Ichiro Kobayashi


2021

pdf bib
Towards a Language Model for Temporal Commonsense Reasoning
Mayuko Kimura | Lis Kanashiro Pereira | Ichiro Kobayashi
Proceedings of the Student Research Workshop Associated with RANLP 2021

Temporal commonsense reasoning is a challenging task as it requires temporal knowledge usually not explicit in text. In this work, we propose an ensemble model for temporal commonsense reasoning. Our model relies on pre-trained contextual representations from transformer-based language models (i.e., BERT), and on a variety of training methods for enhancing model generalization: 1) multi-step fine-tuning using carefully selected auxiliary tasks and datasets, and 2) a specifically designed temporal masked language model task aimed to capture temporal commonsense knowledge. Our model greatly outperforms the standard fine-tuning approach and strong baselines on the MC-TACO dataset.

pdf bib
Multi-Layer Random Perturbation Training for improving Model Generalization Efficiently
Lis Kanashiro Pereira | Yuki Taya | Ichiro Kobayashi
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

We propose a simple yet effective Multi-Layer RAndom Perturbation Training algorithm (RAPT) to enhance model robustness and generalization. The key idea is to apply randomly sampled noise to each input to generate label-preserving artificial input points. To encourage the model to generate more diverse examples, the noise is added to a combination of the model layers. Then, our model regularizes the posterior difference between clean and noisy inputs. We apply RAPT towards robust and efficient BERT training, and conduct comprehensive fine-tuning experiments on GLUE tasks. Our results show that RAPT outperforms the standard fine-tuning approach, and adversarial training method, yet with 22% less training time.

pdf bib
Generating Racing Game Commentary from Vision, Language, and Structured Data
Tatsuya Ishigaki | Goran Topic | Yumi Hamazono | Hiroshi Noji | Ichiro Kobayashi | Yusuke Miyao | Hiroya Takamura
Proceedings of the 14th International Conference on Natural Language Generation

We propose the task of automatically generating commentaries for races in a motor racing game, from vision, structured numerical, and textual data. Commentaries provide information to support spectators in understanding events in races. Commentary generation models need to interpret the race situation and generate the correct content at the right moment. We divide the task into two subtasks: utterance timing identification and utterance generation. Because existing datasets do not have such alignments of data in multiple modalities, this setting has not been explored in depth. In this study, we introduce a new large-scale dataset that contains aligned video data, structured numerical data, and transcribed commentaries that consist of 129,226 utterances in 1,389 races in a game. Our analysis reveals that the characteristics of commentaries change over time or from viewpoints. Our experiments on the subtasks show that it is still challenging for a state-of-the-art vision encoder to capture useful information from videos to generate accurate commentaries. We make the dataset and baseline implementation publicly available for further research.

pdf bib
OCHADAI-KYOTO at SemEval-2021 Task 1: Enhancing Model Generalization and Robustness for Lexical Complexity Prediction
Yuki Taya | Lis Kanashiro Pereira | Fei Cheng | Ichiro Kobayashi
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

We propose an ensemble model for predicting the lexical complexity of words and multiword expressions (MWEs). The model receives as input a sentence with a target word or MWE and outputs its complexity score. Given that a key challenge with this task is the limited size of annotated data, our model relies on pretrained contextual representations from different state-of-the-art transformer-based language models (i.e., BERT and RoBERTa), and on a variety of training methods for further enhancing model generalization and robustness: multi-step fine-tuning and multi-task learning, and adversarial training. Additionally, we propose to enrich contextual representations by adding hand-crafted features during training. Our model achieved competitive results and ranked among the top-10 systems in both sub-tasks.

pdf bib
Targeted Adversarial Training for Natural Language Understanding
Lis Pereira | Xiaodong Liu | Hao Cheng | Hoifung Poon | Jianfeng Gao | Ichiro Kobayashi
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding. The key idea is to introspect current mistakes and prioritize adversarial training steps to where the model errs the most. Experiments show that TAT can significantly improve accuracy over standard adversarial training on GLUE and attain new state-of-the-art zero-shot results on XNLI. Our code will be released upon acceptance of the paper.

