自然語言推理是NLP高級別的任務之一，不過自然語言推理包含的內容比較多，機器閱讀，問答系統和對話等本質上都屬於自然語言推理。最近在看AllenNLP包的時候，里面有個模塊：文本蘊含任務(text entailment)，它的任務形式是：
給定一個前提文本（premise），根據這個前提去推斷假說文本（hypothesis）與premise的關系，一般分為蘊含關系（entailment）和矛盾關系（contradiction），蘊含關系（entailment）表示從premise中可以推斷出hypothesis；矛盾關系（contradiction）即hypothesis與premise矛盾。文本蘊含的結果就是這幾個概率值。
Textual Entailment
Textual Entailment (TE) models take a pair of sentences and predict whether the facts in the first necessarily imply the facts in the second one. The AllenNLP TE model is a re-implementation of the decomposable attention model (Parikh et al, 2017), a widely used TE baseline that was state-of-the-art onthe SNLI dataset in late 2016. The AllenNLP TE model achieves an accuracy of 86.4% on the SNLI 1.0 test dataset, a 2% improvement on most publicly available implementations and a similar score as the original paper. Rather than pre-trained Glove vectors, this model uses ELMo embeddings, which are completely character based and account for the 2% improvement.
AllenNLP集成了EMNLP2016中谷歌作者們撰寫的一篇文章：A Decomposable Attention Model for Natural Language Inference
論文實踐
（1）測試例子一：
前提：Two women are wandering along the shore drinking iced tea.
假設：Two women are sitting on a blanket near some rocks talking about politics.
其測試結果如下：
可視化呈現結果如下：
測試例子二:
前提：If you help the needy, God will reward you.
假設：Giving money to the poor has good consequences.
測試結果如下：
