论文标题
从文本中重建地图
Reconstructing Maps from Text
论文作者
论文摘要
先前的研究表明，分销语义模型（DSM）能够重建新闻库中的地图（Louwerse＆Zwaan，2009年）和小说（Louwerse＆Benesh，2012年）。复制图的能力令人惊讶，因为DSM臭名昭著地缺乏感知的接地（De Vega等，2012）。在本文中，我们调查了语言中所需的统计来源来推断地图，并构成了语义表示机制的限制。研究1在实验控制下将单词共同出现带来，以证明语言中的直接同时出现对于传统的DSMS成功地繁殖地图是必要的。研究2提出了一个基于实例的DSM，该DSM能够重建与城市名称共发生频率的地图。
Previous research has demonstrated that Distributional Semantic Models (DSMs) are capable of reconstructing maps from news corpora (Louwerse & Zwaan, 2009) and novels (Louwerse & Benesh, 2012). The capacity for reproducing maps is surprising since DSMs notoriously lack perceptual grounding (De Vega et al., 2012). In this paper we investigate the statistical sources required in language to infer maps, and resulting constraints placed on mechanisms of semantic representation. Study 1 brings word co-occurrence under experimental control to demonstrate that direct co-occurrence in language is necessary for traditional DSMs to successfully reproduce maps. Study 2 presents an instance-based DSM that is capable of reconstructing maps independent of the frequency of co-occurrence of city names.
