Sökning: "Domain specificity"
Visar resultat 6 - 10 av 18 uppsatser innehållade orden Domain specificity.
6. Emotion Classification with Natural Language Processing (Comparing BERT and Bi-Directional LSTM models for use with Twitter conversations)
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : We have constructed a novel neural network architecture called CWE-LSTM (concatenated word-emoji bidirectional long short-term memory) for classify- ing emotions in Twitter conversations. The architecture is based on a combina- tion of word and emoji embeddings with domain specificity in Twitter data. LÄS MER
7. Thinking things in German versus Swedish
Master-uppsats, Lunds universitet/Masterprogram: Språk och språkvetenskap; Lunds universitet/Allmän språkvetenskapSammanfattning : Against the backdrop of universality proposals claiming that all the world’s languages share the way they conceptualise and express THINKING, this study investigates verbs of thinking in German and Swedish in a comparative perspective. In particular, it examines semantic specificity in verbs of thinking (the restricted availability of only one specific verb in a certain context), and the potential effect of two constraints (intersubjective verifiability and subjectivity). LÄS MER
8. The Creative Networker : Predicted Relations between Network Behavior and Creativity
Kandidat-uppsats, Uppsala universitet/Företagsekonomiska institutionenSammanfattning : The purpose of the present study was to analyze the significance ofcreativity for network behavior. Similar to other network behavioral studiesthe multidimensional approach was utilized where networking was dividedinto sub dimensions with external and internal counterparts. LÄS MER
9. Interpretability of a Deep Learning Model for Semantic Segmentation : Example of Remote Sensing Application
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Understanding a black-box model is a major problem in domains that relies on model predictions in critical tasks. If solved, can help to evaluate the trustworthiness of a model. This thesis proposes a user-centric approach to black-box interpretability. LÄS MER
10. A Transformation of Controlled Natural Language Behavioural Requirements into Modal Sequence Diagram Simulation Models for Requirement Conflict Detection
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : PURPOSE: Specifying requirements in a semi-formal notation, such as a controlled natural language (CNL), allows reduction of ambiguity and underspecification in requirement specifications, as the notation uses well defined semantics and enforces consistency and conformance to syntactical rules. Contradicting requirements can be problematic to detect in practice depending on the size and complexity of the requirement specification. LÄS MER