To develop high-performance natural language understanding (NLU) models, it is necessary to have a benchmark to evaluate and analyze NLU ability from various perspectives. While the English NLU benchmark, GLUE, has been the forerunner, benchmarks are now being released for languages other than English, such as CLUE for Chinese and FLUE for French; but there is no such benchmark for Japanese. We build a Japanese NLU benchmark, JGLUE, from scratch without translation to measure the general NLU ability in Japanese. We hope that JGLUE will facilitate NLU research in Japanese.

In community-based question answering (CQA) platforms, it takes time for a user to get useful information from among many answers.Although one solution is an answer ranking method, the user still needs to read through the top-ranked answers carefully.This paper proposes a new task of selecting a diverse and non-redundant answer set rather than ranking the answers.Our method is based on determinantal point processes (DPPs), and it calculates the answer importance and similarity between answers by using BERT.We built a dataset focusing on a Japanese CQA site, and the experiments on this dataset demonstrated that the proposed method outperformed several baseline methods.

Frequently Asked Question (FAQ) retrieval is an important task where the objective is to retrieve an appropriate Question-Answer (QA) pair from a database based on a user's query. We propose a FAQ retrieval system that considers the similarity between a user's query and a question as well as the relevance between the query and an answer. Although a common approach to FAQ retrieval is to construct labeled data for training, it takes annotation costs. Therefore, we use a traditional unsupervised information retrieval system to calculate the similarity between the query and question. On the other hand, the relevance between the query and answer can be learned by using QA pairs in a FAQ database. The recently-proposed BERT model is used for the relevance calculation. Since the number of QA pairs in FAQ page is not enough to train a model, we cope with this issue by leveraging FAQ sets that are similar to the one in question. We evaluate our approach on two datasets. The first one is localgovFAQ, a dataset we construct in a Japanese administrative municipality domain. The second is StackExchange dataset, which is the public dataset in English. We demonstrate that our proposed method outperforms baseline methods on these datasets.

Predicate argument structure analysis is a task of identifying structured events.To improve this field, we need to identify a salient entity, which cannot be identified without performing coreference resolution and predicate argument structure analysis simultaneously.This paper presents an entity-centric joint model for Japanese coreference resolution and predicate argument structure analysis.Each entity is assigned an embedding, and when the result of both analyses refers to an entity, the entity embedding is updated.The analyses take the entity embedding into consideration to access the global information of entities.Our experimental results demonstrate the proposed method can improve the performance of the intersentential zero anaphora resolution drastically, which is a notoriously difficult task in predicate argument structure analysis.

This article proposes a predicate-argument structure based Textual Entailment Recognition system exploiting wide-coverage lexical knowledge. Different from conventional machine learning approaches where several features obtained from linguistic analysis and resources are utilized, our proposed method regards a predicate-argument structure as a basic unit, and performs the matching/alignment between a text and hypothesis. In matching between predicate-arguments, wide-coverage relations between words/phrases such as synonym and is-a are utilized, which are automatically acquired from a dictionary, Web corpus, and Wikipedia.

The source of a piece of information is a crucial element to consider when judging the credibility of that information. In this paper, we address the task of identifying the information source which is cast as a problem of identifying the {\em information sender configuration (ISC)} of a Web page. An information sender of a Web page is an entity which is involved in the publication of the information on the page. An ISC of a Web page describes the information senders of the page and the relationship among them. Information sender extraction is thus a subtask of identifying ISC, and we present a method for extracting information senders from Web pages and offer preliminary evaluation. The ISC provides a basis for deeper analysis of information on the Web.

This paper describes a system that conducts search result clustering for several thousands of Web pages, and elaborates cluster labels through keyword distillation. Keyword distillation is a method that properly handles spelling variations, transliterations, synonyms, inclusion relations and word ambiguity, using linguistic resources and contexts of a user's query. The system provides a clustering result from 1,000 pages in less than one minute by taking advantage of a search engine infrastructure and grid computing environment. Experimental results show that the system correctly merged synonymous keywords and is useful for finding topics hidden in the lower-ranked pages in a search result.

In order to make the best use of multimedia contents effectively, the crucial point is the structural analysis of the contents, in which several media processing techniques, including image, audio and text analyses, should be integrated. To understand utterances in videos in accordance with the scene, it is essential to recognize what object appears in the videos. In this paper, we focus on Japanese cooking TV videos, and propose a method for acquiring object models of foods in an unsupervised manner and performing object recognition based on the acquired object models. First, a topic of each video segment is identified based on HMMs to obtain good examples for the object model acquisition. After that, close-up images are extracted from image sequences, and an attention region on the close-up image is determined. Then, an important word is extracted as a keyword from utterances around the close-up image, and is made correspond to the close-up image. By collecting a set of close-up image and keyword from a large amount of videos, object models are acquired. After acquiring the object models, object recognition is performed based on the acquired object models and linguistic information. We conducted experiments on two kinds of cooking TV programs. We acquired the object models of around 100 foods with an accuracy 77.8%. The F measure of object recognition was 0.727.