Sosuke Kobayashi


2023

pdf bib
B2T Connection: Serving Stability and Performance in Deep Transformers
Sho Takase | Shun Kiyono | Sosuke Kobayashi | Jun Suzuki
Findings of the Association for Computational Linguistics: ACL 2023

In the perspective of a layer normalization (LN) position, the architecture of Transformers can be categorized into two types: Post-LN and Pre-LN.Recent Transformers prefer to select Pre-LN because the training in Post-LN with deep Transformers, e.g., ten or more layers, often becomes unstable, resulting in useless models. However, in contrast, Post-LN has also consistently achieved better performance than Pre-LN in relatively shallow Transformers, e.g., six or fewer layers. This study first investigates the reason for these discrepant observations empirically and theoretically and discovers 1, the LN in Post-LN is the source of the vanishing gradient problem that mainly leads the unstable training whereas Pre-LN prevents it, and 2, Post-LN tends to preserve larger gradient norms in higher layers during the back-propagation that may lead an effective training. Exploiting the new findings, we propose a method that can equip both higher stability and effective training by a simple modification from Post-LN.We conduct experiments on a wide range of text generation tasks and demonstrate that our method outperforms Pre-LN, and stable training regardless of the shallow or deep layer settings.

2022

pdf bib
Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model
Sosuke Kobayashi | Shun Kiyono | Jun Suzuki | Kentaro Inui
Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models

Ensembling is a popular method used to improve performance as a last resort. However, ensembling multiple models finetuned from a single pretrained model has been not very effective; this could be due to the lack of diversity among ensemble members. This paper proposes Multi-Ticket Ensemble, which finetunes different subnetworks of a single pretrained model and ensembles them. We empirically demonstrated that winning-ticket subnetworks produced more diverse predictions than dense networks and their ensemble outperformed the standard ensemble in some tasks when accurate lottery tickets are found on the tasks.

2021

pdf bib
SHAPE: Shifted Absolute Position Embedding for Transformers
Shun Kiyono | Sosuke Kobayashi | Jun Suzuki | Kentaro Inui
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Position representation is crucial for building position-aware representations in Transformers. Existing position representations suffer from a lack of generalization to test data with unseen lengths or high computational cost. We investigate shifted absolute position embedding (SHAPE) to address both issues. The basic idea of SHAPE is to achieve shift invariance, which is a key property of recent successful position representations, by randomly shifting absolute positions during training. We demonstrate that SHAPE is empirically comparable to its counterpart while being simpler and faster.

pdf bib
Instance-Based Neural Dependency Parsing
Hiroki Ouchi | Jun Suzuki | Sosuke Kobayashi | Sho Yokoi | Tatsuki Kuribayashi | Masashi Yoshikawa | Kentaro Inui
Transactions of the Association for Computational Linguistics, Volume 9

Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations.

2020

pdf bib
Efficient Estimation of Influence of a Training Instance
Sosuke Kobayashi | Sho Yokoi | Jun Suzuki | Kentaro Inui
Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing

Understanding the influence of a training instance on a neural network model leads to improving interpretability. However, it is difficult and inefficient to evaluate the influence, which shows how a model’s prediction would be changed if a training instance were not used. In this paper, we propose an efficient method for estimating the influence. Our method is inspired by dropout, which zero-masks a sub-network and prevents the sub-network from learning each training instance. By switching between dropout masks, we can use sub-networks that learned or did not learn each training instance and estimate its influence. Through experiments with BERT and VGGNet on classification datasets, we demonstrate that the proposed method can capture training influences, enhance the interpretability of error predictions, and cleanse the training dataset for improving generalization.

pdf bib
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition
Hiroki Ouchi | Jun Suzuki | Sosuke Kobayashi | Sho Yokoi | Tatsuki Kuribayashi | Ryuto Konno | Kentaro Inui
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Interpretable rationales for model predictions play a critical role in practical applications. In this study, we develop models possessing interpretable inference process for structured prediction. Specifically, we present a method of instance-based learning that learns similarities between spans. At inference time, each span is assigned a class label based on its similar spans in the training set, where it is easy to understand how much each training instance contributes to the predictions. Through empirical analysis on named entity recognition, we demonstrate that our method enables to build models that have high interpretability without sacrificing performance.

