Aspectuality Across Genre: A Distributional Semantics Approach

Proceedings of the 28th International Conference on Computational Linguistics, pages 4546–4562 Barcelona, Spain (Online), December 8-13, 2020 4546 Aspectuality Across Genre: A Distributional Semantics Approach Thomas Kober Rasa t.kober@rasa.com Malihe Alikhani University of Pittsburgh malihe@pitt.edu Matthew Stone Rutgers University mdstone@rutgers.edu Mark Steedman University of Edinburgh steedman@inf.ed.ac.uk Abstract The interpretation of the lexical aspect of verbs in English plays a crucial role for recognizing textual entailment and learning discourse-level inferences. We show that two elementary dimen- sions of aspectual class, states vs. events, and telic vs. atelic events, can be modelled effectively with distributional semantics. We find that a verb’s local context is most indicative of its aspectual class, and demonstrate that closed class words tend to be stronger discriminating contexts than content words. Our approach outperforms previous work on three datasets. Lastly, we contribute a dataset of human–human conversations annotated with lexical aspect and present experiments that show the correlation of telicity with genre and discourse goals. 1 Introduction One of the fascinating aspects of studying aspectual class of verbs in English is its relation with non- verbal categories. Thus, although in origin a property of the verb, the aspectual class interacts in a tight-knit fashion with other words in a sentence. Previous research has discussed the importance of predicting the aspectual classes of verbs for predicting coherence relations in text and imagery (Alikhani and Stone, 2019), predicting links in entailment graphs (Hosseini et al., 2019) and interpreting sign languages (Wilbur, 2003). In addition, knowledge about the aspectual class of a verb phrase, and its influence on the temporal extent and entailments that it licenses, has been leveraged in the past for a number of natural language understanding tasks such as temporal relation extraction (Costa and Branco, 2012), event ordering (Chambers et al., 2014; Modi and Titov, 2014), and statistical machine transla- tion (Lo´aiciga and Grisot, 2016). The Aktionsart (Vendler, 1957) of a verb determines the temporal extent of the predication as well as whether it causes a change of state for the entities involved (Filip, 2012). As Aktionsart typically refers to the lexical aspect of a verb in isolation, we adopt the terminology of Verkuyl (2005), and refer to the compositionally formed Aktionsart of a verb phrase as predicational aspect. One of the most important distinctions of the predicational aspect of a verb is between states, such as to know or to love, and events, such as visit or swim. This distinction is important for identifying the entailments that a given verb phrase licenses, as stative predications do not, by definition, entail any change of state. This property has important consequences for a number of natural language understand- ing tasks such as question answering. For example, if it is known that John has arrived in Vienna, a system leveraging aspectual information will be able to infer that the completion of the event of arriving in Vienna, indicated by the perfect VP having arrived in, has caused a change of state which entails being in. Therefore, when asked Where is …

Content truncated to 500 words