Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings

TL;DR

This paper introduces a meta-BiLSTM model that enhances morphosyntactic tagging by integrating context-sensitive token encodings, achieving state-of-the-art results across multiple languages.

Contribution

It proposes a novel meta-model that combines context-aware token representations with recurrent neural networks for improved tagging accuracy.

Findings

State-of-the-art performance on multiple languages.

Optimal results achieved with synchronized training of representations.

Context-sensitive encodings improve tagging accuracy.

Abstract

The rise of neural networks, and particularly recurrent neural networks, has produced significant advances in part-of-speech tagging accuracy. One characteristic common among these models is the presence of rich initial word encodings. These encodings typically are composed of a recurrent character-based representation with learned and pre-trained word embeddings. However, these encodings do not consider a context wider than a single word and it is only through subsequent recurrent layers that word or sub-word information interacts. In this paper, we investigate models that use recurrent neural networks with sentence-level context for initial character and word-based representations. In particular we show that optimal results are obtained by integrating these context sensitive representations through synchronized training with a meta-model that learns to combine their states. We present results on part-of-speech and morphological tagging with state-of-the-art performance on a number of languages.