Abstract Talmy’s motion event typology (Talmy, Leonard. 2000 . Towards a cognitive semantics: Conceptual structuring systems , vol. 2. Cambridge, MA: The MIT Press) has served as an influential framework for exploring representation across languages. While confirming its basic premises, many studies argued that the cannot fully capture vast intra- and inter-typological variations. Consequently,...

In this squib we explore a strictly derivational explanation for the differences in possible middle voice constructions in Norwegian and Swedish. Whereas Norwegian allows by its lexical s-passive construction as well as a complex adjectival construction to stand in for middle semantics, only the latter option is available in Swedish. We argue that this contrast lies in the lexicalization of for...

There is a widespread belief among linguists that a predicate's subcategorization frames are largely determined by its lexical-semantic properties [23, 11, 12]. Consider the domain of movement verbs. Following Talmy [23], these can he semantically classified with reference to the meaning components: MOTION, MANNER, CAUSATION, THEME (MOVING ENTITY), PATH AND REFERENCE LOCATIONS (GOAL, SOURCE). L...

Bilingual annotators were paid to link roughly sixteen thousand corresponding words between on-line versions of the Bible in modern French and modern English. These annotations are freely available to the research community from http://www.cis.upenn.edu/~melamed. The annotations can be used for several purposes. First, they can be used as a standard data set for developing and testing translati...

Sequential LSTM has been extended to model tree structures, giving competitive results for a number of tasks. Existing methods model constituent trees by bottom-up combinations of constituent nodes, making direct use of input word information only for leaf nodes. This is different from sequential LSTMs, which contain reference to input words for each node. In this paper, we propose a method for...

We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically uncommon words. Our approach examines the distribution of transitions, selects the uncommon words, and makes lexicalized states for the words. We performed a part-of-speech tagging experiment on the Brown corpus to evaluate the resultant language model and discovered...

Sequential LSTMs have been extended to model tree structures, giving competitive results for a number of tasks. Existing methods model constituent trees by bottom-up combinations of constituent nodes, making direct use of input word information only for leaf nodes. This is different from sequential LSTMs, which contain references to input words for each node. In this paper, we propose a method ...

Previous work on German parsing has provided confusing and conflicting results concerning the difficulty of the task and whether techniques that are useful for English, such as lexicalization, are effective for German. This paper aims to provide some understanding and solid baseline numbers for the task. We examine the performance of three techniques on three treebanks (Negra, Tiger, and TüBa-D...