Advanced search
Showing result 1 - 5 of 13 essays matching the above criteria.
-
1. Ensuring Brand Safety by Using Contextual Text Features: A Study of Text Classification with BERT
University essay from Uppsala universitet/Institutionen för lingvistik och filologiAbstract : When advertisements are placed on web pages, the context in which the advertisements are presented is important. For example, manufacturers of kitchen knives may not want their advertisement to appear in a news article about a knife-wielding murderer. READ MORE
-
2. Enhancing failure prediction from timeseries histogram data : through fine-tuned lower-dimensional representations
University essay from Högskolan i Halmstad/Akademin för informationsteknologiAbstract : Histogram data are widely used for compressing high-frequency time-series signals due to their ability to capture distributional informa-tion. However, this compression comes at the cost of increased di-mensionality and loss of contextual details from the original features. READ MORE
-
3. Optimizing the Performance of Text Classification Models by Improving the Isotropy of the Embeddings using a Joint Loss Function
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Recent studies show that the spatial distribution of the sentence representations generated from pre-trained language models is highly anisotropic, meaning that the representations are not uniformly distributed among the directions of the embedding space. Thus, the expressiveness of the embedding space is limited, as the embeddings are less distinguishable and less diverse. READ MORE
-
4. Exploring Transformer-Based Contextual Knowledge Graph Embeddings : How the Design of the Attention Mask and the Input Structure Affect Learning in Transformer Models
University essay from Linköpings universitet/Artificiell intelligens och integrerade datorsystemAbstract : The availability and use of knowledge graphs have become commonplace as a compact storage of information and for lookup of facts. However, the discrete representation makes the knowledge graph unavailable for tasks that need a continuous representation, such as predicting relationships between entities, where the most probable relationship needs to be found. READ MORE
-
5. The role of working from home within the context of family-friendly work policies and its relationship to firm performance: Implications for managers
University essay from Lunds universitet/Företagsekonomiska institutionenAbstract : Purpose: The purpose of this study is to investigate the role of working from home within family friendly work policies (FFWPs) and its relationship to firm performance, and whether this is affected by the choice of management practices within an organization. Methodology: A cross-sectional dataset from 2004, including data from 732 firms and four countries, accessed through World Management Survey was used in this explorative study. READ MORE