Hayato Kobayashi


2021

pdf bib
A Case Study of In-House Competition for Ranking Constructive Comments in a News Service
Hayato Kobayashi | Hiroaki Taguchi | Yoshimune Tabuchi | Chahine Koleejan | Ken Kobayashi | Soichiro Fujita | Kazuma Murao | Takeshi Masuyama | Taichi Yatsuka | Manabu Okumura | Satoshi Sekine
Proceedings of the Ninth International Workshop on Natural Language Processing for Social Media

Ranking the user comments posted on a news article is important for online news services because comment visibility directly affects the user experience. Research on ranking comments with different metrics to measure the comment quality has shown “constructiveness” used in argument analysis is promising from a practical standpoint. In this paper, we report a case study in which this constructiveness is examined in the real world. Specifically, we examine an in-house competition to improve the performance of ranking constructive comments and demonstrate the effectiveness of the best obtained model for a commercial service.

2019

pdf bib
A Case Study on Neural Headline Generation for Editing Support
Kazuma Murao | Ken Kobayashi | Hayato Kobayashi | Taichi Yatsuka | Takeshi Masuyama | Tatsuru Higurashi | Yoshimune Tabuchi
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)

There have been many studies on neural headline generation models trained with a lot of (article, headline) pairs. However, there are few situations for putting such models into practical use in the real world since news articles typically already have corresponding headlines. In this paper, we describe a practical use case of neural headline generation in a news aggregator, where dozens of professional editors constantly select important news articles and manually create their headlines, which are much shorter than the original headlines. Specifically, we show how to deploy our model to an editing support tool and report the results of comparing the behavior of the editors before and after the release.

pdf bib
Diamonds in the Rough: Generating Fluent Sentences from Early-Stage Drafts for Academic Writing Assistance
Takumi Ito | Tatsuki Kuribayashi | Hayato Kobayashi | Ana Brassard | Masato Hagiwara | Jun Suzuki | Kentaro Inui
Proceedings of the 12th International Conference on Natural Language Generation

The writing process consists of several stages such as drafting, revising, editing, and proofreading. Studies on writing assistance, such as grammatical error correction (GEC), have mainly focused on sentence editing and proofreading, where surface-level issues such as typographical errors, spelling errors, or grammatical errors should be corrected. We broaden this focus to include the earlier revising stage, where sentences require adjustment to the information included or major rewriting and propose Sentence-level Revision (SentRev) as a new writing assistance task. Well-performing systems in this task can help inexperienced authors by producing fluent, complete sentences given their rough, incomplete drafts. We build a new freely available crowdsourced evaluation dataset consisting of incomplete sentences authored by non-native writers paired with their final versions extracted from published academic papers for developing and evaluating SentRev models. We also establish baseline performance on SentRev using our newly built evaluation dataset.

pdf bib
Dataset Creation for Ranking Constructive News Comments
Soichiro Fujita | Hayato Kobayashi | Manabu Okumura
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Ranking comments on an online news service is a practically important task for the service provider, and thus there have been many studies on this task. However, most of them considered users’ positive feedback, such as “Like”-button clicks, as a quality measure. In this paper, we address directly evaluating the quality of comments on the basis of “constructiveness,” separately from user feedback. To this end, we create a new dataset including 100K+ Japanese comments with constructiveness scores (C-scores). Our experiments clarify that C-scores are not always related to users’ positive feedback, and the performance of pairwise ranking models tends to be enhanced by the variation of comments rather than articles.

2018

pdf bib
Extractive Headline Generation Based on Learning to Rank for Community Question Answering
Tatsuru Higurashi | Hayato Kobayashi | Takeshi Masuyama | Kazuma Murao
Proceedings of the 27th International Conference on Computational Linguistics

User-generated content such as the questions on community question answering (CQA) forums does not always come with appropriate headlines, in contrast to the news articles used in various headline generation tasks. In such cases, we cannot use paired supervised data, e.g., pairs of articles and headlines, to learn a headline generation model. To overcome this problem, we propose an extractive headline generation method based on learning to rank for CQA that extracts the most informative substring from each question as its headline. Experimental results show that our method outperforms several baselines, including a prefix-based method, which is widely used in real services.

pdf bib
Pretraining Sentiment Classifiers with Unlabeled Dialog Data
Toru Shimizu | Nobuyuki Shimizu | Hayato Kobayashi
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

The huge cost of creating labeled training data is a common problem for supervised learning tasks such as sentiment classification. Recent studies showed that pretraining with unlabeled data via a language model can improve the performance of classification models. In this paper, we take the concept a step further by using a conditional language model, instead of a language model. Specifically, we address a sentiment classification task for a tweet analysis service as a case study and propose a pretraining strategy with unlabeled dialog data (tweet-reply pairs) via an encoder-decoder model. Experimental results show that our strategy can improve the performance of sentiment classifiers and outperform several state-of-the-art strategies including language model pretraining.

pdf bib
Frustratingly Easy Model Ensemble for Abstractive Summarization
Hayato Kobayashi
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Ensemble methods, which combine multiple models at decoding time, are now widely known to be effective for text-generation tasks. However, they generally increase computational costs, and thus, there have been many studies on compressing or distilling ensemble models. In this paper, we propose an alternative, simple but effective unsupervised ensemble method, post-ensemble, that combines multiple models by selecting a majority-like output in post-processing. We theoretically prove that our method is closely related to kernel density estimation based on the von Mises-Fisher kernel. Experimental results on a news-headline-generation task show that the proposed method performs better than the current ensemble methods.

2017

pdf bib
Incremental Skip-gram Model with Negative Sampling
Nobuhiro Kaji | Hayato Kobayashi
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

This paper explores an incremental training strategy for the skip-gram model with negative sampling (SGNS) from both empirical and theoretical perspectives. Existing methods of neural word embeddings, including SGNS, are multi-pass algorithms and thus cannot perform incremental model update. To address this problem, we present a simple incremental extension of SGNS and provide a thorough theoretical analysis to demonstrate its validity. Empirical experiments demonstrated the correctness of the theoretical analysis as well as the practical usefulness of the incremental algorithm.

2016

pdf bib
On Approximately Searching for Similar Word Embeddings
Kohei Sugawara | Hayato Kobayashi | Masajiro Iwasaki
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2015

pdf bib
Summarization Based on Embedding Distributions
Hayato Kobayashi | Masaki Noguchi | Taichi Yatsuka
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Effects of Game on User Engagement with Spoken Dialogue System
Hayato Kobayashi | Kaori Tanio | Manabu Sassano
Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue

2014

pdf bib
Rapid Development of a Corpus with Discourse Annotations using Two-stage Crowdsourcing
Daisuke Kawahara | Yuichiro Machida | Tomohide Shibata | Sadao Kurohashi | Hayato Kobayashi | Manabu Sassano
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf bib
Perplexity on Reduced Corpora
Hayato Kobayashi
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2011

pdf bib
Topic Models with Logical Constraints on Words
Hayato Kobayashi | Hiromi Wakaki | Tomohiro Yamasaki | Masaru Suzuki
Proceedings of Workshop on Robust Unsupervised and Semisupervised Methods in Natural Language Processing