# Gated Word-Character Recurrent Language Model Source: [Gated Word-Character Recurrent Language Model]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:32.405Z Authors: Yasumasa Miyamoto, Kyunghyun Cho Published: 2016-06-06T11:43:28.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Tag Prediction on Twitter dataset](): Tag prediction; Twitter dataset; Precision@1: 29.74. ## Original sources and implementation [Original paper]() [PDF]()