arXiv subjects

Yue Zhang

Publications and source records attributed to Yue Zhang.

At least 595 records · Page 33Linked to original sources

arXiv2022

Mining Error Templates for Grammatical Error Correction

Some grammatical error correction (GEC) systems incorporate hand-crafted rules and achieve positive results. However, manually defining rules is time-consuming and laborious. In view of this, we propose a method to mine error templates for GEC automatically. An error template is a regular expression aiming at identifying text errors. We use the web crawler to acquire such error templates from the Internet. For each template, we further select the corresponding corrective action by using the language model perplexity as a criterion. We have accumulated 1,119 error templates for Chinese GEC based on this method. Experimental results on the newly proposed CTC-2021 Chinese GEC benchmark show that combing our error templates can effectively improve the performance of a strong GEC system, especially on two error types with very little training data. Our error templates are available at \url{https://github.com/HillZhang1999/gec_error_template}.

cs.CL↗

arXiv2022

Supervised Off-Policy Ranking

Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end goal of OPE is to compare two or multiple candidate policies and choose a good one, which is a much simpler task than precisely evaluating their true performance; and (2) there are usually multiple policies that have been deployed to serve users in real-world systems and thus the true performance of these policies can be known. Inspired by the two observations, in this work, we study a new problem, supervised off-policy ranking (SOPR), which aims to rank a set of target policies based on supervised learning by leveraging off-policy data and policies with known performance. We propose a method to solve SOPR, which learns a policy scoring model by minimizing a ranking loss of the training policies rather than estimating the precise policy performance. The scoring model in our method, a hierarchical Transformer based model, maps a set of state-action pairs to a score, where the state of each pair comes from the off-policy data and the action is taken by a target policy on the state in an offline manner. Extensive experiments on public datasets show that our method outperforms baseline methods in terms of rank correlation, regret value, and stability. Our code is publicly available at GitHub.

cs.LG↗

arXiv2022

whu-nercms at trecvid2021:instance search task

We will make a brief introduction of the experimental methods and results of the WHU-NERCMS in the TRECVID2021 in the paper. This year we participate in the automatic and interactive tasks of Instance Search (INS). For the automatic task, the retrieval target is divided into two parts, person retrieval, and action retrieval. We adopt a two-stage method including face detection and face recognition for person retrieval and two kinds of action detection methods consisting of three frame-based human-object interaction detection methods and two video-based general action detection methods for action retrieval. After that, the person retrieval results and action retrieval results are fused to initialize the result ranking lists. In addition, we make attempts to use complementary methods to further improve search performance. For interactive tasks, we test two different interaction strategies on the fusion results. We submit 4 runs for automatic and interactive tasks respectively. The introduction of each run is shown in Table 1. The official evaluations show that the proposed strategies rank 1st in both automatic and interactive tracks.

cs.CV↗

arXiv2022

Intimate Relationship Between Sterile Neutrino Dark Matter and $ΔN_{\rm eff}$

The self-interacting neutrino hypothesis is well motivated for addressing the tension between the origin of sterile neutrino dark matter and indirect detection constraints. It can also result in a number of testable signals from the laboratories to the cosmos. We explore a model of neutrino self-interaction mediated by a Majoron-like scalar with sub-MeV mass, and show that explaining the relic density of sterile neutrino dark matter implies a lower bound on the amount of extra radiation in early universe, in particular $ΔN_{\rm eff}>0.12$ at the CMB epoch. This lower bound will be further strengthened with an improved $X$-ray search at the Athena observatory. Such an intimate relationship will be unambiguously tested by the upcoming CMB-S4 project.

hep-ph↗

arXiv2022

The Forward Physics Facility: Sites, Experiments, and Physics Potential

The Forward Physics Facility (FPF) is a proposal to create a cavern with the space and infrastructure to support a suite of far-forward experiments at the Large Hadron Collider during the High Luminosity era. Located along the beam collision axis and shielded from the interaction point by at least 100 m of concrete and rock, the FPF will house experiments that will detect particles outside the acceptance of the existing large LHC experiments and will observe rare and exotic processes in an extremely low-background environment. In this work, we summarize the current status of plans for the FPF, including recent progress in civil engineering in identifying promising sites for the FPF and the experiments currently envisioned to realize the FPF's physics potential. We then review the many Standard Model and new physics topics that will be advanced by the FPF, including searches for long-lived particles, probes of dark matter and dark sectors, high-statistics studies of TeV neutrinos of all three flavors, aspects of perturbative and non-perturbative QCD, and high-energy astroparticle physics.

