TY - GEN
T1 - Show me your evidence - An automatic method for context dependent evidence detection
AU - Rinott, Ruty
AU - Dankin, Lena
AU - Alzate, Carlos
AU - Khapra, Mitesh M.
AU - Aharoni, Ehud
AU - Slonim, Noam
N1 - Publisher Copyright:
© 2015 Association for Computational Linguistics.
PY - 2015
Y1 - 2015
N2 - Engaging in a debate with oneself or others to take decisions is an integral part of our day-today life. A debate on a topic (say, use of performance enhancing drugs) typically proceeds by one party making an assertion/claim (say, PEDs are bad for health) and then providing an evidence to support the claim (say, a 2006 study shows that PEDs have psychiatric side effects). In this work, we propose the task of automatically detecting such evidences from unstructured text that support a given claim. This task has many practical applications in decision support and persuasion enhancement in a wide range of domains. We first introduce an extensive benchmark data set taiiored for this task, which aifows training statisticai modefs and assessing their performance. Then, we suggest a system architecture based on supervised ieaming to address the evidence detection task. Finaify, promising experimentai resufts are reported.
AB - Engaging in a debate with oneself or others to take decisions is an integral part of our day-today life. A debate on a topic (say, use of performance enhancing drugs) typically proceeds by one party making an assertion/claim (say, PEDs are bad for health) and then providing an evidence to support the claim (say, a 2006 study shows that PEDs have psychiatric side effects). In this work, we propose the task of automatically detecting such evidences from unstructured text that support a given claim. This task has many practical applications in decision support and persuasion enhancement in a wide range of domains. We first introduce an extensive benchmark data set taiiored for this task, which aifows training statisticai modefs and assessing their performance. Then, we suggest a system architecture based on supervised ieaming to address the evidence detection task. Finaify, promising experimentai resufts are reported.
UR - http://www.scopus.com/inward/record.url?scp=84955292616&partnerID=8YFLogxK
U2 - 10.18653/v1/d15-1050
DO - 10.18653/v1/d15-1050
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:84955292616
T3 - Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing
SP - 440
EP - 450
BT - Conference Proceedings - EMNLP 2015
PB - Association for Computational Linguistics (ACL)
T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2015
Y2 - 17 September 2015 through 21 September 2015
ER -