Learning Sentence Ordering for Opinion Generation of Debate

Proceedings of the 2nd Workshop on Argumentation Mining, pages 94–103, Denver, Colorado, June 4, 2015. c⃝2015 Association for Computational Linguistics Learning Sentence Ordering for Opinion Generation of Debate Toshihiko Yanase Toshinori Miyoshi Research & Development Group, Hitachi, Ltd. {toshihiko.yanase.gm, toshinori.miyoshi.pd, kohsuke.yanai.cs, misa.sato.mw} @hitachi.com Kohsuke Yanai Misa Sato Makoto Iwayama Yoshiki Niwa Research & Development Group, Hitachi, Ltd. {makoto.iwayama.nw, yoshiki.niwa.tx} @hitachi.com Paul Reisert Kentaro Inui Tohoku University {preisert, inui}@ecei.tohoku.ac.jp Abstract We propose a sentence ordering method to help compose persuasive opinions for debat- ing. In debate texts, support of an opinion such as evidence and reason typically follows the main claim. We focused on this claim- support structure to order sentences, and de- veloped a two-step method. First, we select from among candidate sentences a first sen- tence that is likely to be a claim. Second, we order the remaining sentences by using a ranking-based method. We tested the effec- tiveness of the proposed method by compar- ing it with a general-purpose method of sen- tence ordering and found through experiment that it improves the accuracy of first sentence selection by about 19 percentage points and had a superior performance over all metrics. We also applied the proposed method to a con- structive speech generation task. 1 Introduction There are increasing demands for information struc- turing technologies to support decision making us- ing a large amount of data. Argumentation in debat- ing which composes texts in a persuasive manner is a research target suitable for such information struc- turing. In this paper, we discuss sentence ordering for constructive speech generation of debate. The following is an example of constructive speech excerpts that provide affirmative opinions on the banning of gambling1. 1This example is excerpted from De- batabase (http://idebate.org/debatabase). Copyright 2005 Motion: This House should ban gambling. (1) Poor people are more likely to gamble, in the hope of getting rich. (2) In 1999, the National Gambling Im- pact Commission in the United States found that 80 percent of gambling revenue came from lower-income households. We can observe a typical structure of constructive speech in this example. The first sentence describes a claim that is the main statement of the opinion and the second sentence supports the main statement. In this paper, we focus on this claim-support structure to order sentences. Regarding the structures of arguments, we can find research on the modeling of arguments (Free- ley and Steinberg, 2008) and on recognition such as claim detection (Aharoni et al., 2014). To the best of our knowledge, there is no research that exam- ines the claim-support structure of debate texts for the sentence ordering problem. Most of the pre- vious works on sentence ordering (Barzilay et al., 2002; Lapata, 2003; Bollegala et al., 2006; Tan et al., 2013) focus on the sentence order of news ar- ticles and do not consider the structures of argu- ments. These methods mingle claim and supportive sentences together, which decreases the persuasive- ness of generated opinions. In this paper, we propose a sentence ordering method in …

Content truncated to 500 words