What is it? Disambiguating the different readings of the pronoun ‘it’

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1325–1331 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics What is it? Disambiguating the different readings of the pronoun ‘it’ Sharid Lo´aiciga Uppsala University Dept. of Linguistics & Philology Uppsala, Sweden sharid.loaiciga@lingfil.uu.se Liane Guillou University of Edinburgh School of Informatics Scotland, United Kingdom lguillou@inf.ed.ac.uk Christian Hardmeier Uppsala University Dept. of Linguistics & Philology Uppsala, Sweden christian.hardmeier@lingfil.uu.se Abstract In this paper, we address the problem of predicting one of three functions for the English pronoun ‘it’: anaphoric, event ref- erence or pleonastic. This disambigua- tion is valuable in the context of machine translation and coreference resolution. We present experiments using a MAXENT classifier trained on gold-standard data and self-training experiments of an RNN trained on silver-standard data, annotated using the MAXENT classifier. Lastly, we report on an analysis of the strengths of these two models. 1 Introduction We address the problem of disambiguating the English pronoun ‘it’, which may function as a pleonastic, anaphoric, or event reference pronoun. As an anaphoric pronoun, ‘it’ corefers with a noun phrase (called the antecedent), as in example (1): (1) I have a bicycle. It is red. Pleonastic pronouns, in contrast, do not refer to anything but are required to fill the subject position in many languages, including English, French and German: (2) It is raining. Event reference pronouns are anaphoric, but in- stead of referring to a noun phrase, they refer to a verb, verb phrase, clause or even an entire sen- tence, as in example (3): (3) He lost his job. It came as a total surprise. We propose the identification of the three usage types of it, namely anaphoric, event reference, and pleonastic, with a single system. We present sev- eral classification experiments which rely on infor- mation from the current and previous sentences, as well as on the output of external tools. 2 Related Work Due to its difficulty, proposals for the identifi- cation and the subsequent resolution of abstract anaphora (i.e., event reference) are scarce (Eckert and Strube, 2000; Byron, 2002; Navarretta, 2004; M¨uller, 2007). The automatic detection of in- stances of pleonastic ‘it’, on the other hand, has been addressed by the non-referential ‘it’ detec- tor NADA (Bergsma and Yarowsky, 2011), and also in the context of several coreference resolu- tion systems, including the Stanford sieve-based coreference resolution system (Lee et al., 2011). The coreference resolution task focuses on the resolution of nominal anaphoric pronouns, de facto grouping our event and pleonastic categories together and discarding both of them. The coref- erence resolution task can be seen as a two-step problem: mention identification followed by an- tecedent identification. Identifying instances of pleonastic ‘it’ typically takes place in the men- tion identification step. The recognition of event reference ‘it’ is, however, to our knowledge not currently included in any such systems, although from a linguistic point of view, event instances are also referential (Boyd et al., 2005). As suggested by Lee et al., (2016), it …

Content truncated to 500 words