Ryo Nagata


2023

pdf bib
A Report on FCG GenChal 2022: Shared Task on Feedback Comment Generation for Language Learners
Ryo Nagata | Masato Hagiwara | Kazuaki Hanawa | Masato Mita
Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges

We report on the results of the first ever shared task on feedback comment generation for language learners held as Generation Challenge (GenChal) in INLG 2022, which we call FCG GenChal. Feedback comment generation for language learners is a task where, given a text and a span, a system generates, for the span, an explanatory note that helps the writer (language learner) improve their writing skills. We show how well we can generate feedback comments with present techniques. We also shed light on the task properties and the difficulties in this task, with insights into the task including data development, evaluation, and comparisons of generation systems.

pdf bib
Variance Matters: Detecting Semantic Differences without Corpus/Word Alignment
Ryo Nagata | Hiroya Takamura | Naoki Otani | Yoshifumi Kawasaki
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

In this paper, we propose methods for discovering semantic differences in words appearing in two corpora. The key idea is to measure the coverage of meanings of a word in a corpus through the norm of its mean word vector, which is equivalent to examining a kind of variance of the word vector distribution. The proposed methods do not require alignments between words and/or corpora for comparison that previous methods do. All they require are to compute variance (or norms of mean word vectors) for each word type. Nevertheless, they rival the best-performing system in the SemEval-2020 Task 1. In addition, they are (i) robust for the skew in corpus sizes; (ii) capable of detecting semantic differences in infrequent words; and (iii) effective in pinpointing word instances that have a meaning missing in one of the two corpora under comparison. We show these advantages for historical corpora and also for native/non-native English corpora.

pdf bib
Generating Dialog Responses with Specified Grammatical Items for Second Language Learning
Yuki Okano | Kotaro Funakoshi | Ryo Nagata | Manabu Okumura
Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)

This paper proposes a new second language learning task of generating a response including specified grammatical items. We consider two approaches: 1) fine-tuning a pre-trained language model (DialoGPT) by reinforcement learning and 2) providing a few-shot prompt to a large language model (GPT-3). For reinforcement learning, we examine combinations of three reward functions that consider grammatical items, diversity, and fluency. Our experiments confirm that both approaches can generate responses including the specified grammatical items and that it is crucial to consider fluency rather than diversity as the reward function.

2022

pdf bib
Exploring the Capacity of a Large-scale Masked Language Model to Recognize Grammatical Errors
Ryo Nagata | Manabu Kimura | Kazuaki Hanawa
Findings of the Association for Computational Linguistics: ACL 2022

In this paper, we explore the capacity of a language model-based method for grammatical error detection in detail. We first show that 5 to 10% of training data are enough for a BERT-based error detection method to achieve performance equivalent to what a non-language model-based method can achieve with the full training data; recall improves much faster with respect to training data size in the BERT-based method than in the non-language model method. This suggests that (i) the BERT-based method should have a good knowledge of the grammar required to recognize certain types of error and that (ii) it can transform the knowledge into error detection rules by fine-tuning with few training samples, which explains its high generalization ability in grammatical error detection. We further show with pseudo error data that it actually exhibits such nice properties in learning rules for recognizing various types of error. Finally, based on these findings, we discuss a cost-effective method for detecting grammatical errors with feedback comments explaining relevant grammatical rules to learners.

pdf bib
Revisiting Statistical Laws of Semantic Shift in Romance Cognates
Yoshifumi Kawasaki | Maëlys Salingre | Marzena Karpinska | Hiroya Takamura | Ryo Nagata
Proceedings of the 29th International Conference on Computational Linguistics

This article revisits statistical relationships across Romance cognates between lexical semantic shift and six intra-linguistic variables, such as frequency and polysemy. Cognates are words that are derived from a common etymon, in this case, a Latin ancestor. Despite their shared etymology, some cognate pairs have experienced semantic shift. The degree of semantic shift is quantified using cosine distance between the cognates’ corresponding word embeddings. In the previous literature, frequency and polysemy have been reported to be correlated with semantic shift; however, the understanding of their effects needs revision because of various methodological defects. In the present study, we perform regression analysis under improved experimental conditions, and demonstrate a genuine negative effect of frequency and positive effect of polysemy on semantic shift. Furthermore, we reveal that morphologically complex etyma are more resistant to semantic shift and that the cognates that have been in use over a longer timespan are prone to greater shift in meaning. These findings add to our understanding of the historical process of semantic change.

