Papers by Andrew Schneider
COIN – an Inexpensive and Strong Baseline for Predicting Out of Vocabulary Word Embeddings (2022.coling-1)
Copied to clipboard
| Challenge: | Word embedding models only include terms that occur a sufficient number of times in training corpora. |
| Approach: | They propose a method for predicting word embeddings for out of vocabulary terms using word2vec. |
| Outcome: | The proposed method surpasses several methods on benchmark tasks and is inexpensive to compute. |
DebugSL: An Interactive Tool for Debugging Sentiment Lexicons (N18-5)
Copied to clipboard
| Challenge: | Existing studies have shown that polarity disagreements between SLs can negatively impact SA tasks. |
| Approach: | They propose to use a visual debugging tool for sentiment lexicons to detect polarity inconsistencies in SLs. |
| Outcome: | The proposed tool detects inconsistencies of small sizes and has a rich user interface which helps users in the correction process. |