Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network
|저자 :||Martin Gleize Eyal Shnarch Leshem Choshen Lena Dankin GUY MOSHKOWICH Ranit Aharonov Noam Slonim|
|태그 :||Computer Science Machine Learning|
3. Siamese Network
4. The IBM-EviConv data set
-- 4.1. Data set quality
-- 5.1. Experiments over UKPConvArgStrict and UKPConvArgRank
-- 5.2. Experiments over IMB-EviConv
-- 6.1. Performance across preference reasons
-- 6.2. What makes a convincing evidence?
-- 6.3. Cross vs. same stance evidence pairs
-- 6.4. The effect of length difference
7. Discussion and future work
|With the advancement in argument detection, we suggest to pay more attention to the challenging task of identifying the more convincing arguments. Machines capable of responding and interacting with humans in helpful ways have become ubiquitous. We now expect them to discuss with us the more delicate questions in our world, and they should do so armed with effective arguments. But what makes an argument more persuasive? What will convince you? In this paper, we present a new data set, IBM-EviConv, of pairs of evidence labeled for convincingness, designed to be more challenging than existing alternatives. We also propose a Siamese neural network architecture shown to outperform several baselines on both a prior convincingness data set and our own. Finally, we provide insights into our experimental results and the various kinds of argumentative value our method is capable of detecting.