The terms coreference and anaphora tend to be used inconsistently and interchangeably in much empirically-oriented work in NLP, and this threatens to lead to incoherent analyses of texts and arbitrary loss of information. This paper discusses the role of coreference annotation in Information Extraction, focussing on the coreference scheme defined for the MUC-7 evaluation exercise. We point out ...

We are currently constructing a special language corpus, with particular emphasis on such lexically oriented studies and applications as terminology and information retrieval. In the paper, we focus on the problem with de ning the lexical units in running texts, which is essential for the construction of a lexically motivated corpus. Although we focus on Japanese in this paper, the problem disc...

The object of the study is idiodiscourse outstanding philologist M.M. Bakhtin, subject integral and differential features Bakhtin as a realization professional linguistic personality philologist. purpose based on material within framework comparative rhetorical analysis, to reveal invariant core individual set goal predetermines number specific tasks: 1. consider history issue: summarize studie...

Image-text retrieval plays a central role in bridging vision and language, which aims to reduce the semantic discrepancy between images texts. Most of existing works rely on refined words objects representation through data-oriented method capture word-object cooccurrence. Such approaches are prone ignore asymmetric action relation texts, that is, text has explicit (i.e., verb phrase) while ima...

Free access to full-text scientific papers in major digital libraries and other web repositories is limited to only their abstracts consisting of no more than several dozens of words. Current keyword-based techniques allow for clustering such type of short texts only when the data set is multi-category, e.g., some documents are devoted to sport, others to medicine, others to politics, etc. Howe...

Fine-grained named entity classi cation or FG-NEC refers to the process of classifying a set of named entities from naturally occurring texts to the maximum granularity. It is essentially di erent from the traditional coarse-grained NEC (PER, LOC, ORG) in that it requires deep semantic analysis and the FG semantic classes are highly ambiguous. While research has been conducted in an application...

Students at universities and colleges in Belgium as well as abroad often experience difficulties with writing (academic) texts in their native language. Several needs analyses have pointed out that the most frequent writing problems in Dutch are text structure and cohesion, academic style and, to a lesser extent, spelling. Despite many interventions such as extra writing classes or workshops, t...

This study was carried out to compare Iranian college students’ rate of incidental vocabulary learning when reading texts for different purposes (specific vs. general) and in different conditions (marked vs. unmarked) using Computer-Assisted Language Learning (CALL) . The hypertext software programme which was used in this study is characterized with prominent capabilities such as presenting th...

Any study of standards is complicated by the existence of numerous meanings of the term, which are often used virtually interchangeably. A few of these uses are most relevant to this book. It appears that the term fi rst came into general use in English at the Battle of the Standard in 1138. According to a contemporary observer, Richard of Hexham ([1138] 1988, 67), in this battle between the En...