Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
复制标题
DOI：
10.18653/v1/n19-1368
复制
发表时间：
2019-04
期刊：
影响因子：
--
通讯作者：
Debjit Paul;A. Frank
中科院分区：
文献类型：
--
作者：
Debjit Paul;A. Frank
为了让机器更好地理解情感，研究需要从极性识别转向理解情感表达背后的原因。对人类的目标或需求进行分类是解释文本中情感表达的一种方法。人类擅长理解用自然语言描述的情况，并可以使用常识知识轻松地将它们与角色的心理需求联系起来。我们提出了一种新的方法来提取，排名，过滤和选择多跳的关系路径从常识知识资源来解释他们的基本人类需求方面的情感表达。我们有效地将获得的知识路径整合到一个神经模型中，该模型使用门控注意机制将上下文表示与知识连接起来。我们评估模型的性能最近公布的数据集分类人类的需求。选择性地整合知识路径提高了性能，并建立了一个新的国家的最先进的。我们的模型提供了可解释性，通过学习的注意力地图常识知识路径。人类评价突出了编码知识的相关性。
To make machines better understand sentiments, research needs to move from polarity identification to understanding the reasons that underlie the expression of sentiment. Categorizing the goals or needs of humans is one way to explain the expression of sentiment in text. Humans are good at understanding situations described in natural language and can easily connect them to the character’s psychological needs using commonsense knowledge. We present a novel method to extract, rank, filter and select multi-hop relation paths from a commonsense knowledge resource to interpret the expression of sentiment in terms of their underlying human needs. We efficiently integrate the acquired knowledge paths in a neural model that interfaces context representations with knowledge using a gated attention mechanism. We assess the model’s performance on a recently published dataset for categorizing human needs. Selectively integrating knowledge paths boosts performance and establishes a new state-of-the-art. Our model offers interpretability through the learned attention map over commonsense knowledge paths. Human evaluation highlights the relevance of the encoded knowledge.