arXiv subjects

Jun Suzuki

Publications and source records attributed to Jun Suzuki.

At least 91 records · Page 5Linked to original sources

arXiv2020

A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction

Existing approaches for grammatical error correction (GEC) largely rely on supervised learning with manually created GEC datasets. However, there has been little focus on verifying and ensuring the quality of the datasets, and on how lower-quality data might affect GEC performance. We indeed found that there is a non-negligible amount of "noise" where errors were inappropriately edited or left uncorrected. To address this, we designed a self-refinement method where the key idea is to denoise these datasets by leveraging the prediction consistency of existing models, and outperformed strong denoising baseline methods. We further applied task-specific techniques and achieved state-of-the-art performance on the CoNLL-2014, JFLEG, and BEA-2019 benchmarks. We then analyzed the effect of the proposed denoising method, and found that our approach leads to improved coverage of corrections and facilitated fluency edits which are reflected in higher recall and overall performance.

cs.CL↗

arXiv2020

Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness

Large-scale dialogue datasets have recently become available for training neural dialogue agents. However, these datasets have been reported to contain a non-negligible number of unacceptable utterance pairs. In this paper, we propose a method for scoring the quality of utterance pairs in terms of their connectivity and relatedness. The proposed scoring method is designed based on findings widely shared in the dialogue and linguistics research communities. We demonstrate that it has a relatively good correlation with the human judgment of dialogue quality. Furthermore, the method is applied to filter out potentially unacceptable utterance pairs from a large-scale noisy dialogue corpus to ensure its quality. We experimentally confirm that training data filtered by the proposed method improves the quality of neural dialogue agents in response generation.

cs.CL↗

arXiv2020

Error trade-off relations for two-parameter unitary model with commuting generators

We investigate whether a trade-off relation between the diagonal elements of the mean square error matrix exists for the two-parameter unitary models with mutually commuting generators. We show that the error trade-off relation which exists in our models of a finite dimension system is a generic phenomenon in the sense that it occurs with a finite volume in the spate space. We analyze a qutrit system to show that there can be an error trade-off relation given by the SLD and RLD Cramer-Rao bounds that intersect each other. First, we analyze an example of the reference state showing the non-trivial trade-off relation numerically, and find that its eigenvalues must be in a certain range to exhibit the trade-off relation. For another example, one-parameter family of reference states, we analytically show that the non-trivial relation always exists and that the range where the trade-off relation exists is up to about a half of the possible range.

quant-ph↗

arXiv2020

Direct estimation of minimum gate fidelity

With the current interest in building quantum computers, there is a strong need for accurate and efficient characterization of the noise in quantum gate implementations. A key measure of the performance of a quantum gate is the minimum gate fidelity, i.e., the fidelity of the gate, minimized over all input states. Conventionally, the minimum fidelity is estimated by first accurately reconstructing the full gate process matrix using the experimental procedure of quantum process tomography (QPT). Then, a numerical minimization is carried out to find the minimum fidelity. QPT is, however, well known to be costly, and it might appear that we can do better, if the goal is only to estimate one single number. In this work, we propose a hybrid numerical-experimental scheme that employs a numerical gradient-free minimization (GFM) and an experimental target-fidelity estimation procedure to directly estimate the minimum fidelity without reconstructing the process matrix. We compare this to an alternative scheme, referred to as QPT fidelity estimation, that does use QPT, but directly employs the minimum gate fidelity as the termination criterion. Both approaches can thus be considered as direct estimation schemes. General theoretical bounds suggest a significant resource savings for the GFM scheme over QPT fidelity estimation; numerical simulations for specific classes of noise, however, show that both schemes have similar performance, reminding us of the need for caution when using general bounds for specific examples. The GFM scheme, however, presents potential for future improvements in resource cost, with the development of even more efficient GFM algorithms.

quant-ph↗

arXiv2020

Robust phase estimation of Gaussian states in the presence of outlier quantum states

In this paper, we investigate the problem of estimating the phase of a coherent state in the presence of unavoidable noisy quantum states. These unwarranted quantum states are represented by outlier quantum states in this study. We first present a statistical framework of robust statistics in a quantum system to handle outlier quantum states. We then apply the method of M-estimators to suppress untrusted measurement outcomes due to outlier quantum states. Our proposal has the advantage over the classical methods in being systematic, easy to implement, and robust against occurrence of noisy states.

