Blar i NTNU Open på forfatter "Gambäck, Björn"

Deep Detection of Hate Speech in Text Through a Two-Pronged Approach

Meyer, Johannes Skjeggestad (Master thesis, 2018)

With the widespread use of online services like Facebook and Twitter, disseminating hateful messages has become a simple matter. These messages not only spoil the experience for other users of a service. There is also an ...

Distant Supervision and Sentiment Embeddings for Ternary Twitter Sentiment Analysis

Lichtenberg, Frederik Gørvell de; Byrkjeland, Mats (Master thesis, 2017)

Tang et al. (2014) acknowledged the context-based word embeddings inability to dis-criminate between words with opposite sentiments that appear in similar contexts. Anexample is the words good and bad two opposites ...

Distributional Semantic Models for Clinical Text Applied to Health Record Summarization

Moen, Hans (Doctoral thesis at NTNU;2016:134, Doctoral thesis, 2016)

As information systems in the health sector are becoming increasingly computerized, large amounts of care-related information are being stored electronically. In hospitals clinicians continuously document treatment and ...

Generating Blues Solos with Variational Autoencoders

Sandberg, Eirik Katnosa (Master thesis, 2018)

This thesis describes the design and implementation of a variational autoencoder that generates blues solos. The architecture of the variational autoencoder is capable of capturing long-term dependencies in musical data, ...

Generating Novel Compounds in Technical Translations

Orvedal, Maren Helene (Master thesis, 2020)

Samansetjingar er leksem som er samansette av fleire ledd. Prinsipielt sett er det mogleg å forme eit uendeleg antal samansette ord, og det er derfor umogleg å ramsa opp alle moglege samansetjingar i eit leksikon. Når ein ...

Generering av en navnedatabase for kinesiske tegn i japanske navn med utgangspunkt i Wikipedia

Holdaas, Lars Alexander (Master thesis, 2016)

Å finne den korrekte måten å uttale et japansk navn skrevet med kinesiske tegn er en utfordring for både de som studerer japansk såvel som de som har japansk som morsspråk. I japanske navn kan kinesiske tegn uttalles på ...

Guiding the training of Generative Adversarial Networks

Selseng, Simen (Master thesis, 2017)

Image generation with Artificial Neural Networks (ANNs) has been popular in the last few years by using the knowledge about objects and structures to generate dreamlike images, applying smart filters or making images appear ...

Identifying Languages at the Word Level in Code-Mixed Indian Social Media Text

Das, Amitava; Gambäck, Björn (Proceedings of the 11th International Conference on Natural Language Processing;52, Chapter; Conference object, 2014)

Language identification at the document level has been considered an almost solved problem in some application areas, but language detectors fail in the social media context due to phenomena such as ...

Identifying Sarcasm in English and Norwegian Twitter Messages

Trelease, Hanne Marie (Master thesis, 2017)

Twitter is today a very popular microblogging platform with vast amounts of available data. This has created an interest in collecting information from Twitter data, for example in the form of sentiment analysis. Natural ...

Information Maximizing and Pattern-Producing Generative Adversarial Networks

Ekern, Erlend Gjesteland (Master thesis, 2019)

En rekke teknologiske fremskritt og innovasjoner har dukket opp innenfor forskningsområdet rundt generative modeller i løpet av de siste årene. Denne typen modeller benytter seg ofte av kunstige nevrale nettverk som et ...

Investigating the Effects of User Features in Hate Speech Detection on Twitter

Unsvåg, Elise Fehn (Master thesis, 2018)

Detecting hate speech has become an increasingly important task for online communities. Current methods for handling such unintended content are often heavily dependent on manual effort, and are therefore not scalable or ...

Multi-Domain Adapted Machine Translation Using Unsupervised Text Clustering

Bungum, Lars; Gambäck, Björn (LNCS;, Chapter; Conference object; Peer reviewed, 2015)

Domain Adaptation in Machine Translation means to take a machine translation system that is restricted to work in a specific context and to enable the system to translate text from a different domain. The paper presents a ...

Multilingual Poetry Generation

Vincent, Rémi (Master thesis, 2019)

I krysset mellom Natural Language Processing and Computational Creativity er diktgenerering en sammensatt oppgave, delvis på grunn av de forskjellige formene den kan ta og subjektiviteten til evalueringen. På grunn av deres ...

Negation Scope Detection for Twitter Sentiment Analysis

Reitan, Johan; Faret, Jørgen; Gambäck, Björn; Bungum, Lars (Chapter; Conference object, 2015)

NIT_Agartala_NLP_Team at SemEval-2019 Task 6: An Ensemble Approach to Identifying and Categorizing Offensive Language in Twitter Social Media Corpora

Swamy, Steve Durairaj; Jamatia, Anupam; Gambäck, Björn; Das, Amitava (Chapter, 2019)

The paper describes the systems submitted to OffensEval (SemEval 2019, Task 6) on ‘Identifying and Categorizing Offensive Language in Social Media’ by the ‘NIT_Agartala_NLP_Team’. A Twitter annotated dataset of 13,240 ...

Once More, with Feeling - Computer Generated Poetry with Inherent Sentiment

Røstvold, Kasper Aalberg (Master thesis, 2019)

Denne masteroppgaven presenterer implementasjonen og evalueringen av et system som kan generere poesi med et forhåndsbestemt sentiment. Poesigenerering er en av de mer interessante utfordringenge innenfor feltene Naturlig ...

Open-Domain Word-Level Interpretation of Norwegian: Towards a General Encyclopedic Question-Answering System for Norwegian

Ranang, Martin Thorsen (Doctoral Theses at NTNU, 1503-8181; 2010:11, Doctoral thesis, 2010)

No large-scale, open-domain semantic resource for Norwegian, with a rich number of semantic relations currently exists. The existing semantic resources for Norwegian are either limited in size and/or incompatible with the ...