Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
Learning a semantic lexicon is often an important first step in building a system that learns to interpret the meaning of natural language. It is especially important in language grounding where the training data usually consist of language paired with an ambiguous perceptual context. Recent work by Chen and Mooney (2011) introduced a lexicon learning method that deals with ambiguous relational data by taking intersections of graphs. | Fast Online Lexicon Learning for Grounded Language Acquisition David L. Chen Department of Computer Science The University of Texas at Austin 1616 Guadalupe Suite 2.408 Austin TX 78701 USA dlcc@cs.utexas.edu Abstract Learning a semantic lexicon is often an important first step in building a system that learns to interpret the meaning of natural language. It is especially important in language grounding where the training data usually consist of language paired with an ambiguous perceptual context. Recent work by Chen and Mooney 2011 introduced a lexicon learning method that deals with ambiguous relational data by taking intersections of graphs. While the algorithm produced good lexicons for the task of learning to interpret navigation instructions it only works in batch settings and does not scale well to large datasets. In this paper we introduce a new online algorithm that is an order of magnitude faster and surpasses the state-of-the-art results. We show that by changing the grammar of the formal meaning representation language and training on additional data collected from Amazon s Mechanical Turk we can further improve the results. We also include experimental results on a Chinese translation of the training data to demonstrate the generality of our approach. 1 Introduction Learning to understand the semantics of human languages has been one of the ultimate goals of natural language processing NLP . Traditional learning approaches have relied on access to parallel corpora of natural language sentences paired with their meanings Mooney 2007 Zettlemoyer and Collins 2007 Lu et al. 2008 Kwiatkowski et al. 2010 . However constructing such semantic annotations can be 430 difficult and time-consuming. More recently there has been work on learning from ambiguous supervision where a set of potential sentence meanings are given only one or a small subset of which are correct Chen and Mooney 2008 Liang et al. 2009 Bordes et al. 2010 Chen and Mooney 2011 . Given the .
