Word-finding difficulty (anomia) is the most common linguistic deficit in dementia. It is often measured by picture naming tasks as naming a picture taps all the major processes in word production, i.e., activation of a concept, retrieval of lexical-semantic information on that concept, retrieval of the corresponding word form and articulation. Naming and naming errors have extensively been sim...

1.1 Introduction This paper proposes the lexicalization of context in HPSG. Instead of phrasal amalgamation of contextual information from a phrase's daughters , which is speciied by the Principle of Contextual Consistency of Pollard and Sag 1994, we propose lexical amalgamation of context from a word's arguments by means of lexical constraints. The Principle of Contextual Consistency is replac...

We present an ILP model of concept-totext generation. Unlike pipeline architectures, our model jointly considers the choices in content selection, lexicalization, and aggregation to avoid greedy decisions and produce more compact texts.

Elicited production data from English, French and Japanese children reveal that predicates of ‘traversal’ (e.g. across, through) present a particular lexicalization difficulty in the early stages of acquisition, regardless of expression in verbs or adpositions. Adult-like lexicalization patterns are consistently produced only by 6 or 7 years old. In all three languages, children circumvent the ...

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...

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...