论文标题
句法查看句子压缩的注意力网络
Syntactically Look-Ahead Attention Network for Sentence Compression
论文作者
论文摘要
句子压缩是通过删除冗余单词将长句子压缩成简短句子的任务。在基于序列到序列（SEQ2SEQ）模型中，解码器单向决定保留或删除单词。因此，它通常无法明确捕获解码单词与看不见的单词之间的关系，这些单词将在将来的时间步骤中解码。因此，为了避免产生不语法的句子，解码器有时会在压缩句子中掉下重要单词。为了解决这个问题，我们提出了一种新颖的SEQ2SEQ模型，即句法观察的注意力网络（Slahan），可以通过在解码和捕获将来将解码的重要单词中明确跟踪依赖性父母和子单词来产生信息的摘要。 Google句子压缩数据集对自动评估的结果表明，Slahan分别达到了最佳的基于token的F1，Rouge-1，Rouge-2和Rouge-L得分，分别为85.5、79.3、71.3和79.1。 Slahan还改善了较长句子的总结性能。此外，在人类评估中，斯拉汉（Slahan）提高了信息性而不会失去可读性。
Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words. In sequence-to-sequence (Seq2Seq) based models, the decoder unidirectionally decides to retain or delete words. Thus, it cannot usually explicitly capture the relationships between decoded words and unseen words that will be decoded in the future time steps. Therefore, to avoid generating ungrammatical sentences, the decoder sometimes drops important words in compressing sentences. To solve this problem, we propose a novel Seq2Seq model, syntactically look-ahead attention network (SLAHAN), that can generate informative summaries by explicitly tracking both dependency parent and child words during decoding and capturing important words that will be decoded in the future. The results of the automatic evaluation on the Google sentence compression dataset showed that SLAHAN achieved the best kept-token-based-F1, ROUGE-1, ROUGE-2 and ROUGE-L scores of 85.5, 79.3, 71.3 and 79.1, respectively. SLAHAN also improved the summarization performance on longer sentences. Furthermore, in the human evaluation, SLAHAN improved informativeness without losing readability.
