We investigate in this paper the degree of overlap between synonym sets of translated word pairs across three languages: French, English and Romanian. We use for this purpose a French Synonym Dictionary, a Romanian Synonym Dictionary, Princeton’s WordNet and Google Translate API. We build a database containing pairs of (translated) words from the three languages, along with their corresponding ...

Synonym extraction is an important task in natural language processing and often used as a submodule in query expansion, question answering and other applications. Automatic synonym extractor is highly preferred for large scale applications. Previous studies in synonym extraction are most limited to small scale datasets. In this paper, we build a large dataset with 3.4 million synonym/nonsynony...

The authors propose a new synonym between Collaria scenica (senior synonym) and Collaria columbiensis (junior synonym) based on external morphology and genitalia characteristics of male and female adults of both species. There was no significant difference found to believe that they are two different species.

Examination of the holotype of the tetragnathid spider Sternospina concretipalpis Schmidt & Krause, 1993 demonstrates that the extraordinary claim by the authors of the original description of this species that the male palps are fused is unfounded. The monotypic genus Sternospina Schmidt & Krause, 1993 is a junior synonym of Tylorida Simon, 1894 and S. concretipalpis is a junior synonym of the...

s (150 words) Titles Only Abstracts Null Summaries Nulls Null Summaries Null Synonym Recognition (Thesaurus) only Word Stem Match Synonym Recognition Statistical Phrase Recognition Simple Word Stems Synonym Recognition Index Term Match Abstracts with Thesarus » "much greater than > "greater than" ~ "about equal to" (based on experiments with 4 collections in 3 topic areas) Overall Evaluation Re...

Online learning calls for instant assessment and feedback. YanFa is a system developed to score online EnglishChinese translation exercises with intelligent feedback for Chinese non-English majors. With the aid of HowNet and Cilin—Chinese Synonym Set (Extended Version), the system adopts the hybrid approach to scoring student translation semantically. It compares student translation with model ...

The University of Illinois at Urbana-Champaign (UIUC) participated in TREC 2007 Genomics Track. Our general goal of participation is to apply language modelbased approaches to the genomics retrieval task and study how we may extend the standard language models to accommodate two special needs for this year’s genomics retrieval task: (1) gene synonym expansion and (2) conjunctive query interpret...

The goal of this project is to attribute the authorship of excerpts from a set of New York Times articles to author Gina Kolata. The training data included labeled excerpts from New York Times as Gina Kolata vs other authors. We extracted and tried a multitude of features, setting the baseline as an SVM on 1000 most frequent words and then moving onto more complex features like Parts-of-Speech,...

The goal of formalization, proposed in this paper, is to bring together, as near as possible, the theoretic linguistic problem of synonym conception and the computer linguistic methods based generally on empirical intuitive unjustified factors. Using the word vector representation we have proposed the geometric approach to mathematical modeling of synonym set (synset). The word embedding is bas...