2021

pdf bib
Shared Task on Feedback Comment Generation for Language Learners
Ryo Nagata | Masato Hagiwara | Kazuaki Hanawa | Masato Mita | Artem Chernodub | Olena Nahorna
Proceedings of the 14th International Conference on Natural Language Generation

In this paper, we propose a generation challenge called Feedback comment generation for language learners. It is a task where given a text and a span, a system generates, for the span, an explanatory note that helps the writer (language learner) improve their writing skills. The motivations for this challenge are: (i) practically, it will be beneficial for both language learners and teachers if a computer-assisted language learning system can provide feedback comments just as human teachers do; (ii) theoretically, feedback comment generation for language learners has a mixed aspect of other generation tasks together with its unique features and it will be interesting to explore what kind of generation technique is effective against what kind of writing rule. To this end, we have created a dataset and developed baseline systems to estimate baseline performance. With these preparations, we propose a generation challenge of feedback comment generation.

pdf bib
Exploring Methods for Generating Feedback Comments for Writing Learning
Kazuaki Hanawa | Ryo Nagata | Kentaro Inui
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

The task of generating explanatory notes for language learners is known as feedback comment generation. Although various generation techniques are available, little is known about which methods are appropriate for this task. Nagata (2019) demonstrates the effectiveness of neural-retrieval-based methods in generating feedback comments for preposition use. Retrieval-based methods have limitations in that they can only output feedback comments existing in a given training data. Furthermore, feedback comments can be made on other grammatical and writing items than preposition use, which is still unaddressed. To shed light on these points, we investigate a wider range of methods for generating many feedback comments in this study. Our close analysis of the type of task leads us to investigate three different architectures for comment generation: (i) a neural-retrieval-based method as a baseline, (ii) a pointer-generator-based generation method as a neural seq2seq method, (iii) a retrieve-and-edit method, a hybrid of (i) and (ii). Intuitively, the pointer-generator should outperform neural-retrieval, and retrieve-and-edit should perform best. However, in our experiments, this expectation is completely overturned. We closely analyze the results to reveal the major causes of these counter-intuitive results and report on our findings from the experiments.

2020

pdf bib
Creating Corpora for Research in Feedback Comment Generation
Ryo Nagata | Kentaro Inui | Shin’ichiro Ishikawa
Proceedings of the Twelfth Language Resources and Evaluation Conference

In this paper, we report on datasets that we created for research in feedback comment generation — a task of automatically generating feedback comments such as a hint or an explanatory note for writing learning. There has been almost no such corpus open to the public and accordingly there has been a very limited amount of work on this task. In this paper, we first discuss the principle and guidelines for feedback comment annotation. Then, we describe two corpora that we have manually annotated with feedback comments (approximately 50,000 general comments and 6,700 on preposition use). A part of the annotation results is now available on the web, which will facilitate research in feedback comment generation

pdf bib
Taking the Correction Difficulty into Account in Grammatical Error Correction Evaluation
Takumi Gotou | Ryo Nagata | Masato Mita | Kazuaki Hanawa
Proceedings of the 28th International Conference on Computational Linguistics

This paper presents performance measures for grammatical error correction which take into account the difficulty of error correction. To the best of our knowledge, no conventional measure has such functionality despite the fact that some errors are easy to correct and others are not. The main purpose of this work is to provide a way of determining the difficulty of error correction and to motivate researchers in the domain to attack such difficult errors. The performance measures are based on the simple idea that the more systems successfully correct an error, the easier it is considered to be. This paper presents a set of algorithms to implement this idea. It evaluates the performance measures quantitatively and qualitatively on a wide variety of corpora and systems, revealing that they agree with our intuition of correction difficulty. A scorer and difficulty weight data based on the algorithms have been made available on the web.

