A Hierarchical Sequence-to-Sequence Model for Korean POS Tagging

Part-of-speech (POS) tagging is a fundamental task in natural language processing. Korean POS tagging consists of two subtasks: morphological analysis and POS tagging. In recent years, scholars have tended to use the seq2seq model to solve this problem. The full context of a sentence is considered in these seq2seq-based Korean POS tagging methods. However, Korean morphological analysis relies more on local contextual information, and in many cases, there exists one-to-one matching between morpheme surface form and base form. To make better use of these characteristics, we propose a hierarchical seq2seq model. In our model, the low-level Bi-LSTM encodes the syllable sequence, whereas the high-level Bi-LSTM models the context information of the whole sentence, and the decoder generates the morpheme base form syllables as well as the POS tags. To improve the accuracy of the morpheme base form recovery, we introduced the convolution layer and the attention mechanism to our model. The experimental results on the Sejong corpus show that our model outperforms strong baseline systems in both morpheme-level F1-score and eojeol-level accuracy, achieving state-of-the-art performance.

Reconstructing boosted Higgs jets from event image segmentation

Based on the jet image approach, which treats the energy deposition in each calorimeter cell as the pixel intensity, the Convolutional neural network (CNN) method has been found to achieve a sizable improvement in jet tagging compared to the traditional jet substructure analysis. In this work, the Mask R-CNN framework is adopted to reconstruct Higgs jets in collider-like events, with the effects of pileup contamination taken into account. This automatic jet reconstruction method achieves higher efficiency of Higgs jet detection and higher accuracy of Higgs boson four-momentum reconstruction than traditional jet clustering and jet substructure tagging methods. Moreover, the Mask R-CNN trained on events containing a single Higgs jet is capable of detecting one or more Higgs jets in events of several different processes, without apparent degradation in reconstruction efficiency and accuracy. The outputs of the network also serve as new handles for the $$ t\overline{t} $$ t t ¯ background suppression, complementing to traditional jet substructure variables.

Problems and puzzles in echinoderm demography

Introduction: There are problems and puzzles in understanding reproduction, growth and mortality in echinoderm life cycles. Objective: Explore problems and puzzles in life cycles that are important and challenging. Methods: The literature is used to elucidate problems associated with all life stages. Results: Sources of larvae that settle at a site are explored using oceanographic modelling and genetic methods. There are few studies that have estimated larval mortality in the plankton under field conditions and results differ from experimental results or patterns of settlement. In a small number of studies, mortality rate of newly settled larvae appears to change rapidly as individuals grow. There are problems measuring size, and measurement bias that interferes with many tagging methods used to estimate growth. There also are problems with the use of natural growth lines and commonly used software to estimate both growth and mortality from size-frequency data. An interesting puzzle is that echinoderms may show negative senescence with mortality rate decreasing with size. There is a problem in fertilization success based on density so there should not be rare species where sexes are separate with free spawning of gametes yet there seem to be rare echinoderms. Conclusions: All parts of echinoderm life cycles provide problems and puzzles that are important and challenging.

Wing tags severely impair movement in African Cape Vultures

Background The use of tracking technologies is key for the study of animal movement and pivotal to ecological and conservation research. However, the potential effects of devices attached to animals are sometimes neglected. The impact of tagging not only rises welfare concerns, but can also bias the data collected, causing misinterpretation of the observed behaviour which invalidates the comparability of information across individuals and populations. Patagial (wing) tags have been extensively used as a marking method for visual resightings in endangered vulture species, but their effect on the aerodynamics of the birds and their flight behaviour is yet to be investigated. Using GPS backpack mounted devices, we compared the flight performance of 27 captive and wild Cape Vultures (Gyps coprotheres), marked with either patagial tags or coloured leg bands. Results Individuals equipped with patagial tags were less likely to fly, travelled shorter distances and flew slower compared to individuals equipped with leg bands. These effects were also observed in one individual that recovered its flight performance after replacing its patagial tag by a leg band. Conclusions Although we did not measure the effects of patagial tags on body condition or survival, our study strongly suggests that they have severe adverse effects on vultures’ flight behaviour and emphasises the importance of investigating the effects that tagging methods can have on the behaviour and conservation of the study species, as well as on the quality of the scientific results.

Under pressure: comparing in situ and boat tagging methods using time-to-event analyses

Background With the increase in telemetry studies over the past decade, improving understanding of how different tagging methods influence the probability of presence in a receiver array is important in maximizing the resulting data. Disappearance from the array may be due to mortality from surgery complications, tag loss, predation, or emigration. Internally tagging fish on a boat can cause barotrauma injuries, increased stress from prolonged handling times, or predation after fish have been released back into the water. Conducting in situ internal acoustic tagging at depth of capture removes barotrauma stresses and simplifies the release method, which may improve fish survival and decrease risk of disappearance from the array. In this study, we used 8 years of acoustic tagging data to determine if the tagging method (in situ versus on the boat) influenced the likelihood of a fish being detected 4 and 6 days after the tagging event. Results At 6 days after tagging, Kaplan–Meier survival curves revealed that the probability of presence for fish tagged on the boat was 66% compared to 90% for fish tagged in situ. Tagging method was the only variable to significantly affect probability of presence based on Cox proportional hazards models, with fish tagged in situ ~ 75% less likely to disappear from the array compared to fish tagged on the boat at both 4 and 6 days after tagging. Examining tagging methods separately, handling time only marginally influenced probability of presence of boat-tagged fish and no variables had a significant effect on probability of presence of in situ tagged fish. Conclusions In this study, tagging method was the only variable to significantly affect the probability of presence for internally tagged fish. Other factors had little to no influence, but correlation of variables limited what factors could be included in the models. Implanting internal acoustic tags in situ is not a practical method for every species and for every environment, but given the increased probability of presence demonstrated here, we strongly suggest it be considered where applicable.

Under pressure: Comparing in situ and boat tagging methods using time-to-event analyses

Background With the increase in telemetry studies over the past decade, improving understanding of how different tagging methods influence fish survivorship is critical. By examining the effects of tagging methods, we can maximize the information gained from telemetry studies. Mortality resulting from internally tagging fish on a boat may be due to barotrauma injuries, increased stress from prolonged handling times, or predation after fish have been released back into the water. Conducting in situ internal acoustic tagging at depth of capture completely removes barotrauma stresses and simplifies the release method, which may improve fish survival. In this study, we used 8 years of acoustic tagging data to determine if the tagging method ( in situ versus on the boat) influenced fish survivorship and evaluated the role of other tagging variables. Results At 6 days after tagging, Kaplan–Meier survival curves revealed that the survival probability of fish tagged on the boat was 66% while survival probability of fish tagged in situ was 90%. Tagging method was the only variable to significantly affect survival probability based on Cox proportional hazards models, with fish tagged in situ ~75% less likely to have an “event” (mortality, tag loss, or emigration) compared to fish tagged on the boat at both 4 and 6 days after tagging. Examining tagging methods separately, handling time only marginally influenced survival probability of boat-tagged fish and no variables had a significant effect on survival of in situ tagged fish. Conclusions In this study, tagging method was the only variable to significantly affect survival of internally tagged fish. Implanting internal acoustic tags in situ is not a practical method for every species and for every environment, but given the increased fish survivorship demonstrated here, we strongly suggest it be considered as the preferred tagging methodology where applicable.