Many NLP tasks including machine comprehension, answer selection and text
entailment require the comparison between sequences. Matching the important
units between sequences is a key to solve these problems. In this paper, we
present a general "compare-aggregate" framework that performs word-level
matching followed by aggregation using Convolutional Neural Networks. We
particularly focus on the different comparison functions we can use to match
two vectors. We use four different datasets to evaluate the model. We find that
some simple comparison functions based on element-wise operations can work
better than standard neural network and neural tensor network.

本研究将词汇级别的比较和聚合作为一个一般的框架，以解决在 NLP 任务中，如机器理解、答案选择和文本蕴含等方面的序列匹配问题，并使用卷积神经网络来执行该框架。研究结果表明，某些基于逐元素操作的简单比较功能可以比标准神经网络和神经张量网络表现更佳。

一个用于文本序列匹配的比较和聚合模型

A Compare-Aggregate Model for Matching Text Sequences

In this paper, we proposed a sentence encoding-based model for recognizing
text entailment. In our approach, the encoding of sentence is a two-stage
process. Firstly, average pooling was used over word-level bidirectional LSTM
(biLSTM) to generate a first-stage sentence representation. Secondly, attention
mechanism was employed to replace average pooling on the same sentence for
better representations. Instead of using target sentence to attend words in
source sentence, we utilized the sentence's first-stage representation to
attend words appeared in itself, which is called "Inner-Attention" in our paper
. Experiments conducted on Stanford Natural Language Inference (SNLI) Corpus
has proved the effectiveness of "Inner-Attention" mechanism. With less number
of parameters, our model outperformed the existing best sentence encoding-based
approach by a large margin.

该论文提出了一种基于句子编码技术的模型，通过使用双向 LSTM 进行单词级别的平均池化生成第一阶段的句子表示，并采用注意力机制替代平均池化，以更好地表示文本蕴含关系。最终，通过对斯坦福自然语言推理语料库的实验验证了该模型具有较少的参数以及比现有最佳的句子编码方法更高的性能。