Gated Word-Character Recurrent Language Model

TL;DR

This paper presents a novel recurrent neural network language model that combines character-level and word-level inputs through a gating mechanism, improving performance on rare and out-of-vocabulary words.

Contribution

The introduction of a gating mechanism that adaptively combines character and word representations in an LSTM language model is a new approach.

Findings

Outperforms traditional word-level models on multiple English corpora.

Effectively handles rare and OOV words using character-level inputs.

Gating mechanism improves overall language modeling accuracy.

Abstract

We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has a gate that adaptively finds the optimal mixture of the character-level and word-level inputs. The gate creates the final vector representation of a word by combining two distinct representations of the word. The character-level inputs are converted into vector representations of words using a bidirectional LSTM. The word-level inputs are projected into another high-dimensional space by a word lookup table. The final vector representations of words are used in the LSTM language model which predicts the next word given all the preceding words. Our model with the gating mechanism effectively utilizes the character-level inputs for rare and out-of-vocabulary words and outperforms word-level language models on several English corpora.