scispace - formally typeset
Search or ask a question
Author

Hiroyuki Shindo

Bio: Hiroyuki Shindo is an academic researcher from Nara Institute of Science and Technology. The author has contributed to research in topics: Sentence & Parsing. The author has an hindex of 20, co-authored 111 publications receiving 1675 citations. Previous affiliations of Hiroyuki Shindo include Hitachi & Nippon Telegraph and Telephone.


Papers
More filters
Posted Content
TL;DR: New pretrained contextualized representations of words and entities based on the bidirectional transformer, and an entity-aware self-attention mechanism that considers the types of tokens (words or entities) when computing attention scores are proposed.
Abstract: Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and entities in a given text as independent tokens, and outputs contextualized representations of them. Our model is trained using a new pretraining task based on the masked language model of BERT. The task involves predicting randomly masked words and entities in a large entity-annotated corpus retrieved from Wikipedia. We also propose an entity-aware self-attention mechanism that is an extension of the self-attention mechanism of the transformer, and considers the types of tokens (words or entities) when computing attention scores. The proposed model achieves impressive empirical performance on a wide range of entity-related tasks. In particular, it obtains state-of-the-art results on five well-known datasets: Open Entity (entity typing), TACRED (relation classification), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), and SQuAD 1.1 (extractive question answering). Our source code and pretrained representations are available at this https URL.

288 citations

Proceedings ArticleDOI
01 Jan 2016
TL;DR: In this paper, the authors proposed a novel embedding method for NED, which jointly maps words and entities into the same continuous vector space by using skip-gram model and anchor context model, and achieved state-of-the-art accuracy of 93.1% on the standard CoNLL dataset.
Abstract: Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in a document to their correct references in a knowledge base (KB) (e.g., Wikipedia). In this paper, we propose a novel embedding method specifically designed for NED. The proposed method jointly maps words and entities into the same continuous vector space. We extend the skip-gram model by using two models. The KB graph model learns the relatedness of entities using the link structure of the KB, whereas the anchor context model aims to align vectors such that similar words and entities occur close to one another in the vector space by leveraging KB anchors and their context words. By combining contexts based on the proposed embedding with standard NED features, we achieved state-of-the-art accuracy of 93.1% on the standard CoNLL dataset and 85.2% on the TAC 2010 dataset.

266 citations

Posted Content
TL;DR: A novel embedding method specifically designed for NED that jointly maps words and entities into the same continuous vector space and extends the skip-gram model by using two models.
Abstract: Named Entity Disambiguation (NED) refers to the task of resolving multiple named entity mentions in a document to their correct references in a knowledge base (KB) (e.g., Wikipedia). In this paper, we propose a novel embedding method specifically designed for NED. The proposed method jointly maps words and entities into the same continuous vector space. We extend the skip-gram model by using two models. The KB graph model learns the relatedness of entities using the link structure of the KB, whereas the anchor context model aims to align vectors such that similar words and entities occur close to one another in the vector space by leveraging KB anchors and their context words. By combining contexts based on the proposed embedding with standard NED features, we achieved state-of-the-art accuracy of 93.1% on the standard CoNLL dataset and 85.2% on the TAC 2010 dataset.

195 citations

Proceedings ArticleDOI
01 Jul 2018
TL;DR: This paper restores interpretability to adversarial training methods by restricting the directions of perturbations toward the existing words in the input embedding space and can straightforwardly reconstruct each input with perturbATIONS to an actual text by considering the perturbation to be the replacement of words in a sentence while maintaining or even improving the task performance.
Abstract: Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the image processing field to the input word embedding space instead of the discrete input space of texts. However, this approach abandons such interpretability as generating adversarial texts to significantly improve the performance of NLP tasks. This paper restores interpretability to such methods by restricting the directions of perturbations toward the existing words in the input embedding space. As a result, we can straightforwardly reconstruct each input with perturbations to an actual text by considering the perturbations to be the replacement of words in the sentence while maintaining or even improving the task performance.

155 citations

Proceedings ArticleDOI
02 Oct 2020
TL;DR: This article proposed new pretrained contextualized representations of words and entities based on the bidirectional transformer, which treats words and entity in a given text as independent tokens, and outputs contextualised representations of them.
Abstract: Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and entities in a given text as independent tokens, and outputs contextualized representations of them. Our model is trained using a new pretraining task based on the masked language model of BERT. The task involves predicting randomly masked words and entities in a large entity-annotated corpus retrieved from Wikipedia. We also propose an entity-aware self-attention mechanism that is an extension of the self-attention mechanism of the transformer, and considers the types of tokens (words or entities) when computing attention scores. The proposed model achieves impressive empirical performance on a wide range of entity-related tasks. In particular, it obtains state-of-the-art results on five well-known datasets: Open Entity (entity typing), TACRED (relation classification), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), and SQuAD 1.1 (extractive question answering). Our source code and pretrained representations are available at https://github.com/studio-ousia/luke.

