Research on Spoken Language Understanding Based on Deep Learning

Aiming at solving the problem that the recognition effect of rare slot values in spoken language is poor, which affects the accuracy of oral understanding task, a spoken language understanding method is designed based on deep learning. The local features of semantic text are extracted and classified to make the classification results match the dialogue task. An intention recognition algorithm is designed for the classification results. Each datum has a corresponding intention label to complete the task of semantic slot filling. The attention mechanism is applied to the recognition of rare slot value information, the weight of hidden state and corresponding slot characteristics are obtained, and the updated slot value is used to represent the tracking state. An auxiliary gate unit is constructed between the upper and lower slots of historical dialogue, and the word vector is trained based on deep learning to complete the task of spoken language understanding. The simulation results show that the proposed method can realize multiple rounds of man-machine spoken language. Compared with the spoken language understanding methods based on cyclic network, context information, and label decomposition, it has higher accuracy and F1 value and has higher practical application value.

Show and Tell More: Topic-Oriented Multi-Sentence Image Captioning

Image captioning aims to generate textual descriptions for images. Most previous work generates a single-sentence description for each image. However, a picture is worth a thousand words. Single-sentence can hardly give a complete view of an image even by humans. In this paper, we propose a novel Topic-Oriented Multi-Sentence (\emph{TOMS}) captioning model, which can generate multiple topic-oriented sentences to describe an image. Different from object instances or attributes, topics mined by the latent Dirichlet allocation reflect hidden thematic structures in reference sentences of an image. In our model, each topic is integrated to a caption generator with a Fusion Gate Unit (FGU) to guide the generation of a sentence towards a certain topic perspective. With multiple sentences from different topics, our \emph{TOMS} provides a complete description of an image. Experimental results on both sentence and paragraph datasets demonstrate the effectiveness of our \emph{TOMS} in terms of topical consistency and descriptive completeness.

KAJIAN DAMPAK LINGKUNGAN PENERAPAN TEKNOLOGI BIOFLOK PADA KEGIATAN BUDIDAYA UDANG VANAME DENGAN METODE LIFE CYCLE ASSESSMENT

ABSTRAKPenerapan teknologi bioflok pada kegiatan budidaya vaname perlu dievaluasi, terkaitpenggunaan sumberdaya alam dan energi listrik yang berpotensi mengakibatkan dampaklingkungan disertai biaya investasi yang tinggi. Tujuan penelitian ini adalah menganalisisdampak lingkungan dan menentukan strategi pengelolaan budidaya udang berbasis teknologibioflok. Penelitian ini merupakan penelitian deskriptif kuantitatif dengan menggunakanmetode penaksiran daur hidup. Kajian dibatasi pada kegiatan pembesaran di tambak “cradleto farm gate”, unit yang digunakan adalah produksi 1 ton udang vaname. Hasil penelitian inimenunjukkan teknologi bioflok mampu meningkatkan produksi per satuan luas lahan yangdigunakan dengan ukuran panen ± 16,4 gr/ekor, nilai FCR 1,3, SR 86 - 92%, dan SGR 15,6%.Produksi per ton udang vaname menghasilkan dampak: acidification (Acd); 63.39 ± 15.37 kgSO2eq, eutrophication (Eut); 14.10 ± 3.28 kg PO4eq, ; global warming potential (GWP); 7336.77± 1,46 kg CO2eq, ; dan cumulative energy use (CEU) sebesar 101,64 ± 18.84 GJ. Strategipengelolaan perlu dilakukan dengan perbaikan manajemen pemberian pakan berbasis kualitasair, pengurangan konsumsi energi listrik, menerapkan panen bertahap dan menambahkankolam pengolahan limbah.Kata Kunci : kajian, lingkungan, bioflok, budidaya udang,