2018

pdf bib
Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
Sho Yokoi | Sosuke Kobayashi | Kenji Fukumizu | Jun Suzuki | Kentaro Inui
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In this paper, we propose a new kernel-based co-occurrence measure that can be applied to sparse linguistic expressions (e.g., sentences) with a very short learning time, as an alternative to pointwise mutual information (PMI). As well as deriving PMI from mutual information, we derive this new measure from the Hilbert–Schmidt independence criterion (HSIC); thus, we call the new measure the pointwise HSIC (PHSIC). PHSIC can be interpreted as a smoothed variant of PMI that allows various similarity metrics (e.g., sentence embeddings) to be plugged in as kernels. Moreover, PHSIC can be estimated by simple and fast (linear in the size of the data) matrix calculations regardless of whether we use linear or nonlinear kernels. Empirically, in a dialogue response selection task, PHSIC is learned thousands of times faster than an RNN-based PMI while outperforming PMI in accuracy. In addition, we also demonstrate that PHSIC is beneficial as a criterion of a data selection task for machine translation owing to its ability to give high (low) scores to a consistent (inconsistent) pair with other pairs.

pdf bib
Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations
Sosuke Kobayashi
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

We propose a novel data augmentation for labeled sentences called contextual augmentation. We assume an invariance that sentences are natural even if the words in the sentences are replaced with other words with paradigmatic relations. We stochastically replace words with other words that are predicted by a bi-directional language model at the word positions. Words predicted according to a context are numerous but appropriate for the augmentation of the original words. Furthermore, we retrofit a language model with a label-conditional architecture, which allows the model to augment sentences without breaking the label-compatibility. Through the experiments for six various different text classification tasks, we demonstrate that the proposed method improves classifiers based on the convolutional or recurrent neural networks.

pdf bib
Unsupervised Learning of Style-sensitive Word Vectors
Reina Akama | Kento Watanabe | Sho Yokoi | Sosuke Kobayashi | Kentaro Inui
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner. We propose extending the continuous bag of words (CBOW) embedding model (Mikolov et al., 2013b) to learn style-sensitive word vectors using a wider context window under the assumption that the style of all the words in an utterance is consistent. In addition, we introduce a novel task to predict lexical stylistic similarity and to create a benchmark dataset for this task. Our experiment with this dataset supports our assumption and demonstrates that the proposed extensions contribute to the acquisition of style-sensitive word embeddings.

2017

pdf bib
An RNN-based Binary Classifier for the Story Cloze Test
Melissa Roemmele | Sosuke Kobayashi | Naoya Inoue | Andrew Gordon
Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics

The Story Cloze Test consists of choosing a sentence that best completes a story given two choices. In this paper we present a system that performs this task using a supervised binary classifier on top of a recurrent neural network to predict the probability that a given story ending is correct. The classifier is trained to distinguish correct story endings given in the training data from incorrect ones that we artificially generate. Our experiments evaluate different methods for generating these negative examples, as well as different embedding-based representations of the stories. Our best result obtains 67.2% accuracy on the test set, outperforming the existing top baseline of 58.5%.

pdf bib
A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse
Sosuke Kobayashi | Naoaki Okazaki | Kentaro Inui
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

This study addresses the problem of identifying the meaning of unknown words or entities in a discourse with respect to the word embedding approaches used in neural language models. We proposed a method for on-the-fly construction and exploitation of word embeddings in both the input and output layers of a neural model by tracking contexts. This extends the dynamic entity representation used in Kobayashi et al. (2016) and incorporates a copy mechanism proposed independently by Gu et al. (2016) and Gulcehre et al. (2016). In addition, we construct a new task and dataset called Anonymized Language Modeling for evaluating the ability to capture word meanings while reading. Experiments conducted using our novel dataset show that the proposed variant of RNN language model outperformed the baseline model. Furthermore, the experiments also demonstrate that dynamic updates of an output layer help a model predict reappearing entities, whereas those of an input layer are effective to predict words following reappearing entities.

pdf bib
Generating Stylistically Consistent Dialog Responses with Transfer Learning
Reina Akama | Kazuaki Inada | Naoya Inoue | Sosuke Kobayashi | Kentaro Inui
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

We propose a novel, data-driven, and stylistically consistent dialog response generation system. To create a user-friendly system, it is crucial to make generated responses not only appropriate but also stylistically consistent. For leaning both the properties effectively, our proposed framework has two training stages inspired by transfer learning. First, we train the model to generate appropriate responses, and then we ensure that the responses have a specific style. Experimental results demonstrate that the proposed method produces stylistically consistent responses while maintaining the appropriateness of the responses learned in a general domain.

2016

pdf bib
Dynamic Entity Representation with Max-pooling Improves Machine Reading
Sosuke Kobayashi | Ran Tian | Naoaki Okazaki | Kentaro Inui
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Tohoku at SemEval-2016 Task 6: Feature-based Model versus Convolutional Neural Network for Stance Detection
Yuki Igarashi | Hiroya Komatsu | Sosuke Kobayashi | Naoaki Okazaki | Kentaro Inui
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)