142 citations


Cited by
More filters
Proceedings ArticleDOI
Zhengyan Zhang1, Xu Han1, Zhiyuan Liu1, Xin Jiang2, Maosong Sun1, Qun Liu2 
17 May 2019
TL;DR: This paper utilizes both large-scale textual corpora and KGs to train an enhanced language representation model (ERNIE) which can take full advantage of lexical, syntactic, and knowledge information simultaneously, and is comparable with the state-of-the-art model BERT on other common NLP tasks.
Abstract: Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks. However, the existing pre-trained language models rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better language understanding. We argue that informative entities in KGs can enhance language representation with external knowledge. In this paper, we utilize both large-scale textual corpora and KGs to train an enhanced language representation model (ERNIE), which can take full advantage of lexical, syntactic, and knowledge information simultaneously. The experimental results have demonstrated that ERNIE achieves significant improvements on various knowledge-driven tasks, and meanwhile is comparable with the state-of-the-art model BERT on other common NLP tasks. The code and datasets will be available in the future.

1,076 citations

Journal Article
TL;DR: An efficient deep learning approach is developed that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems, and unifies concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate chemical space predictions.
Abstract: Learning from data has led to paradigm shifts in a multitude of disciplines, including web, text and image search, speech recognition, as well as bioinformatics. Can machine learning enable similar breakthroughs in understanding quantum many-body systems? Here we develop an efficient deep learning approach that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems. We unify concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate (1 kcal mol−1) predictions in compositional and configurational chemical space for molecules of intermediate size. As an example of chemical relevance, the model reveals a classification of aromatic rings with respect to their stability. Further applications of our model for predicting atomic energies and local chemical potentials in molecules, reliable isomer energies, and molecules with peculiar electronic structure demonstrate the potential of machine learning for revealing insights into complex quantum-chemical systems.

570 citations

Proceedings ArticleDOI
01 Jul 2019
TL;DR: A new word replacement order determined by both the wordsaliency and the classification probability is introduced, and a greedy algorithm called probability weighted word saliency (PWWS) is proposed for text adversarial attack.
Abstract: We address the problem of adversarial attacks on text classification, which is rarely studied comparing to attacks on image classification. The challenge of this task is to generate adversarial examples that maintain lexical correctness, grammatical correctness and semantic similarity. Based on the synonyms substitution strategy, we introduce a new word replacement order determined by both the word saliency and the classification probability, and propose a greedy algorithm called probability weighted word saliency (PWWS) for text adversarial attack. Experiments on three popular datasets using convolutional as well as LSTM models show that PWWS reduces the classification accuracy to the most extent, and keeps a very low word substitution rate. A human evaluation study shows that our generated adversarial examples maintain the semantic similarity well and are hard for humans to perceive. Performing adversarial training using our perturbed datasets improves the robustness of the models. At last, our method also exhibits a good transferability on the generated adversarial examples.

501 citations

Journal ArticleDOI
TL;DR: This paper provided a comprehensive review of more than 150 deep learning-based models for text classification developed in recent years, and discussed their technical contributions, similarities, and strengths, and provided a quantitative analysis of the performance of different deep learning models on popular benchmarks.
Abstract: Deep learning--based models have surpassed classical machine learning--based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural language inference. In this article, we provide a comprehensive review of more than 150 deep learning--based models for text classification developed in recent years, and we discuss their technical contributions, similarities, and strengths. We also provide a summary of more than 40 popular datasets widely used for text classification. Finally, we provide a quantitative analysis of the performance of different deep learning models on popular benchmarks, and we discuss future research directions.

457 citations

Journal ArticleDOI
TL;DR: In this paper, a deep multi-task artificial neural network is used to predict multiple electronic ground-and excited-state properties, such as atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity, and excitation energies.
Abstract: The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amount of data amenable to intelligent data analysis for the identification of meaningful, novel, and predictive structure-property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compounds that are synthetically accessible. Here, we present a machine learning (ML) model, trained on a data base of \textit{ab initio} calculation results for thousands of organic molecules, that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity, and excitation energies. The ML model is based on a deep multi-task artificial neural network, exploiting underlying correlations between various molecular properties. The input is identical to \emph{ab initio} methods, \emph{i.e.} nuclear charges and Cartesian coordinates of all atoms. For small organic molecules the accuracy of such a "Quantum Machine" is similar, and sometimes superior, to modern quantum-chemical methods---at negligible computational cost.

456 citations