Command Palette
Search for a command to run...
Yue Zhang; Qi Liu; Linfeng Song
Abstract
Bi-directional LSTMs are a powerful tool for text representation. On the other hand, they have been shown to suffer various limitations due to their sequential nature. We investigate an alternative LSTM structure for encoding text, which consists of a parallel state for each word. Recurrent steps are used to perform local and global information exchange between words simultaneously, rather than incremental reading of a sequence of words. Results on various classification and sequence labelling benchmarks show that the proposed model has strong representation power, giving highly competitive performances compared to stacked BiLSTM models with similar parameter numbers.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| named-entity-recognition-ner-on-conll-2003 | S-LSTM | F1: 91.57 |
| part-of-speech-tagging-on-penn-treebank | S-LSTM | Accuracy: 97.55 |
| sentiment-analysis-on-imdb | S-LSTM | Accuracy: 87.15 |
| sentiment-analysis-on-mr | S-LSTM | Accuracy: 76.2 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.