排序方式： 共有15条查询结果，搜索用时 250 毫秒
11.
This work addresses the information retrieval problem of auto-indexing Arabic documents. Auto-indexing a text document refers to automatically extracting words that are suitable for building an index for the document. In this paper, we propose an auto-indexing method for Arabic text documents. This method is mainly based on morphological analysis and on a technique for assigning weights to words. The morphological analysis uses a number of grammatical rules to extract stem words that become candidate index words. The weight assignment technique computes weights for these words relative to the container document. The weight is based on how spread is the word in a document and not only on its rate of occurrence. The candidate index words are then sorted in descending order by weight so that information retrievers can select the more important index words. We empirically verify the usefulness of our method using several examples. For these examples, we obtained an average recall of 46% and an average precision of 64%. 相似文献
12.
13.
Arabic documents that are available only in print continue to be ubiquitous and they can be scanned and subsequently OCR’ed
to ease their retrieval. This paper explores the effect of context-based OCR correction on the effectiveness of retrieving
Arabic OCR documents using different index terms. Different OCR correction techniques based on language modeling with different
correction abilities were tested on real OCR and synthetic OCR degradation. Results show that the reduction of word error
rates needs to pass a certain limit to get a noticeable effect on retrieval. If only moderate error reduction is available,
then using short character n-gram for retrieval without error correction is not a bad strategy. Word-based correction in conjunction
with language modeling had a statistically significant impact on retrieval even for character 3-grams, which are known to
be among the best index terms for OCR degraded Arabic text. Further, using a sufficiently large language model for correction
can minimize the need for morphologically sensitive error correction.
相似文献
| Kareem DarwishEmail: |
14.
Walid E. Zahran Magda I. Mahmoud Kamal A. Shalaby Manal H. Abbas 《Indian journal of clinical biochemistry : IJCB》2013,28(3):272-276
Rheumatoid arthritis (RA) is the most common inflammatory systemic autoimmune disease, primarily affecting the peripheral joints. Anti-mutated citrullinated vimentin autoantibodies (anti-MCV) of IgG isotype were shown to be a useful diagnostic marker of RA especially in RA patients who were anti-cyclic citrullinated protein autoantibodies (anti-CCP) negative. Nevertheless, published data correlates rheumatoid factor (RF), anti-CCP or anti-MCV antibodies with either erythrocyte sedimentation rate (ESR) or serum C-reactive protein (CRP) as markers of disease activity, not investigated the possible correlations of RA autoantibodies towards ESR and CRP in comparison. Herein, we aim to evaluate the usefulness of anti-MCV as a dependable marker in established RA compared with anti-CCP and RF antibodies and to examine correlations between RF, anti-CCP and anti-MCV antibodies towards ESR and serum CRP. Serum RF-IgA, RF-IgM, anti-CCP and anti-MCV levels were measured in 30 patients with RA and 40 patients with other autoimmune diseases (non-RA) compared with 20 normal subjects. Specificity, sensitivity and AUC for RF antibodies, anti-CCP and anti-MCV were calculated towards RA diagnosis. Our results showed that ESR and CRP had significantly higher values in both RA and non-RA patients compared with our healthy controls with observed significant increment in RA patients compared with non-RA patients. An important finding from our study is that 33.3 % of RA patients were anti-CCP negative but being positive towards anti-MCV. Also, in-between 36.7 up to 40 % of RA patients were RF-IgA and RF-IgM negative while being anti-MCV positive. Anti-MCV antibodies showed the highest specificity and sensitivity (97.5 and 86.6 %, respectively) towards RA diagnosis with the highest AUC value (0.920) compared with anti-CCP and RF antibodies. Correlation analyses revealed that there was no significant correlation between ESR along with CRP towards RF-IgA, RF-IgM and anti-CCP while profound highly significant correlation exhibited between ESR and CRP towards anti-MCV data (r = 0.879 and 0.994, respectively). Thus, our data suggest that the assessment of serum anti-MCV autoantibodies along with ESR and CRP considered as a simple laboratory regime for monitoring RA patients to assess and follow-up disease activity. The addition of anti-MCV autoantibodies to serologic markers in the ACR/EULAR classification criteria for RA will add points for patients with negative anti-CCP and RF antibodies. 相似文献
15.