Generating flexible proper name references in text: Data, models and evaluation

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 655–664, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics Generating flexible proper name references in text: Data, models and evaluation Thiago Castro Ferreira and Emiel Krahmer and Sander Wubben Tilburg center for Cognition and Communication (TiCC) Tilburg University The Netherlands {tcastrof,e.j.krahmer,s.wubben}@tilburguniversity.edu Abstract This study introduces a statistical model able to generate variations of a proper name by taking into account the person to be mentioned, the discourse context and variation. The model relies on the REGnames corpus, a dataset with 53,102 proper name references to 1,000 people in different discourse contexts. We eval- uate the versions of our model from the perspective of how human writers produce proper names, and also how human read- ers process them. The corpus1 and the model2 are publicly available. 1 Introduction In automatic text generation, Referring Expression Generation (REG) is the task responsible for gen- erating references to discourse entities, address- ing, for example, the question whether the text should refer to an entity using a definite descrip- tion (the West Coast poet and patron saint of drinking writers), a pronoun (he) or a proper name (Henry Charles Bukowski). REG is among the tasks which have received most attention in text generation (see Krahmer and van Deemter (2012), for a survey), but the vast majority of the research has concentrated on the generation of descriptions, while proper name generation has received virtu- ally no attention, albeit with notable exceptions (Siddharthan et al., 2011; van Deemter, 2016) to which we return below. Still, proper names occur frequently in texts. For instance, Ferreira et al. (2016a) showed that human writers use proper names in 91% of the cases to initially refer to persons. Indeed, some 1http://ilk.uvt.nl/˜tcastrof/regnames/ 2http://github.com/ThiagoCF05/ ProperName earlier research on text generation has stated that discourse-new references should be generated by using the strategy to “simply give the name of the object (if it has a name)” (Reiter and Dale, 2000). However, the Bukowski example already indicates that this is not as straightforward as Re- iter and Dale suggest - the poet’s full name is Henry Charles Bukowski and his birth name is Heinrich Karl Bukowski, but he is more commonly known as simply Charles Bukowski; see also van Deemter (2016), for a discussion of this and other complicating factors in proper name generation. In addition, Reiter and Dale (2000) do not ad- dress how repeated references using a name in a text should be generated. For instance, should our discourse-old example-writer be referred to as Charles, Bukowski or some combination of these and other attributes (e.g., using a modifier like the poet Bukowski)? Imagine, for the sake of argument, that we would generate proper name references in a text by initially generating the full name, after which repeated references only consist of the last name (a.k.a. the family or surname). Intuitively, it is not difficult to come up with counterexam- ples to …

Content truncated to 500 words