The Story Cloze Test (SCT) is a recent framework for evaluating story comprehension and script learning. There have been a variety of models tackling the SCT so far. Although the original goal behind the SCT was to require systems to perform deep language understanding and commonsense reasoning for successful narrative understanding, some recent models could perform significantly better than the initial baselines by leveraging human-authorship biases discovered in the SCT dataset. In order to shed some light on this issue, we have performed various data analysis and analyzed a variety of top performing models presented for this task. Given the statistics we have aggregated, we have designed a new crowdsourcing scheme that creates a new SCT dataset, which overcomes some of the biases. We benchmark a few models on the new dataset and show that the topperforming model on the original SCT dataset fails to keep up its performance. Our findings further signify the importance of benchmarking NLP systems on various evolving test sets.

Comparison is one of the most important phenomena in language for expressing objective and subjective facts about various entities. Systems that can understand and reason over comparative structure can play a major role in the applications which require deeper understanding of language. In this paper we present a novel semantic framework for representing the meaning of comparative structures in natural language, which models comparisons as predicate-argument pairs interconnected with semantic roles. Our framework supports not only adjectival, but also adverbial, nominal, and verbal comparatives. With this paper, we provide a novel dataset of gold-standard comparison structures annotated according to our semantic framework.

Domain-independent meaning representation of text has received a renewed interest in the NLP community. Comparison plays a crucial role in shaping objective and subjective opinion and measurement in natural language, and is often expressed in complex constructions including ellipsis. In this paper, we introduce a novel framework for jointly capturing the semantic structure of comparison and ellipsis constructions. Our framework models ellipsis and comparison as interconnected predicate-argument structures, which enables automatic ellipsis resolution. We show that a structured prediction model trained on our dataset of 2,800 gold annotated review sentences yields promising results. Together with this paper we release the dataset and an annotation tool which enables two-stage expert annotation on top of tree structures.

Understanding common entities and their attributes is a primary requirement for any system that comprehends natural language.In order to enable learning about common entities, we introduce a novel machine comprehension task, GuessTwo: given a short paragraph comparing different aspects of two realworld semantically-similar entities, a system should guess what those entities are. Accomplishing this task requires deep language understanding which enables inference, connecting each comparison paragraph to different levels of knowledge about world entities and their attributes. So far we have crowdsourced a dataset of more than 14K comparison paragraphs comparing entities from a variety of categories such as fruits and animals. We have designed two schemes for evaluation: open-ended, and binary-choice prediction. For benchmarking further progress in the task, we have collected a set of paragraphs as the test set on which human can accomplish the task with an accuracy of 94.2% on open-ended prediction. We have implemented various models for tackling the task, ranging from semantic-driven to neural models. The semantic-driven approach outperforms the neural models, however, the results indicate that the task is very challenging across the models.

No abstract