scholarly journals Backward-Forward Sequence Generative Network for Multiple Lexical Constraints

Author(s):  
Seemab Latif ◽  
Sarmad Bashir ◽  
Mir Muntasar Ali Agha ◽  
Rabia Latif
JURNAL ELINK ◽  
2016 ◽  
Vol 4 (2) ◽  
Author(s):  
Diah Astuty

his study aims to describe the sorts of lexical constraints that appeared on the students translation when translating some source language texts into some target language texts. The competence of linguistic fields that the students have acquired is in the fact assumed to be inadequate and it can cause the lexical constraints.Keywords: CALLS, lexical constraints,source language text,target language text


1997 ◽  
Vol 24 (3) ◽  
pp. 737-765 ◽  
Author(s):  
TASSOS STEVENS ◽  
ANNETTE KARMILOFF-SMITH

Williams syndrome (WS), a rare neurodevelopmental disorder, is of special interest to developmental psycholinguists because of its uneven linguistico-cognitive profile of abilities and deficits. One proficiency manifest in WS adolescents and adults is an unusually large vocabulary despite serious deficits in other domains. In this paper, rather than focus on vocabulary size, we explore the processes underlying vocabulary acquisition, i.e. how new words are learned. A WS group was compared to groups of normal MA-matched controls in the range 3–9 years in four different experiments testing for constraints on word learning. We show that in construing the meaning of new words, normal children at all ages display fast mapping and abide by the constraints tested: mutual exclusivity, whole object and taxonomic. By contrast, while the WS group showed fast mapping and the mutual exclusivity constraint, they did not abide by the whole object or taxonomic constraints. This suggests that measuring only the size of WS vocabulary can distort conclusions about the normalcy of WS language. Our study shows that despite equivalent behaviour (i.e. vocabulary test age), the processes underlying how vocabulary is acquired in WS follow a somewhat different path from that of normal children and that the atypically developing brain is not necessarily a window on normal development.


Author(s):  
Mary Dalrymple ◽  
John J. Lowe ◽  
Louise Mycock

This chapter explores the syntax and semantics of functional and anaphoric control, constructions in which either syntactic or lexical constraints require coreference between an argument of the matrix clause (the controller) and an argument of a subordinate or modifying adjunct clause (the controllee). Such cases include the classes of “raising” verbs (Section 15.2) and “equi” verbs (Section 15.4). Crosslinguistically, descriptions of such constructions involve reference to functional syntactic relations such as subject and object; therefore, the syntactic discussion in this chapter is primarily centered around the f-structures of functional and anaphoric control constructions. A detailed semantic analyses of functional and anaphoric control constructions is also presented, considering arbitrary, obligatory, and quasi-obligatory (partial) control relations, and a discussion of the syntax and semantics of control in adjuncts (Section 15.8).


1996 ◽  
Vol 10 (3) ◽  
pp. 207-223 ◽  
Author(s):  
M. Koopmans ◽  
I. Slis ◽  
T. Rietveld
Keyword(s):  

1978 ◽  
Vol 46 (3) ◽  
pp. 979-983
Author(s):  
Michael Gamble

Temporal interactions among opponent and non-opponent hues were investigated in a visual masking paradigm in which both backward and forward temporal sequences were employed. Subjective confidence ratings rather than identification thresholds alone served as response indicators for masking sequences. Results indicate that in the backward sequence (test stimulus followed by masking stimulus) a greater masking effect occurred when the stimuli were of non-opponent hue pairs (red-yellow, red-blue, green-yellow, green-blue) than when compared with opponent hue pairs (red-green, yellow-blue). For the forward sequence (test stimulus preceded by masking stimulus) the masking effect was reduced when compared with the backward sequence. These findings appear to reflect the presumed temporal and spatial antagonistic qualities of opponent hue processes as postulated in the Hering model of color vision.


Author(s):  
Bernd Bohnet ◽  
Joakim Nivre ◽  
Igor Boguslavsky ◽  
Richárd Farkas ◽  
Filip Ginter ◽  
...  

Joint morphological and syntactic analysis has been proposed as a way of improving parsing accuracy for richly inflected languages. Starting from a transition-based model for joint part-of-speech tagging and dependency parsing, we explore different ways of integrating morphological features into the model. We also investigate the use of rule-based morphological analyzers to provide hard or soft lexical constraints and the use of word clusters to tackle the sparsity of lexical features. Evaluation on five morphologically rich languages (Czech, Finnish, German, Hungarian, and Russian) shows consistent improvements in both morphological and syntactic accuracy for joint prediction over a pipeline model, with further improvements thanks to lexical constraints and word clusters. The final results improve the state of the art in dependency parsing for all languages.


Sign in / Sign up

Export Citation Format

Share Document