stages. Content selection chooses ‘what to say’ and constructs a semantic form. Ut- terance planning organises the message into sub- messages and surface realisation maps the seman- tics onto words. Recently, a number of studies have pointed out that many decisions made at these distinct stages require interrelated, rather than iso- lated, optimisations (Angeli et al., 2010; Lemon, 2011; Cuay´ahuitl and Dethlefs, 2011a; Dethlefs and Cuay´ahuitl, 2011a). The key feature of a joint archi- tecture is that decisions of all three NLG stages share information and can be made in an interrelated fash- ion. We present a joint NLG framework based on Hierarchical RL and focus, in particular, on the sur- face realisation component of joint NLG systems. We compare the user satisfaction and naturalness of surface realisation using Hidden Markov Models (HMMs) and Bayesian Networks (BNs) which both have been suggested as generation spaces—spaces of surface form variants for a semantic concept— within joint NLG systems (Dethlefs and Cuay´ahuitl, 2011a; Dethlefs and Cuay´ahuitl, 2011b) and in iso- lation (Georgila et al., 2002; Mairesse et al., 2010). 2 Surface Realisation for Situated NLG We address the generation of navigation instruc- tions, where e.g. the semantic form (path(target = end of corridor) ∧ (landmark = lift ∧ dir = left)) can be expressed as ‘Go to the end of the corridor’, ‘Head to the end of the corridor past the lift on your left’ and many more. The best realisa- tion depends on the space (types and properties of spatial objects), the user (position, orientation, prior knowledge) and decisions of content selection and utterance planning. These can be interrelated with surface realisation, for example: (1) ‘Follow this corridor and go past the lift on your left. Then turn right at the junction.’ (2) ’Pass the lift and turn right at the junction.’ Here, (1) is appropriate for a user unfamiliar with the space and a high information need, so that more in- formation should be given. For a familiar user, how- ever, …

Content truncated to 500 words