2020

pdf bib
Adversarial Training for Commonsense Inference
Lis Pereira | Xiaodong Liu | Fei Cheng | Masayuki Asahara | Ichiro Kobayashi
Proceedings of the 5th Workshop on Representation Learning for NLP

We apply small perturbations to word embeddings and minimize the resultant adversarial risk to regularize the model. We exploit a novel combination of two different approaches to estimate these perturbations: 1) using the true label and 2) using the model prediction. Without relying on any human-crafted features, knowledge bases, or additional datasets other than the target datasets, our model boosts the fine-tuning performance of RoBERTa, achieving competitive results on multiple reading comprehension datasets that require commonsense inference.

pdf bib
Learning with Contrastive Examples for Data-to-Text Generation
Yui Uehara | Tatsuya Ishigaki | Kasumi Aoki | Hiroshi Noji | Keiichi Goshima | Ichiro Kobayashi | Hiroya Takamura | Yusuke Miyao
Proceedings of the 28th International Conference on Computational Linguistics

Existing models for data-to-text tasks generate fluent but sometimes incorrect sentences e.g., “Nikkei gains” is generated when “Nikkei drops” is expected. We investigate models trained on contrastive examples i.e., incorrect sentences or terms, in addition to correct ones to reduce such errors. We first create rules to produce contrastive examples from correct ones by replacing frequent crucial terms such as “gain” or “drop”. We then use learning methods with several losses that exploit contrastive examples. Experiments on the market comment generation task show that 1) exploiting contrastive examples improves the capability of generating sentences with better lexical choice, without degrading the fluency, 2) the choice of the loss function is an important factor because the performances on different metrics depend on the types of loss functions, and 3) the use of the examples produced by some specific rules further improves performance. Human evaluation also supports the effectiveness of using contrastive examples.

pdf bib
Market Comment Generation from Data with Noisy Alignments
Yumi Hamazono | Yui Uehara | Hiroshi Noji | Yusuke Miyao | Hiroya Takamura | Ichiro Kobayashi
Proceedings of the 13th International Conference on Natural Language Generation

End-to-end models on data-to-text learn the mapping of data and text from the aligned pairs in the dataset. However, these alignments are not always obtained reliably, especially for the time-series data, for which real time comments are given to some situation and there might be a delay in the comment delivery time compared to the actual event time. To handle this issue of possible noisy alignments in the dataset, we propose a neural network model with multi-timestep data and a copy mechanism, which allows the models to learn the correspondences between data and text from the dataset with noisier alignments. We focus on generating market comments in Japanese that are delivered each time an event occurs in the market. The core idea of our approach is to utilize multi-timestep data, which is not only the latest market price data when the comment is delivered, but also the data obtained at several timesteps earlier. On top of this, we employ a copy mechanism that is suitable for referring to the content of data records in the market price data. We confirm the superiority of our proposal by two evaluation metrics and show the accuracy improvement of the sentence generation using the time series data by our proposed method.

pdf bib
Dialogue over Context and Structured Knowledge using a Neural Network Model with External Memories
Yuri Murayama | Lis Kanashiro Pereira | Ichiro Kobayashi
Proceedings of Knowledgeable NLP: the First Workshop on Integrating Structured Knowledge and Neural Networks for NLP

The Differentiable Neural Computer (DNC), a neural network model with an addressable external memory, can solve algorithmic and question answering tasks. There are various improved versions of DNC, such as rsDNC and DNC-DMS. However, how to integrate structured knowledge into these DNC models remains a challenging research question. We incorporate an architecture for knowledge into such DNC models, i.e. DNC, rsDNC and DNC-DMS, to improve the ability to generate correct responses using both contextual information and structured knowledge. Our improved rsDNC model improves the mean accuracy by approximately 20% to the original rsDNC on tasks requiring knowledge in the dialog bAbI tasks. In addition, our improved rsDNC and DNC-DMS models also yield better performance than their original models in the Movie Dialog dataset.

pdf bib
Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning
Fei Cheng | Masayuki Asahara | Ichiro Kobayashi | Sadao Kurohashi
Findings of the Association for Computational Linguistics: EMNLP 2020

Temporal relation classification is the pair-wise task for identifying the relation of a temporal link (TLINKs) between two mentions, i.e. event, time and document creation time (DCT). It leads to two crucial limits: 1) Two TLINKs involving a common mention do not share information. 2) Existing models with independent classifiers for each TLINK category (E2E, E2T and E2D) hinder from using the whole data. This paper presents an event centric model that allows to manage dynamic event representations across multiple TLINKs. Our model deals with three TLINK categories with multi-task learning to leverage the full size of data. The experimental results show that our proposal outperforms state-of-the-art models and two strong transfer learning baselines on both the English and Japanese data.

