论文标题
使用单词嵌入的隐喻解释
Metaphor Interpretation Using Word Embeddings
论文作者
论文摘要
我们建议使用在相对较大的语料库中训练的单词嵌入式的隐喻解释模型。我们的系统处理名义隐喻，例如“时间是金钱”。它生成了给定隐喻的潜在解释的排名列表。候选含义是从主题（“时间”）和车辆（“货币”）组件的搭配中得出的，这些组件会自动从依赖性优先级的语料库中提取。我们探索添加源自单词关联规范的候选者（人类对线索的共同反应）。我们的排名程序考虑了在语义向量空间中测量的候选解释和隐喻组件之间的相似性。最后，一种聚类算法消除了语义上相关的重复项，从而允许其他候选人解释获得更高的排名。我们使用不同的带注释的隐喻来评估，并令人鼓舞的初步结果。
We suggest a model for metaphor interpretation using word embeddings trained over a relatively large corpus. Our system handles nominal metaphors, like "time is money". It generates a ranked list of potential interpretations of given metaphors. Candidate meanings are drawn from collocations of the topic ("time") and vehicle ("money") components, automatically extracted from a dependency-parsed corpus. We explore adding candidates derived from word association norms (common human responses to cues). Our ranking procedure considers similarity between candidate interpretations and metaphor components, measured in a semantic vector space. Lastly, a clustering algorithm removes semantically related duplicates, thereby allowing other candidate interpretations to attain higher rank. We evaluate using different sets of annotated metaphors, with encouraging preliminary results.