2019

pdf bib
Cross-Corpora Evaluation and Analysis of Grammatical Error Correction Models — Is Single-Corpus Evaluation Enough?
Masato Mita | Tomoya Mizumoto | Masahiro Kaneko | Ryo Nagata | Kentaro Inui
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

This study explores the necessity of performing cross-corpora evaluation for grammatical error correction (GEC) models. GEC models have been previously evaluated based on a single commonly applied corpus: the CoNLL-2014 benchmark. However, the evaluation remains incomplete because the task difficulty varies depending on the test corpus and conditions such as the proficiency levels of the writers and essay topics. To overcome this limitation, we evaluate the performance of several GEC models, including NMT-based (LSTM, CNN, and transformer) and an SMT-based model, against various learner corpora (CoNLL-2013, CoNLL-2014, FCE, JFLEG, ICNALE, and KJ). Evaluation results reveal that the models’ rankings considerably vary depending on the corpus, indicating that single-corpus evaluation is insufficient for GEC models.

pdf bib
Toward a Task of Feedback Comment Generation for Writing Learning
Ryo Nagata
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

In this paper, we introduce a novel task called feedback comment generation — a task of automatically generating feedback comments such as a hint or an explanatory note for writing learning for non-native learners of English. There has been almost no work on this task nor corpus annotated with feedback comments. We have taken the first step by creating learner corpora consisting of approximately 1,900 essays where all preposition errors are manually annotated with feedback comments. We have tested three baseline methods on the dataset, showing that a simple neural retrieval-based method sets a baseline performance with an F-measure of 0.34 to 0.41. Finally, we have looked into the results to explore what modifications we need to make to achieve better performance. We also have explored problems unaddressed in this work

pdf bib
Analytic Score Prediction and Justification Identification in Automated Short Answer Scoring
Tomoya Mizumoto | Hiroki Ouchi | Yoriko Isobe | Paul Reisert | Ryo Nagata | Satoshi Sekine | Kentaro Inui
Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications

This paper provides an analytical assessment of student short answer responses with a view to potential benefits in pedagogical contexts. We first propose and formalize two novel analytical assessment tasks: analytic score prediction and justification identification, and then provide the first dataset created for analytic short answer scoring research. Subsequently, we present a neural baseline model and report our extensive empirical results to demonstrate how our dataset can be used to explore new and intriguing technical challenges in short answer scoring. The dataset is publicly available for research purposes.

2018

pdf bib
A POS Tagging Model Adapted to Learner English
Ryo Nagata | Tomoya Mizumoto | Yuta Kikuchi | Yoshifumi Kawasaki | Kotaro Funakoshi
Proceedings of the 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text

There has been very limited work on the adaptation of Part-Of-Speech (POS) tagging to learner English despite the fact that POS tagging is widely used in related tasks. In this paper, we explore how we can adapt POS tagging to learner English efficiently and effectively. Based on the discussion of possible causes of POS tagging errors in learner English, we show that deep neural models are particularly suitable for this. Considering the previous findings and the discussion, we introduce the design of our model based on bidirectional Long Short-Term Memory. In addition, we describe how to adapt it to a wide variety of native languages (potentially, hundreds of them). In the evaluation section, we empirically show that it is effective for POS tagging in learner English, achieving an accuracy of 0.964, which significantly outperforms the state-of-the-art POS-tagger. We further investigate the tagging results in detail, revealing which part of the model design does or does not improve the performance.

pdf bib
Exploring the Influence of Spelling Errors on Lexical Variation Measures
Ryo Nagata | Taisei Sato | Hiroya Takamura
Proceedings of the 27th International Conference on Computational Linguistics

This paper explores the influence of spelling errors on lexical variation measures. Lexical richness measures such as Type-Token Ration (TTR) and Yule’s K are often used for learner English analysis and assessment. When applied to learner English, however, they can be unreliable because of the spelling errors appearing in it. Namely, they are, directly or indirectly, based on the counts of distinct word types, and spelling errors undesirably increase the number of distinct words. This paper introduces and examines the hypothesis that lexical richness measures become unstable in learner English because of spelling errors. Specifically, it tests the hypothesis on English learner corpora of three groups (middle school, high school, and college students). To be precise, it estimates the difference in TTR and Yule’s K caused by spelling errors, by calculating their values before and after spelling errors are manually corrected. Furthermore, it examines the results theoretically and empirically to deepen the understanding of the influence of spelling errors on them.

