Classification of telicity using cross-linguistic annotation projection

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2559–2565 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Classification of telicity using cross-linguistic annotation projection Annemarie Friedrich1 Damyana Gateva2 1Center for Information and Language Processing, LMU Munich 2Department of Computational Linguistics, Saarland University anne@cis.uni-muenchen.de dgateva@coli.uni-saarland.de Abstract This paper addresses the automatic recog- nition of telicity, an aspectual notion. A telic event includes a natural endpoint (she walked home), while an atelic event does not (she walked around). Recognizing this difference is a prerequisite for temporal natural language understanding. In En- glish, this classification task is difficult, as telicity is a covert linguistic category. In contrast, in Slavic languages, aspect is part of a verb’s meaning and even available in machine-readable dictionaries. Our con- tributions are as follows. We successfully leverage additional silver standard train- ing data in the form of projected annota- tions from parallel English-Czech data as well as context information, improving au- tomatic telicity classification for English significantly compared to previous work. We also create a new data set of English texts manually annotated with telicity. 1 Introduction This paper addresses the computational modeling of telicity, a linguistic feature which represents whether the event type evoked by a sentence’s verb constellation (i.e., the verb and its arguments and modifiers) has a natural endpoint or not (Comrie, 1976; Smith, 1997), see (1a) and (1b). (1) (a) Mary ate an apple. (telic) (b) I gazed at the sunset. (atelic) Automatic recognition of telicity is a neces- sary step for natural language understanding tasks that require reasoning about time, e.g., natural language generation, summarization, question an- swering, information extraction or machine trans- lation (Moens and Steedman, 1988; Siegel and McKeown, 2000). For example, there is an en- tailment relation between English Progressive and Perfect constructions (as shown in (2)), but only for atelic verb constellations. (2) (a) He was swimming in the lake. (atelic) |= He has swum in the lake. (b) He was swimming across the lake. (telic) ̸|= He has swum across the lake. We model telicity at the word-sense level, cor- responding to the fundamental aspectual class of Siegel and McKeown (2000), i.e., we take into ac- count the verb and its arguments and modifiers, but no additional aspectual markers (such as the Progressive). In (2) we classify whether the event types “swim in the lake” and “swim across the lake” have natural endpoints. This is defined on a linguistic level rather than by world knowledge requiring inference. “Swimming in the lake” has no natural endpoint, as also shown by the linguis- tic test presented in (2). In contrast, “swimming across the lake” will necessarily be finished once the other side is reached. In English, the aspectual notion of telicity is a covert category, i.e., a semantic distinction that is not expressed overtly by lexical or morphological means. As illustrated by (2) and (3), the same verb type (lemma) can introduce telic and atelic events to the discourse depending on the context …

Content truncated to 500 words