arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.01700cs.CL
收藏

门控词-字符递归语言模型

Gated Word-Character Recurrent Language Model

Center for Data Science(数据科学中心);New York University(纽约大学)

Yasumasa Miyamoto, Kyunghyun Cho

摘要:

我们引入了一个具有长短期记忆(LSTM)单元的递归神经网络语言模型(RNN-LM),该单元利用字符级和单词级输入。我们的模型有一个门,自适应地找到字符级和单词级输入的最佳混合。门通过组合单词的两个不同表示来创建单词的最终矢量表示。使用双向LSTM将字符级输入转换为单词的向量表示。词级输入通过词查找表投影到另一个高维空间。单词的最终向量表示用于LSTM语言模型,该模型预测给定所有前面单词的下一个单词。我们的模型与门控机制有效地利用字符级输入的罕见和词汇外的单词,并优于词级语言模型在几个英语语料库。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