This paper develops a model that addresses sentence embedding using recurrent neural networks (RNN) with Long Short Term Memory (LSTM) cells. The proposed LSTM-RNN model sequentially takes each word in a sentence, extracts its information, and embeds it into a semantic vector. Due to its ability to capture long term memory, the LSTM-RNN accumulates increasingly richer information as it goes through the sentence, and when it reaches the last word, the hidden layer of the network provides a semantic representation of the whole sentence. In this paper, the LSTM-RNN is trained in a weakly supervised manner on user click-through data logged by a commercial web search engine. Visualization and analysis are performed to understand how the embedding process works. The model automatically attenuates the unimportant words and detects the salient keywords in the sentence. Furthermore, these detected keywords automatically activate different cells of the LSTM-RNN, where words belonging to a similar topic activate the same cell. As a semantic representation of the sentence, the embedding vector can be used in many different applications. These keyword detection and topic allocation tasks enabled by the LSTM-RNN allow the network to perform web document retrieval, where the similarity between the query and documents can be measured by the distance between their corresponding sentence embedding vectors computed by the LSTM-RNN. On a web search task, the LSTM-RNN embedding is shown to significantly outperform all existing state of the art methods.

本文提出了一种基于循环神经网络和长短时记忆单元的句子嵌入模型，该模型能够自动侦测句子中关键词和主题，从而进行网络文档检索等艰难的语言处理任务，并在性能上显著优于现有的先进方法。

使用长短期记忆网络的深度句子嵌入：分析和在信息检索中的应用