Hand-built verb clusters such as the widely used Levin classes (Levin, 1993) have proved useful, but have limited coverage. Verb classes automatically induced from corpus data such as those from VerbKB (Wijaya, 2016), on the other hand, can give clusters with much larger coverage, and can be adapted to specific corpora such as Twitter. We present a method for clustering the outputs of VerbKB: v...

In his comprehensive and succinct overview of passives in the world’s languages, Edward Keenan (1985) makes the following typological observations. First, not all languages have passives; and second, such passive-less languages commonly use one of the following grammaticized means to express functional equivalents of passive: (a) to use the “impersonal” third person plural subject; or (b) to el...

This paper describes an extension to the MOSAIC model which aims to increase MOSAIC’s fit to the cross-linguistic occurrence of Optional Infinitive (OI) errors. While previous versions of MOSAIC have successfully simulated these errors as truncated compound finites with missing modals or auxiliaries, they have tended to underestimate the rate of OI errors in (some) obligatory subject languages....

Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement learning is specifying a reward function for the agent to optimize. Traditionally, imitation learning in RL has been used to overcome this problem. Unfortunately, hitherto imitation learning methods tend to require that d...

The computational implementation of a linguistic theory of the representation and projection of grammatical features in nominals is described. The processing of nominals is part of a larger model of language comprehension implemented as a computational cognitive model within the ACT-R cognitive architecture. The model combines a serial, pseudo-deterministic processing mechanism for building lin...