Sökning: "Marcus Liwicki"

Visar resultat 1 - 5 av 13 avhandlingar innehållade orden Marcus Liwicki.

1. 1. Vector Representations of Idioms in Data-Driven Chatbots for Robust Assistance

   Författare :Oluwatosin Adewumi; Marcus Liwicki; Foteini Liwicki; Taiwo Kolajo; Luleå tekniska universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; conversational system; chatbot; vectors; data; deep models; Maskininlärning; Machine Learning;

   Sammanfattning : This thesis presents resources capable of enhancing solutions of some Natural Language Processing (NLP) tasks, demonstrates the learning of abstractions by deep models through cross-lingual transferability, and shows how deep learning models trained on idioms can enhance open-domain conversational systems. The challenges of open-domain conversational systems are many and include bland repetitive utterances, lack of utterance diversity, lack of training data for low-resource languages, shallow world-knowledge and non-empathetic responses, among others. LÄS MER

3. 2. Data driven crop disease modeling

   Författare :Priyamvada Shankar; Marcus Liwicki; Foteini Liwicki; Lili Jiang; Luleå tekniska universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; LANTBRUKSVETENSKAPER; AGRICULTURAL SCIENCES; Crop Disease Prediction; Precision Agriculture; Digital Farming; Artificial Intelligence; Machine learning; Maskininlärning; Machine Learning;

   Sammanfattning : The concept of precision farming deals with the creation and use of data from machinery and sensors on and off the field to optimize resources and sustainably intensify food production to keep up with increasing demand. However, in the face of a growing amount of data being collected, smarter data processing and analysis techniques are needed and have prompted the evaluation and incorporation of artificial intelligence (AI) and machine learning (ML) techniques for multiple use cases right from seeding to harvesting. LÄS MER

4. 3. Deep Learning for Geo-referenced Data : Case Study: Earth Observation

   Författare :Nosheen Abid; Marcus Liwicki; Muhammad Zeshan Afzal; Luleå tekniska universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Artificial Intelligence; Machine Learning; Earth Observation; Computer Vision; Machine Learning; Maskininlärning;

   Sammanfattning : The thesis focuses on machine learning methods for Earth Observation (EO) data, more specifically, remote sensing data acquired by satellites and drones. EO plays a vital role in monitoring the Earth’s surface and modelling climate change to take necessary precautionary measures. LÄS MER

5. 4. Word Vector Representations using Shallow Neural Networks

   Författare :Oluwatosin Adewumi; Marcus Liwicki; Marco Kuhlmann; Luleå tekniska universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Word vectors; NLP; Neural networks; Embeddings; Maskininlärning; Machine Learning;

   Sammanfattning : This work highlights some important factors for consideration when developing word vector representations and data-driven conversational systems. The neural network methods for creating word embeddings have gained more prominence than their older, count-based counterparts. LÄS MER

7. 5. Faster and More Resource-Efficient Intent Classification

   Författare :Pedro Alonso; Marcus Liwicki; Ali Basrat; Luleå tekniska universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Maskininlärning; Machine Learning;

   Sammanfattning : Intent classification is known to be a complex problem in Natural Language Processing (NLP) research. This problem represents one of the stepping stones to obtain machines that can understand our language. Several different models recently appeared to tackle the problem. The solution has become reachable with deep learning models. LÄS MER