• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• Journal of Animal Science and Technology
• /
• v.44 no.2
• /
• pp.165-170
• /
• 2002

Mature weight (A) and rate of maturing (k) estimated by nonlinear regression were studied to determine the optimum age range over which the estimate of growth curve parameters can be estimated. The weight-age data from 1,133 Hanwoo bulls at Hanwoo Improvement Center of N.A.C.F. were used to fit the growth curve using Gompertz model. All available weight data from birth to the specific age of months were used for the estimation of parameters: the six specific ages used were 12, 14, 16, 18, 20 22 and 24 months of age. The mean estimates of mature weight (A) were 966.5, 1,255.9, 1,126.2, 916.5, 842.2, 780.9 and 767.0kg for ages 12 through 24 months, respectively. The mean estimates of mature weight (A) to 22 and 24 months of age were not different from each other. However, they were different from the estimates based on the data to other ages. Mean estimates of rate of maturing (k) were 3.362, 3.595, 3.536, 3.421, 3.403, 3.409 and 3.411 for ages 12 through 24 months, respectively. The mean estimates of maturing rate (k) for ages 18 through 24 months of age were not significantly different from each other. However, they were different from the estimates based on the data to other ages. Correlations among estimates of A at various ages showed the highest value of 0.93 between 22 and 24 months. Correlations among estimates of k at various ages were highest ranging from 0.91 to 0.99 among 18 to 24 months. The correlations between A and k were positive and tended to decrease with the increase of the age from 0.84 for the age of 12 months to 0.10 for the age of 24 months. Thus, the estimates of growth curve parameters, A and k, suitable for genetic studies can be derived from accumulated Hanwoo bulls after 22 months of age.

• Korean journal of applied entomology
• /
• v.57 no.4
• /
• pp.261-269
• /
• 2018

The cowpea aphid Aphis craccivora Koch (Hemiptera: Aphididae) is a polyphagous species with a worldwide distribution. We investigated the temperature effects on development periods of nymphs, and the longevity and fecundity of apterous female of A. craccivora. The study was conducted at six constant temperatures of 10.0, 15.0, 20.0, 25, 30.0, and $32.5^{\circ}C$. A. craccivora developed successfully from nymph to adult stage at all temperatures subjected. The developmental rate of A. craccivora increased as temperature increased. The lower developmental threshold (LT) and thermal constant (K) of A. craccivora nymph stage were estimated by linear regression as $5.3^{\circ}C$ and 128.4 degree-days (DD), respectively. Lower and higher threshold temperatures (TL, TH and TH-TL, respectively) were calculated by the Sharpe_Schoolfield_Ikemoto (SSI) model as $17.0^{\circ}C$, $34.6^{\circ}C$ and $17.5^{\circ}C$. Developmental completion of nymph stages was described using a three-parameter Weibull function. Life table parameters were estimated. The intrinsic rate of increase was highest at $25^{\circ}C$, while the net reproductive rate was highest at $20^{\circ}C$. Biological characteristics of A. craccivora populations from different geographic areas were discussed.