Existing research on sentiment analysis mainly uses sentiment words and phrases to determine sentiments expressed in documents and sentences. Techniques have also been developed to find such words and phrases using dictionaries and domain corpora. However, there are still other types of words and phrases that do not bear sentiments on their own, but when they appear in some particular contexts,...

It is noticed that i n natural speech sentences are breaked into breath groups. Some words seem to be more closely grouped with adjacent words: we call these groups prosodic phrases. In order to improve the naturalness of synthesized speech, prosodic processing in both text-processing component and speech generation component is needed. The text-processing component is more important because th...

Disclosure control of natural language information (DCNL), which we are trying to realize, is described. DCNL will be used for securing human communications over the internet, such as through blogs and social network services. Before sentences in the communications are disclosed, they are checked by DCNL and any phrases that could reveal sensitive information are transformed or omitted so that ...

In this paper I discuss the grammatical properties of container phrases in Yudja (Tupi; Brazil). I show that container phrases are syntactically indistinguishable from locative phrases. Based on two experimental studies with Yudja children and adults, I address two questions about the interpretation of container phrases. First, given that container constructions are identical to locative constr...

This study aims to describe the form of politeness in novel Geez And Ann by Rintik Sedu. research is a qualitative using document analysis method. Data collection techniques. used content sourced from and words, phrases, sentences. The results indicate that use language often done because speech participants already know try show their attention with sympathy.

Globalization and multilingualism contribute to code-switching – the phenomenon in which speakers produce utterances containing words or expressions from a second language. Processing code-switched sentences is a significant challenge for multilingual intelligent systems. This study proposes a language modeling approach to the problem of codeswitching language processing, dividing the problem i...

Parts of Speech Tagger (POS) is the task of assigning to each word of a text the proper POS tag in its context of appearance in sentences. The Chunking is the process of identifying and assigning different types of phrases in sentences. In this paper, a statistical approach with the Hidden Markov Model following the Viterbi algorithm is described. The corpus both tagged and untagged used for tr...

This paper describes a system for finding phrasal translation correspondences from parallel parsed corpus that are collections paired English and Japanese sentences. First, the system finds phrasal correspondences by Japanese-English translation dictionary consultation. Then, the system finds correspondences in remaining phrases by using sentences dependency structures and the balance of all co...

This paper explains the automatic semantic interpretation of sentences. These sentences were selected for testing the verb predicates that we have been defining for WordNet 1.6 verb classes, and the algorithm that uses them. Semantic interpretation is performed for determining the meaning of the verb, or, verb predicate, its semantic roles, adjuncts, the attachment of postverbal prepositional p...

This paper presents an approach that enables automatic titling of e-mails relying on the morphosyntactic study of real titles. Automatic titling of e-mails has two interests: Titling mails ’no object’ and managing personal information. The method is developed in three stages: Candidate sentences determination for titling, noun phrases extraction in the candidate sentences, and finally, selectin...