新聞立場辨識任務的目的為判斷一篇新聞對於某個議題的立場是中立、贊成或反對。 此項任務與自然語言推理 (Natural Language Inference, NLI) 任務類似，目標在給定兩 個句子，判斷兩者之間是否無關或存在蘊涵、矛盾關係。本論文以新聞立場檢索競賽 提供的資料作為參考，但其大部分的新聞文章都屬於支持特定議題的立場，造成資料 在不同類別的分佈不平衡。本篇論文提出 Hierarchical Decomposable Attention Model 來解決新聞立場辨識任務，我們以句子為單位分割新聞文章，並基於 Decomposable Attention 的原理找出文章中的每個句子與特定議題的關係。針對資料不平衡的問題， 我們建立反義的議題，並手動標記新聞對反義議題的立場，以改善模型效能。實驗結果顯示，我們提出的模型效能優於其他模型。 The goal of News Stance Detection task is to identify whether the stance of a news article is neutral, partial approval or opposition with respect to a given query. The task is similar to Natural Language Inference (NLI) task, which aims to determine if one given statement (a premise) semantically entails another given statement (a hypothesis). Besides, most news articles hold neutral stances with respect to the given query, leading to an unbalanced training dataset, which is also a challenge of this task. In this paper, we proposed a Hierarchical Decomposable Attention Model to solve News Stance Detection task, which is based on the Decomposable Attention Model for NLI tasks and the hierarchical way to deal with discourse. For the data imbalance problem, we heuristically create opposite queries and label supporting news articles from unrelated one of the original query. This mechanism improves the model to identify unrelated news articles. The experiment result showed that the performance of our architecture is better than other models.