-
Reyes Ayala, B.; Knudson, R.; Chen, J.; Cao, G.; Wang, X.: Metadata records machine translation combining multi-engine outputs with limited parallel data (2018)
0.01
0.009625921 = product of:
0.019251842 = sum of:
0.019251842 = product of:
0.038503684 = sum of:
0.038503684 = weight(_text_:systems in 4010) [ClassicSimilarity], result of:
0.038503684 = score(doc=4010,freq=4.0), product of:
0.16037072 = queryWeight, product of:
3.0731742 = idf(docFreq=5561, maxDocs=44218)
0.052184064 = queryNorm
0.24009174 = fieldWeight in 4010, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.0731742 = idf(docFreq=5561, maxDocs=44218)
0.0390625 = fieldNorm(doc=4010)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- One way to facilitate Multilingual Information Access (MLIA) for digital libraries is to generate multilingual metadata records by applying Machine Translation (MT) techniques. Current online MT services are available and affordable, but are not always effective for creating multilingual metadata records. In this study, we implemented 3 different MT strategies and evaluated their performance when translating English metadata records to Chinese and Spanish. These strategies included combining MT results from 3 online MT systems (Google, Bing, and Yahoo!) with and without additional linguistic resources, such as manually-generated parallel corpora, and metadata records in the two target languages obtained from international partners. The open-source statistical MT platform Moses was applied to design and implement the three translation strategies. Human evaluation of the MT results using adequacy and fluency demonstrated that two of the strategies produced higher quality translations than individual online MT systems for both languages. Especially, adding small, manually-generated parallel corpora of metadata records significantly improved translation performance. Our study suggested an effective and efficient MT approach for providing multilingual services for digital collections.
-
Qin, C.; Liu, Y.; Mou, J.; Chen, J.: User adoption of a hybrid social tagging approach in an online knowledge community (2019)
0.01
0.008837775 = product of:
0.01767555 = sum of:
0.01767555 = product of:
0.0353511 = sum of:
0.0353511 = weight(_text_:22 in 5492) [ClassicSimilarity], result of:
0.0353511 = score(doc=5492,freq=2.0), product of:
0.1827397 = queryWeight, product of:
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.052184064 = queryNorm
0.19345059 = fieldWeight in 5492, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.5018296 = idf(docFreq=3622, maxDocs=44218)
0.0390625 = fieldNorm(doc=5492)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Date
- 20. 1.2015 18:30:22
-
Chen, J.; Wang, D.; Xie, I.; Lu, Q.: Image annotation tactics : transitions, strategies and efficiency (2018)
0.01
0.007700737 = product of:
0.015401474 = sum of:
0.015401474 = product of:
0.030802948 = sum of:
0.030802948 = weight(_text_:systems in 5046) [ClassicSimilarity], result of:
0.030802948 = score(doc=5046,freq=4.0), product of:
0.16037072 = queryWeight, product of:
3.0731742 = idf(docFreq=5561, maxDocs=44218)
0.052184064 = queryNorm
0.19207339 = fieldWeight in 5046, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
3.0731742 = idf(docFreq=5561, maxDocs=44218)
0.03125 = fieldNorm(doc=5046)
0.5 = coord(1/2)
0.5 = coord(1/2)
- Abstract
- Human interpretation of images during image annotation is complicated, but most existing interactive image annotation systems are generally operated based on social tagging, while ignoring that tags are insufficient to convey image semantics. Hence, it is critical to study the nature of image annotation behaviors and process. This study investigated annotation tactics, transitions, strategies and their efficiency during the image annotation process. A total of 90 participants were recruited to annotate nine pictures in three emotional dimensions with three interactive annotation methods. Data collected from annotation logs and verbal protocols were analyzed by applying both qualitative and quantitative methods. The findings of this study show that the cognitive process of human interpretation of images is rather complex, which reveals a probable bias in research involving image relevance feedback. Participants preferred applying scroll bar (Scr) and image comparison (Cim) tactics comparing with rating tactic (Val), and they did fewer fine tuning activities, which reflects the influence of perceptual level and users' cognitive load during image annotation. Annotation tactic transition analysis showed that Cim was more likely to be adopted at the beginning of each phase, and the most remarkable transition was from Cim to Scr. By applying sequence analysis, the authors found 10 most commonly used sequences representing four types of annotation strategies, including Single tactic strategy, Tactic combination strategy, Fix mode strategy and Shift mode strategy. Furthermore, two patterns, "quarter decreasing" and "transition cost," were identified based on time data, and both multiple tactics (e.g., the combination of Cim and Scr) and fine tuning activities were recognized as efficient tactic applications. Annotation patterns found in this study suggest more research needs to be done considering the need for multi-interactive methods and their influence. The findings of this study generated detailed and useful guidance for the interactive design in image annotation systems, including recommending efficient tactic applications in different phases, highlighting the most frequently applied tactics and transitions, and avoiding unnecessary transitions.
