Sökning: "ordinbäddning"
Visar resultat 1 - 5 av 6 uppsatser innehållade ordet ordinbäddning.
1. Software Issue Time Estimation With Natural Language Processing and Machine Learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Time estimation for software issues is crucial to planning projects. Developers and experts have for many decades tried to estimate time requirements for issues as accurately as possible. The methods that are used today are often time-consuming and complex. LÄS MER
2. Extending a Text Classifier to Multiple Languages
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : This thesis explores the possibility to extend monolingual and bilingual text classifiers to multiple languages. Two different language models are explored, language aligned word embeddings and a transformer model. The goal was to take a classifier based on Swedish and English samples and extend it to Danish, German, and Finnish samples. LÄS MER
3. Text ranking based on semantic meaning of sentences
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Finding a suitable candidate to client match is an important part of consultant companies work. It takes a lot of time and effort for the recruiters at the company to read possibly hundreds of resumes to find a suitable candidate. LÄS MER
4. Automatic Question Paraphrasing in Swedish with Deep Generative Models
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Paraphrase generation refers to the task of automatically generating a paraphrase given an input sentence or text. Paraphrase generation is a fundamental yet challenging natural language processing (NLP) task and is utilized in a variety of applications such as question answering, information retrieval, conversational systems etc. LÄS MER
5. Using Word Embedding to Generate Cloze Sentences
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Creating cloze sentences—contextual fill-in-the-blanks questions—can be time consuming and challenging. While research has been done on automatic question generation, a problem within this area is the high complexity of processing text and constructing relevant questions. LÄS MER