2019

pdf bib
Learning to Select, Track, and Generate for Data-to-Text
Hayate Iso | Yui Uehara | Tatsuya Ishigaki | Hiroshi Noji | Eiji Aramaki | Ichiro Kobayashi | Yusuke Miyao | Naoaki Okazaki | Hiroya Takamura
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. Our proposed model is considered to simulate the human-like writing process that gradually selects the information by determining the intermediate variables while writing the summary. In addition, we also explore the effectiveness of the writer information for generations. Experimental results show that our proposed model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization.

pdf bib
Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels
Kasumi Aoki | Akira Miyazawa | Tatsuya Ishigaki | Tatsuya Aoki | Hiroshi Noji | Keiichi Goshima | Ichiro Kobayashi | Hiroya Takamura | Yusuke Miyao
Proceedings of the 12th International Conference on Natural Language Generation

We propose a data-to-document generator that can easily control the contents of output texts based on a neural language model. Conventional data-to-text model is useful when a reader seeks a global summary of data because it has only to describe an important part that has been extracted beforehand. However, because depending on users, it differs what they are interested in, so it is necessary to develop a method to generate various summaries according to users’ interests. We develop a model to generate various summaries and to control their contents by providing the explicit targets for a reference to the model as controllable factors. In the experiments, we used five-minute or one-hour charts of 9 indicators (e.g., Nikkei225), as time-series data, and daily summaries of Nikkei Quick News as textual data. We conducted comparative experiments using two pieces of information: human-designed topic labels indicating the contents of a sentence and automatically extracted keywords as the referential information for generation.

2018

pdf bib
Generating Market Comments Referring to External Resources
Tatsuya Aoki | Akira Miyazawa | Tatsuya Ishigaki | Keiichi Goshima | Kasumi Aoki | Ichiro Kobayashi | Hiroya Takamura | Yusuke Miyao
Proceedings of the 11th International Conference on Natural Language Generation

Comments on a stock market often include the reason or cause of changes in stock prices, such as “Nikkei turns lower as yen’s rise hits exporters.” Generating such informative sentences requires capturing the relationship between different resources, including a target stock price. In this paper, we propose a model for automatically generating such informative market comments that refer to external resources. We evaluated our model through an automatic metric in terms of BLEU and human evaluation done by an expert in finance. The results show that our model outperforms the existing model both in BLEU scores and human judgment.

2016

pdf bib
Human-like Natural Language Generation Using Monte Carlo Tree Search
Kaori Kumagai | Ichiro Kobayashi | Daichi Mochihashi | Hideki Asoh | Tomoaki Nakamura | Takayuki Nagai
Proceedings of the INLG 2016 Workshop on Computational Creativity in Natural Language Generation

pdf bib
A POMDP-based Multimodal Interaction System Using a Humanoid Robot
Sae Iijima | Ichiro Kobayashi
Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Posters

pdf bib
Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity
Eri Matsuo | Ichiro Kobayashi | Shinji Nishimoto | Satoshi Nishida | Hideki Asoh
Proceedings of the ACL 2016 Student Research Workshop

2015

pdf bib
Learning Word Meanings and Grammar for Describing Everyday Activities in Smart Environments
Muhammad Attamimi | Yuji Ando | Tomoaki Nakamura | Takayuki Nagai | Daichi Mochihashi | Ichiro Kobayashi | Hideki Asoh
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

2014

pdf bib
Zero-Shot Learning of Language Models for Describing Human Actions Based on Semantic Compositionality of Actions
Hideki Asoh | Ichiro Kobayashi
Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing

pdf bib
Topic-based Multi-document Summarization using Differential Evolution forCombinatorial Optimization of Sentences
Haruka Shigematsu | Ichiro Kobayashi
Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing

pdf bib
On-line Summarization of Time-series Documents using a Graph-based Algorithm
Satoko Suzuki | Ichiro Kobayashi
Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing

2013

pdf bib
Event Sequence Model for Semantic Analysis of Time and Location in Dialogue System
Yasuhiro Noguchi | Satoru Kogure | Makoto Kondo | Ichiro Kobayashi | Hideki Asoh | Akira Takagi | Tatsuhiro Konishi | Yukihiro Itoh
Proceedings of the 27th Pacific Asia Conference on Language, Information, and Computation (PACLIC 27)

pdf bib
Text Classification based on the Latent Topics of Important Sentences extracted by the PageRank Algorithm
Yukari Ogura | Ichiro Kobayashi
51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Student Research Workshop

pdf bib
High-quality Training Data Selection using Latent Topics for Graph-based Semi-supervised Learning
Akiko Eriguchi | Ichiro Kobayashi
51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Student Research Workshop

2011

pdf bib
A Latent Topic Extracting Method based on Events in a Document and its Application
Risa Kitajima | Ichiro Kobayashi
Proceedings of the ACL 2011 Student Session

1998

pdf bib
The Multex generator and its environment: application and development
Christian Matthiessen | Licheng Zeng | Marilyn Cross | Ichiro Kobayashi | Kazuhiro Teruya | Canzhong Wu
Natural Language Generation