Papers with Word embedding methods
Building Location Embeddings from Physical Trajectories and Textual Representations (2020.aacl-main)
Copied to clipboard
| Challenge: | Using a dataset consisting of the location trajectories of 729 students over a seven month period, we investigate whether embeddings can represent aspects such as location presence or location functionality. |
| Approach: | They propose to use location embeddings to generate embeddables of sequences of locations a student has visited to identify surface properties captured in the representations. |
| Outcome: | The proposed models can be used to predict depression levels and area of study, and can be applied to complex tasks such as predicting area of studies and depression levels. |
Enhancing Out-of-Vocabulary Estimation with Subword Attention (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to learn OOV word representations use advanced architectures like attention on the context of the word, but they tend to use simple structures like ngram addition or character based convolutional neural networks (CNN) |
| Approach: | They propose a transformer-based OOV estimation model that uses attention mechanisms on both the context and the subwords to learn OOV representations. |
| Outcome: | The proposed model outperforms current state-of-the-art models on OOV representations based on attention mechanisms on the context and subwords . |
Are Embedding Spaces Interpretable? Results of an Intrusion Detection Evaluation on a Large French Corpus (2022.lrec-1)
Copied to clipboard
| Challenge: | Word embedding methods use word co-occurrences to encode, syntactic and semantic information to describe vocabulary in a low-dimensional space. |
| Approach: | They evaluate word embedding interpretability using two methods . they use a word-in-space vector encoder and graph-based method SPINE . |
| Outcome: | The proposed methods show that they can be interpretable on a large French corpus. |