Abstract. Oo Y, Suanpaga W, Muenpong P. 2021. Assessment of forest degradation condition in Natmataung National Park Watershed, Myanmar. Biodiversitas 22: 1354-1362. Natmataung National Park (NTNP) is an important biodiversity hotspot in Myanmar, yet it is threatened by various anthropogenic activities, leading to deforestation and forest degradation. As such, the park needs to be restored to bring back its main function of conserving biodiversity. Ecological restoration in NTNP needs assessment of forest restoration potential through forest degradation condition. This research aimed: (1) to assess forest stand parameters of tree density, basal area, Above Ground Biomass (AGB), and Above Ground Carbon (AGC) at plot level and study area level through sampling with fixed area in the NTNP watershed, (2) to compare the accessed forest stand parameters of old-growth forest (OF) and secondary forest (SF) (per plot individual level and per stem individual level) and tree species richness and diversity of OF and SF (per plot individual level only) in order to know the forest degradation condition. A total of 69 square plots were sampled to achieve such aims. This study found two main results: (1) the estimation of stand parameters in both OF and SF at the plot level and study area level had acceptable statistical proration: (2) stand parameters at stem level had significant differences in which OF had overall higher values of parameters than in SF. Based on the results of this study, we recommend that the OF sites should be conserved through sustainable forest management, while the SF sites should be restored to mimic condition in OF through the implementation of assisted natural regeneration (ANR) with highest dominant native tree species, and the abandoned fallow lands should be restored using pioneer native tree species.

No abstract

No abstract

No abstract

Morphological stemming becomes a critical step toward natural language processing. The process of stemming is to reduce alternative forms to a common morphological root. Word segmentation for Myanmar Language, like for most Asian Languages, is an important task and extensively-studied sequence labelling problem. Named entity detection is one of the issues in Asian Language that has traditionally required a large amount of feature engineering to achieve high performance. The new approach is integrating them that would benefit in all these processes. In recent years, end-to-end sequence labelling models with deep learning are widely used. This paper introduces a deep BiGRU-CNN-CRF network that jointly learns word segmentation, stemming and named entity recognition tasks. We trained the model using manually annotated corpora. State-of-the-art named entity recognition systems rely heavily on handcrafted feature built in our new approach, we introduce the joint model that relies on two sources of information: character level representation and syllable level representation.