In this paper, we present a novel method for the computation of compositionality within a distributional framework. The key idea is that compositionality is modeled as a multi-way interaction between latent factors, which are automatically constructed from corpus data. We use our method to model the composition of subject verb object triples. The method consists of two steps. First, we compute ...

This paper presents experimental work on the relative naturalness of subject-oriented reflexives (herself) and pronouns (her) in English locative prepositional phrases (e.g., Michele set a glass next to her/herself). Syntactic approaches anaphor licensing have tended focus lack complementarity such constructions; however, it has long been observed that preferences between forms may depend verb ...

In this paper we describe some ways to utilize various lexical resources to improve the quality of statistical machine translation system. We have augmented the training corpus with various lexical resources such as IndoWordnet semantic relation set, function words, kridanta pairs and verb phrases etc. Our research on the usage of lexical resources mainly focused on two ways such as augmenting ...

Lack of proper linguistic resources is the major challenges faced by the Machine Translation system developments when dealing with the resource poor languages. In this paper, we describe effective ways to utilize the lexical resources to improve the quality of statistical machine translation. Our research on the usage of lexical resources mainly focused on two ways, such as; augmenting the para...

In this paper, we present our work on the creation of lexical resources for the Machine Translation between English and Hindi. We describes the development of phrase pair mappings for our experiments and the comparative performance evaluation between different trained models on top of the baseline Statistical Machine Translation system. We focused on augmenting the parallel corpus with more voc...

The Chinese negation marker bu ‘not’ is analyzed as a clitic-like element in the literature (Huang 1988; Ernst 1995; etc.) in order to explain why it cannot co-occur with (i) the perfective marker -le or (ii) manner phrases in the V-de construction. Huang (1988) assumes that bu must cliticize onto auxiliaries/modals or the following verb, and since bu cliticizing directly to a verb induces a ‘‘...

The constant growth of digital information, facilitated by storage technologies, imposes new challenges for information processing tasks, and maintains the need of effective search mechanisms, oriented towards improving in precision but simultaneously capable of producing useful information in a short time. Hence, this paper presents a document representation to encode textual relations. This r...

“karbala’s epic” was composed in 222 odes and more than 6000 verses by “saeed al osaili” (1929 - 1994), the contemporary lebanese poet. accounting to the life of imam hussain (as) from birth to death, this epic contains, tender affection, fluent words and phrases and appropriate rhythm. this paper is seeking to study the literary elements of  karbala’s epic and analyze the affection of the poet...

The paper shows that catena representation together with valence information can provide a good way of encoding Multiword Expressions (beyond idioms). It also discusses a strategy for mapping noun/verb compounds with their counterpart syntactic phrases. The data on Multiword Expression comes from BulTreeBank, while the data on compounds comes from a morphological dictionary of Bulgarian.