Junta Mizuno

Leveraging Diverse Lexical Resources for Textual Entailment Recognition

Since the problem of textual entailment recognition requires capturing semantic relations between diverse expressions of language, linguistic and world knowledge play an important role. In this article, we explore the effectiveness of different types of currently available resources including synonyms, antonyms, hypernym-hyponym relations, and lexical entailment relations for the task of textual entailment recognition. In order to do so, we develop an entailment relation recognition system which utilizes diverse linguistic analyses and resources to align the linguistic units in a pair of texts and identifies entailment relations based on these alignments. We use the Japanese subset of the NTCIR-9 RITE-1 dataset for evaluation and error analysis, conducting ablation testing and evaluation on hand-crafted alignment gold standard data to evaluate the contribution of individual resources. Error analysis shows that existing knowledge sources are effective for RTE, but that their coverage is limited, especially for domain-specific and other low-frequency expressions. To increase alignment coverage on such expressions, we propose a method of alignment inference that uses syntactic and semantic dependency information to identify likely alignments without relying on external resources. Evaluation adding alignment inference to a system using all available knowledge sources shows improvements in both precision and recall of entailment relation recognition.

A Corpus Study for Identifying Evidence on Microblogs

Microblogs are a popular way for users to communicate and have recently caught the attention of researchers in the natural language processing (NLP) field. However, regardless of their rising popularity, little attention has been given towards determining the properties of discourse relations for the rapid, large-scale microblog data. Therefore, given their importance for various NLP tasks, we begin a study of discourse relations on microblogs by focusing on evidence relations. As no annotated corpora for evidence relations on microblogs exist, we conduct a corpus study to identify such relations on Twitter, a popular microblogging service. We create annotation guidelines, conduct a large-scale annotation phase, and develop a corpus of annotated evidence relations. Finally, we report our observations, annotation difficulties, and data statistics.

Semantic Annotation of Japanese Functional Expressions and its Impact on Factuality Analysis

Recognizing the meaning of functional expressions is essential for natural language understanding. This is a difficult task, owing to the lack of a sufficient corpus for machine learning and evaluation. In this study, we design a new annotation scheme and construct a corpus containing 2,327 Japanese sentences and 8,775 functional expressions. Our scheme achieves high inter-annotator agreement with kappa score of 0.85. In the experiments, we confirmed that machine learning-based functional expression analysis contributes to factuality analysis.

Evidence in automatic error correction improves learners' english skill

Mastering proper article usage, especially in the English language, has been known to pose an extreme challenge to non-native speakers whose L1 languages have no concept of articles. Although the development of correction methods for article usage has posed a challenge for researchers, current methods do not perfectly correct the articles. In addition, proper article usage is not taught by these methods. Therefore, they are not useful for those wishing to learn a language with article usage. In this paper, we discuss the necessity of presenting evidence for corrections of English article usage. We demonstrate the effectiveness of this approach to improve the writing skills of English learners.

Organizing Information on the Web through Agreement-Conflict Relation Classification

The vast amount of information on the Web makes it difficult for users to comprehensively survey the various viewpoints on topics of interest. To help users cope with this information overload, we have developed an Information Organization System that applies state-of-the-art technology from Recognizing Textual Entailment to automatically detect Web texts that are relevant to natural language queries and organize them into agreeing and conflicting groups. Users are presented with a bird’s-eye-view visualization of the viewpoints on their queries that makes it easier to gain a deeper understanding of an issue. In this paper, we describe the implementation of our Information Organization System and evaluate our system through empirical analysis of the semantic relation recognition system that classifies texts and through a large-scale usability study. The empirical evaluation and usability study both demonstrate the usefulness of our system. User feedback further shows that by exposing our users to differing viewpoints promotes objective thinking and helps to reduce confirmation bias.

Mining False Information on Twitter for a Major Disaster Situation

Social networking services (SNS), such as Twitter, disseminate not only useful information, but also false information. Identifying this false information is crucial in order to keep the information on a SNS reliable. The aim of this paper is to develop a method of extracting false information from among a large collection of tweets. We do so by using a set of linguistic patterns formulated to correct false information. More specifically, the proposed method extracts text passages that match specified correction patterns, clusters the passages into topics of false information, and selects a passage that represents each topic of false information. In the experiment we conduct, we build an evaluation set manually, and demonstrate the effectiveness of the proposed method.