quant-ph↗

arXiv2020

Uncertainty relation for the position of an electron in a uniform magnetic field from quantum estimation theory

We investigate the uncertainty relation for estimating the position of one electron in a uniform magnetic field in the framework of the quantum estimation theory. Two kinds of momenta, canonical one and mechanical one, are used to generate a shift in the position of the electron. We first consider pure state models whose wave function is in the ground state with zero angular momentum. The model generated by the two-commuting canonical momenta becomes the quasi-classical model, in which the symmetric logarithmic derivative quantum Cramér-Rao bound is achievable. The model generated by the two non-commuting mechanical momenta, on the other hand, turns out to be a Gaussian model, where the generalized right logarithmic derivative quantum Cramér-Rao bound is achievable. We next consider mixed-state models by taking into account the effects of thermal noise. The model with the canonical momenta now becomes genuine quantum mechanical, although its generators commute with each other. The derived uncertainty relationship is in general determined by two different quantum Cramér-Rao bounds in a non-trivial manner. The model with the mechanical momenta is identified with the well-known Gaussian shift model, and the uncertainty relation is governed by the right logarithmic derivative Cramér-Rao bound.

quant-ph↗

arXiv2020

Quantum state estimation with nuisance parameters

In parameter estimation, nuisance parameters refer to parameters that are not of interest but nevertheless affect the precision of estimating other parameters of interest. For instance, the strength of noises in a probe can be regarded as a nuisance parameter. Despite its long history in classical statistics, the nuisance parameter problem in quantum estimation remains largely unexplored. The goal of this article is to provide a systematic review of quantum estimation in the presence of nuisance parameters, and to supply those who work in quantum tomography and quantum metrology with tools to tackle relevant problems. After an introduction to the nuisance parameter and quantum estimation theory, we explicitly formulate the problem of quantum state estimation with nuisance parameters. We extend quantum Cramer-Rao bounds to the nuisance parameter case and provide a parameter orthogonalization tool to separate the nuisance parameters from the parameters of interest. In particular, we put more focus on the case of one-parameter estimation in the presence of nuisance parameters, as it is most frequently encountered in practice.

quant-ph↗

arXiv2020

Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition

In general, the labels used in sequence labeling consist of different types of elements. For example, IOB-format entity labels, such as B-Person and I-Person, can be decomposed into span (B and I) and type information (Person). However, while most sequence labeling models do not consider such label components, the shared components across labels, such as Person, can be beneficial for label prediction. In this work, we propose to integrate label component information as embeddings into models. Through experiments on English and Japanese fine-grained named entity recognition, we demonstrate that the proposed method improves performance, especially for instances with low-frequency labels.

cs.CL↗

arXiv2020

Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction

This paper investigates how to effectively incorporate a pre-trained masked language model (MLM), such as BERT, into an encoder-decoder (EncDec) model for grammatical error correction (GEC). The answer to this question is not as straightforward as one might expect because the previous common methods for incorporating a MLM into an EncDec model have potential drawbacks when applied to GEC. For example, the distribution of the inputs to a GEC model can be considerably different (erroneous, clumsy, etc.) from that of the corpora used for pre-training MLMs; however, this issue is not addressed in the previous methods. Our experiments show that our proposed method, where we first fine-tune a MLM with a given GEC corpus and then use the output of the fine-tuned MLM as additional features in the GEC model, maximizes the benefit of the MLM. The best-performing model achieves state-of-the-art performances on the BEA-2019 and CoNLL-2014 benchmarks. Our code is publicly available at: https://github.com/kanekomasahiro/bert-gec.

cs.CL↗

arXiv2020

Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese

We examine a methodology using neural language models (LMs) for analyzing the word order of language. This LM-based method has the potential to overcome the difficulties existing methods face, such as the propagation of preprocessor errors in count-based methods. In this study, we explore whether the LM-based method is valid for analyzing the word order. As a case study, this study focuses on Japanese due to its complex and flexible word order. To validate the LM-based method, we test (i) parallels between LMs and human word order preference, and (ii) consistency of the results obtained using the LM-based method with previous linguistic studies. Through our experiments, we tentatively conclude that LMs display sufficient word order knowledge for usage as an analysis tool. Finally, using the LM-based method, we demonstrate the relationship between the canonical word order and topicalization, which had yet to be analyzed by large-scale experiments.

