Topic
Phrase
About: Phrase is a research topic. Over the lifetime, 12580 publications have been published within this topic receiving 317823 citations. The topic is also known as: syntagma & phrases.
Papers published on a yearly basis
Papers
More filters
Patent•
11 Sep 1989TL;DR: In this article, the semantic structures of a plurality of semantic structures are represented by a common item during the expressing of the meanings of words, phrases, and sentences, and the items are written in parallel during expressing the meanings.
Abstract: Meanings of words, phrases, and a sentence are expressed in items. Items, which have equal contents, of a plurality of semantic structures are represented by a common item during the expressing of the meanings. Items, which have different contents, of the semantic structures are written in parallel during the expressing of the meanings. The semantic structures are rewritten into a parallel semantic structure through the representing and the writing. Contents of the parallel semantic structure are examined and corrected in consideration of a parallel characteristic of the parallel semantic structure.
66 citations
Proceedings Article•
01 Dec 2012TL;DR: It is shown that the phrase-based SMT approach is effective in correcting frequent errors that can be identified by local context, and that it is difficult for phrase- based SMT to correct errors that need long range contextual information.
Abstract: English as a Second Language (ESL) learners’ writings contain various grammatical errors. Previous research on automatic error correction for ESL learners’ grammatical errors deals with restricted types of learners’ errors. Some types of errors can be corrected by rules using heuristics, while others are difficult to correct without statistical models using native corpora and/or learner corpora. Since adding error annotation to learners’ text is time-consuming, it was not until recently that large scale learner corpora became publicly available. However, little is known about the effect of learner corpus size in ESL grammatical error correction. Thus, in this paper, we investigate the effect of learner corpus size on various types of grammatical errors, using an error correction system based on phrase-based statistical machine translation (SMT) trained on a large scale errortagged learner corpus. We show that the phrase-based SMT approach is effective in correcting frequent errors that can be identified by local context, and that it is difficult for phrase-based SMT to correct errors that need long range contextual information.
66 citations
TL;DR: The results suggest that semantic and syntactic information are integrated during the earlier stages of syntactic processing indexed by the anterior negativities, and that these interactions continue in the later stages of processingindexed by the P600.
66 citations
TL;DR: De Gruyter as mentioned in this paper examines the intersection of language, interaction and cognition and examines a communicative type of fictivity, called fictive verbal interaction or simply fictive interaction, which constitutes a self-sufficient discourse unit conceptualized within a non-factive communicative occurrence.
Abstract: This paper examines the intersection of language, interaction and cognition. Specifically, a communicative type of fictivity is discussed, which I call fictive verbal interaction or simply fictive interaction (Pascual 2002). This constitutes a self-sufficient discourse unit conceptualized within a non-factive communicative occurrence, which functions syntactically and semantically as a grammatical constituent. Attested examples at different syntactic levels are dealt with. These levels are: (i) the clause (e.g., The attitude that, yes, I can do it); (ii) the phrase (e.g., The attitude of yes, I can do it.); and (iii) the lexical item (e.g., The 'yes, I can do it' attitude). © Walter de Gruyter.
66 citations
Proceedings Article•
06 Jun 2010TL;DR: This paper explores the effectiveness of Mechanical Turk for creating parallel corpora for the task of sentence translation, both into and out of a language.
Abstract: Corpus based approaches to machine translation (MT) rely on the availability of parallel corpora. In this paper we explore the effectiveness of Mechanical Turk for creating parallel corpora. We explore the task of sentence translation, both into and out of a language. We also perform preliminary experiments for the task of phrase translation, where ambiguous phrases are provided to the turker for translation in isolation and in the context of the sentence it originated from.
66 citations