A large annotated corpus for learning natural language inference

2 A new corpus for NLI

1. How does event coreference make NLI labels indeterminate? Give an example.
   “A boat sank in the Pacific Ocean” / “A boat sank in the Atlantic Ocean” is a contradiction if both describe the same event, neutral otherwise. Assuming coreference everywhere makes unrelated pairs contradictions; never assuming it leaves contradictions only for universal claims.
   • Bowman et al., 2015, A large annotated corpus for learning natural language inference (Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP)), §2, pp. 633–634
2. How did SNLI’s collection method control coreference indeterminacy?
   Both sentences describe the same grounded scenario (a photo) from the same perspective: workers saw an image caption (not the photo) and wrote new captions about that same scene, so entities and events are naturally taken to corefer.
   • Bowman et al., 2015, A large annotated corpus for learning natural language inference (Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP)), §2, pp. 633–634