The LSDSem’17 shared task is the Story Cloze Test, a new evaluation for story understanding and script learning. This test provides a system with a four-sentence story and two possible endings, and the system must choose the correct ending to the story. Successful narrative understanding (getting closer to human performance of 100%) requires systems to link various levels of semantics to common...

Reading comprehension has embraced a booming in recent NLP research. Several institutes have released the Cloze-style reading comprehension data, and these have greatly accelerated the research of machine comprehension. In this work, we firstly present Chinese reading comprehension datasets, which consist of People Daily news dataset and Children’s Fairy Tale (CFT) dataset. Also, we propose a c...

Cloze tests have been widely used for measuring reading comprehension, readability and language proficiency. There is still much controversy on what it really is that cloze measures. The result of much correlational research is contradictory and very unsatisfactory. Thus, with a qualitative orientation, this study attempts to look at the judgmental validity of cloze as a test of reading compreh...

We present two NLP components for the Story Cloze Task – dictionary-based sentiment analysis and lexical cohesion. While previous research found no contribution from sentiment analysis to the accuracy on this task, we demonstrate that sentiment is an important aspect. We describe a new approach, using a rule that estimates sentiment congruence in a story. Our sentiment-based system achieves str...

Fill-in-the-blank questions, or cloze items, are commonly used in language learning applications. The benefits of personalized items, tailored to the user’s interest and proficiency, have motivated research on automatic generation of cloze items. This paper is concerned with generating cloze items for prepositions, whose usage often poses problems for non-native speakers of English. The quality...

Does producing a word slow performance of a concurrent, unrelated task? In 2 experiments, 108 participants named pictures and discriminated tones. In Experiment 1, pictures were named after cloze sentences; the durations of the word-production stages of lemma and phonological word-form selection were manipulated with high- and low-constraint cloze sentences and high- and low-frequency-name pict...

This study aims to examine when and how readers make use of top-down information to predict or integrate upcoming words by utilizing the characteristics of Chinese classifier-noun agreement, as measured by event-related potentials (ERPs). Constraint strength of classifiers (strong and weak) and cloze probability of the pairing noun (high, low, implausible) was manipulated. Weakly constrained cl...

Most of the previous work on cloze prediction focused on grammar testing such as preposition generation. In this paper we explore a different problem on knowledge testing by designing a system to automatically generate blanks for cloze test. We present a cross-document Information Extraction (IE) driven approach, and compare its performance on two different tasks with and without background doc...

Linguists have suggested that one mechanism for the creative extension of meaning in language involves mapping, or constructing correspondences between conceptual domains. For example, the sentence, "The clever boys used a cardboard box as a boat," sets up a novel mapping between the concepts cardboard box and boat, while "His main method of transportation is a boat," relies on a more conventio...

The automatic induction of scripts (Schank and Abelson, 1977) has been the focus of many recent works. In this paper, we employ a variety of these methods to learn Schank and Abelson’s canonical restaurant script, using a novel dataset of restaurant narratives we have compiled from a website called “Dinners from Hell.” Our models learn narrative chains, script-like structures that we evaluate w...