cs.CL↗

arXiv2020

Single Model Ensemble using Pseudo-Tags and Distinct Vectors

Model ensemble techniques often increase task performance in neural networks; however, they require increased time, memory, and management effort. In this study, we propose a novel method that replicates the effects of a model ensemble with a single model. Our approach creates K-virtual models within a single parameter space using K-distinct pseudo-tags and K-distinct vectors. Experiments on text classification and sequence labeling tasks on several datasets demonstrate that our method emulates or outperforms a traditional model ensemble with 1/K-times fewer parameters.

cs.CL↗

arXiv2020

Evaluating Dialogue Generation Systems via Response Selection

Existing automatic evaluation metrics for open-domain dialogue response generation systems correlate poorly with human evaluation. We focus on evaluating response generation systems via response selection. To evaluate systems properly via response selection, we propose the method to construct response selection test sets with well-chosen false candidates. Specifically, we propose to construct test sets filtering out some types of false candidates: (i) those unrelated to the ground-truth response and (ii) those acceptable as appropriate responses. Through experiments, we demonstrate that evaluating systems via response selection with the test sets developed by our method correlates more strongly with human evaluation, compared with widely used automatic evaluation metrics such as BLEU.

cs.CL↗

arXiv2020

Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition

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.

cs.CL↗

arXiv2020

JParaCrawl: A Large Scale Web-Based English-Japanese Parallel Corpus

Recent machine translation algorithms mainly rely on parallel corpora. However, since the availability of parallel corpora remains limited, only some resource-rich language pairs can benefit from them. We constructed a parallel corpus for English-Japanese, for which the amount of publicly available parallel corpora is still limited. We constructed the parallel corpus by broadly crawling the web and automatically aligning parallel sentences. Our collected corpus, called JParaCrawl, amassed over 8.7 million sentence pairs. We show how it includes a broader range of domains and how a neural machine translation model trained with it works as a good pre-trained model for fine-tuning specific domains. The pre-training and fine-tuning approaches achieved or surpassed performance comparable to model training from the initial state and reduced the training time. Additionally, we trained the model with an in-domain dataset and JParaCrawl to show how we achieved the best performance with them. JParaCrawl and the pre-trained models are freely available online for research purposes.

cs.CL↗

arXiv2020

User-specified random sampling of quantum channels and its applications

Random samples of quantum channels have many applications in quantum information processing tasks. Due to the Choi--Jamiołkowski isomorphism, there is a well-known correspondence between channels and states, and one can imagine adapting \emph{state} sampling methods to sample quantum channels. Here, we discuss such an adaptation, using the Hamiltonian Monte Carlo method, a well-known classical method capable of producing high quality samples from arbitrary, user-specified distributions. Its implementation requires an exact parameterization of the space of quantum channels, with no superfluous parameters and no constraints. We construct such a parameterization, and demonstrate its use in three common channel sampling applications.

quant-ph↗

arXiv2019

Diamonds in the Rough: Generating Fluent Sentences from Early-Stage Drafts for Academic Writing Assistance

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, spelling, 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.

cs.CL↗

arXiv2019

Select and Attend: Towards Controllable Content Selection in Text Generation

Many text generation tasks naturally contain two steps: content selection and surface realization. Current neural encoder-decoder models conflate both steps into a black-box architecture. As a result, the content to be described in the text cannot be explicitly controlled. This paper tackles this problem by decoupling content selection from the decoder. The decoupled content selection is human interpretable, whose value can be manually manipulated to control the content of generated text. The model can be trained end-to-end without human annotations by maximizing a lower bound of the marginal likelihood. We further propose an effective way to trade-off between performance and controllability with a single adjustable hyperparameter. In both data-to-text and headline generation tasks, our model achieves promising results, paving the way for controllable content selection in text generation.

cs.CL↗

arXiv2019

TEASPN: Framework and Protocol for Integrated Writing Assistance Environments

Language technologies play a key role in assisting people with their writing. Although there has been steady progress in e.g., grammatical error correction (GEC), human writers are yet to benefit from this progress due to the high development cost of integrating with writing software. We propose TEASPN, a protocol and an open-source framework for achieving integrated writing assistance environments. The protocol standardizes the way writing software communicates with servers that implement such technologies, allowing developers and researchers to integrate the latest developments in natural language processing (NLP) with low cost. As a result, users can enjoy the integrated experience in their favorite writing software. The results from experiments with human participants show that users use a wide range of technologies and rate their writing experience favorably, allowing them to write more fluent text.

cs.CL↗