2017

pdf bib
Analyzing the Impact of Spelling Errors on POS-Tagging and Chunking in Learner English
Tomoya Mizumoto | Ryo Nagata
Proceedings of the 4th Workshop on Natural Language Processing Techniques for Educational Applications (NLPTEA 2017)

Part-of-speech (POS) tagging and chunking have been used in tasks targeting learner English; however, to the best our knowledge, few studies have evaluated their performance and no studies have revealed the causes of POS-tagging/chunking errors in detail. Therefore, we investigate performance and analyze the causes of failure. We focus on spelling errors that occur frequently in learner English. We demonstrate that spelling errors reduced POS-tagging performance by 0.23% owing to spelling errors, and that a spell checker is not necessary for POS-tagging/chunking of learner English.

pdf bib
Analyzing Semantic Change in Japanese Loanwords
Hiroya Takamura | Ryo Nagata | Yoshifumi Kawasaki
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers

We analyze semantic changes in loanwords from English that are used in Japanese (Japanese loanwords). Specifically, we create word embeddings of English and Japanese and map the Japanese embeddings into the English space so that we can calculate the similarity of each Japanese word and each English word. We then attempt to find loanwords that are semantically different from their original, see if known meaning changes are correctly captured, and show the possibility of using our methodology in language education.

2016

pdf bib
Discriminative Analysis of Linguistic Features for Typological Study
Hiroya Takamura | Ryo Nagata | Yoshifumi Kawasaki
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

We address the task of automatically estimating the missing values of linguistic features by making use of the fact that some linguistic features in typological databases are informative to each other. The questions to address in this work are (i) how much predictive power do features have on the value of another feature? (ii) to what extent can we attribute this predictive power to genealogical or areal factors, as opposed to being provided by tendencies or implicational universals? To address these questions, we conduct a discriminative or predictive analysis on the typological database. Specifically, we use a machine-learning classifier to estimate the value of each feature of each language using the values of the other features, under different choices of training data: all the other languages, or all the other languages except for the ones having the same origin or area with the target language.

pdf bib
Phrase Structure Annotation and Parsing for Learner English
Ryo Nagata | Keisuke Sakaguchi
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2014

pdf bib
Correcting Preposition Errors in Learner English Using Error Case Frames and Feedback Messages
Ryo Nagata | Mikko Vilenius | Edward Whittaker
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Language Family Relationship Preserved in Non-native English
Ryo Nagata
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2013

pdf bib
LIMSI’s participation to the 2013 shared task on Native Language Identification
Thomas Lavergne | Gabriel Illouz | Aurélien Max | Ryo Nagata
Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications

pdf bib
Reconstructing an Indo-European Family Tree from Non-native English Texts
Ryo Nagata | Edward Whittaker
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2011

pdf bib
Creating a manually error-tagged and shallow-parsed learner corpus
Ryo Nagata | Edward Whittaker | Vera Sheinman
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2010

pdf bib
Evaluating performance of grammatical error detection to maximize learning effect
Ryo Nagata | Kazuhide Nakatani
Coling 2010: Posters

2008

pdf bib
Recognizing Noisy Romanized Japanese Words in Learner English
Ryo Nagata | Jun-ichi Kakegawa | Hiromi Sugimoto | Yukiko Yabuta
Proceedings of the Third Workshop on Innovative Use of NLP for Building Educational Applications

2006

pdf bib
A Feedback-Augmented Method for Detecting Errors in the Writing of Learners of English
Ryo Nagata | Atsuo Kawai | Koichiro Morihiro | Naoki Isu
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf bib
Reinforcing English Countability Prediction with One Countability per Discourse Property
Ryo Nagata | Atsuo Kawai | Koichiro Morihiro | Naoki Isu
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

2005

pdf bib
Detecting Article Errors Based on the Mass Count Distinction
Ryo Nagata | Takahiro Wakana | Fumito Masui | Atsuo Kawai | Naoki Isu
Second International Joint Conference on Natural Language Processing: Full Papers