How Factuality Determines Sentiment Inferences

Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics (*SEM 2016), pages 75–84, Berlin, Germany, August 11-12, 2016. How Factuality Determines Sentiment Inferences Manfred Klenner and Simon Clematide Computational Linguistics University of Zurich, Switzerland {klenner|siclemat}@cl.uzh.ch Abstract In a complex sentence comprised of one or more subclauses, the overt or hidden atti- tudes between the various entities depend on the factuality projection of the verbs, their polar effects, and the modality and affirmative status (negated or not) of the clauses. If factuality is given, some refer- ents might even be considered to benefit or to suffer from the (effects of the) described situation, independently of their relations to the other referents. An interesting ques- tion is, how the reader evaluates all this from his/her perspective. We introduce an approach based on Description Logics that integrates these various perspectives into a joint model. 1 Introduction Sentences can express a positive or negative re- lationship between people, organizations, and na- tions etc. For instance, in the sentence “the EU supports Greece”, a positive attitude of the EU towards Greece is expressed. At the same time, a positive effect that is meant to be true, is as- serted. That is, Greece benefits from the situa- tion described. If the reader has a negative atti- tude towards the beneficiary (Greece), he might regard the apparent benefactor (EU) as his oppo- nent. However, if the sentence is embedded into a non-factive verb like “to pretend” (“The EU pre- tends to support Greece”), neither the positive re- lationship between the referents nor the positive effect on Greece hold any longer. Instead, the ma- trix verb “to pretend” casts a negative effect on the EU. If the reader adheres to this common sense verb connotation, he will adopt the negative at- titude towards the EU. Furthermore, if some ac- tor criticizes that the EU supports Greece, factu- ality of the embedded clause is given (compared to “pretend”). Thus, the positive effect on Greece still takes place, but now there is a negative at- titude of this actor of the matrix clause towards both referents of the complement clause. Finally, if an actor criticizes that the EU does not support Greece, his attitude towards Greece is positive (but negative towards the EU). Given a text, we would like to be able to answer the following questions: What is good or bad for the entities mentioned in the text? What is good or bad of these entities? What are the attitudes of the entities towards each other? And last but not least, what follows from the reader’s stance, i.e. his prior attitudes towards some entities? A user of our system then could mine texts for proponents and opponents of his, in the sense that entities that do things (or like others that) he likes are proponents, and entities that act in the opposite way (or like others he dislikes) are opponents. In contrast to existing work (e.g. Deng and Wiebe (2015)), we stress the point that verb sig- …

Content truncated to 500 words