Evaluation of natural language processing tools and systems must focus on two complementary aspects: first, evaluation of the accuracy of the output, and second, evaluation of the functionality of the output as embedded in an application. This paper presents evaluations of two aspects of LinkIT, a tool for noun phrase identification linking, sorting and filtering. LinkIT [Evans 1998] uses a hea...

Comparatively little is known about how semantic properties (such as animacy) and syntactic properties (such as word order) affect production of complex sentences. Relative clauses were elicited using a picture description task that manipulated head noun animacy in both English (which has head-first relative clauses and Japanese (head-final relative clauses). Participants of both languages prod...

Very often, the data we study as linguists are discrete in nature. That is, the linguistic elements we study come in different categories and, trivially, if two elements are labeled the same, they belong to the same category, and if they are labeled differently, they belong to different categories. In statistical approaches, this kind of scenario is usually described with the terminology of var...

Using the eye-tracking method, the present study depicted pre- and post-head processing for simple scrambled sentences of head-final languages. Three versions of simple Japanese active sentences with ditransitive verbs were used: namely, (1) SO₁O₂V canonical, (2) SO₂O₁V single-scrambled, and (3) O₁O₂SV double-scrambled order. First pass reading times indicated that the third noun phrase just be...

This paper offers a new LFG analysis of possessive DPs in Hungarian. This account is designed to overcome two difficulties that the majority of previous generative approaches had to face: (a) the problem of the (a)symmetrical cohead relationship between the noun head and the possessive marker (b) the problem of dual theta role assignment in GB (or its LFG equivalent) when the noun head is relat...

Motivated by recent advances in the area of Compositional Distributional Semantic Models (CDSMs), we propose a compositional approach for estimating continuous affective ratings for adjective-noun (AN) and noun-noun (NN) pairs. The ratings are computed for the three basic dimensions of continuous affective spaces, namely, valence, arousal and dominance. We propose that similarly to the semantic...

In general, English gerunds such as (We were talking about) John having a sabbatical combine the internal characteristics of a clause with the external characteristics of a noun phrase. Previous analyses have tried to recognise the mixed character of gerunds by assigning them two separate nodes, one verbal and the other nominal, but all such analyses are problematic. This paper proposes an anal...

Compound words are integral to the development of word knowledge in English. This study explored cross-linguistic similarities and differences compound-meaning inference, focusing on semantic relation between modifier head noun-noun compounds. Semantic specifies how meanings combined. Although some less-established compounds allow multiple relation, causing ambiguity meaning, L1 speakers Englis...

English noun phrases can be categorized into simple and complex phrases. Whether or not a phrase is complex, it seen from the structure of that has pre-modification, head, post-modification its complementation. However, when translated Indonesian, shifts happen. In translations, there are two types shifts. They level category This research aimed at finding out in novel entitled Ugly Love their ...