hep-ph↗

arXiv2022

A Graph Enhanced BERT Model for Event Prediction

Predicting the subsequent event for an existing event context is an important but challenging task, as it requires understanding the underlying relationship between events. Previous methods propose to retrieve relational features from event graph to enhance the modeling of event correlation. However, the sparsity of event graph may restrict the acquisition of relevant graph information, and hence influence the model performance. To address this issue, we consider automatically building of event graph using a BERT model. To this end, we incorporate an additional structured variable into BERT to learn to predict the event connections in the training process. Hence, in the test process, the connection relationship for unseen events can be predicted by the structured variable. Results on two event prediction tasks: script event prediction and story ending prediction, show that our approach can outperform state-of-the-art baseline methods.

cs.CL↗

arXiv2022

Graph Pre-training for AMR Parsing and Generation

Abstract meaning representation (AMR) highlights the core semantic information of text in a graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation, respectively. However, PLMs are typically pre-trained on textual data, thus are sub-optimal for modeling structural knowledge. To this end, we investigate graph self-supervised training to improve the structure awareness of PLMs over AMR graphs. In particular, we introduce two graph auto-encoding strategies for graph-to-graph pre-training and four tasks to integrate text and graph information during pre-training. We further design a unified framework to bridge the gap between pre-training and fine-tuning tasks. Experiments on both AMR parsing and AMR-to-text generation show the superiority of our model. To our knowledge, we are the first to consider pre-training on semantic graphs.

cs.CL↗

arXiv2022

MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction

This paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7,063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources. Each sentence is corrected by three annotators, and their corrections are carefully reviewed by a senior annotator, resulting in 2.3 references per sentence. We conduct experiments with two mainstream CGEC models, i.e., the sequence-to-sequence model and the sequence-to-edit model, both enhanced with large pretrained language models, achieving competitive benchmark performance on previous and our datasets. We also discuss CGEC evaluation methodologies, including the effect of multiple references and using a char-based metric. Our annotation guidelines, data, and code are available at \url{https://github.com/HillZhang1999/MuCGEC}.

cs.CL↗

arXiv2022

The Cross-lingual Conversation Summarization Challenge

We propose the shared task of cross-lingual conversation summarization, \emph{ConvSumX Challenge}, opening new avenues for researchers to investigate solutions that integrate conversation summarization and machine translation. This task can be particularly useful due to the emergence of online meetings and conferences. We construct a new benchmark, covering 2 real-world scenarios and 3 language directions, including a low-resource language. We hope that \emph{ConvSumX} can motivate researches to go beyond English and break the barrier for non-English speakers to benefit from recent advances of conversation summarization.

cs.CL↗

arXiv2022

Computing the Lyapunov operator φ-functions, with an application to matrix-valued exponential integrators

In this paper, we develop efficient and accurate evaluation for the Lyapunov operator function $φ_l(\mathcal{L}_A)[Q],$ where $φ_l(\cdot)$ is the function related to the exponential, $\mathcal{L}_A$ is a Lyapunov operator and $Q$ is a symmetric and full-rank matrix. An important application of the algorithm is to the matrix-valued exponential integrators for matrix differential equations such as differential Lyapunov equations and differential Riccati equations. The method is exploited by using the modified scaling and squaring procedure combined with the truncated Taylor series. A quasi-backward error analysis is presented to determine the value of the scaling parameter and the degree of the Taylor approximation. Numerical experiments show that the algorithm performs well in both accuracy and efficiency.

math.NA↗

arXiv2022

An Efficient Approach for Optimizing the Cost-effective Individualized Treatment Rule Using Conditional Random Forest

Evidence from observational studies has become increasingly important for supporting healthcare policy making via cost-effectiveness (CE) analyses. Similar as in comparative effectiveness studies, health economic evaluations that consider subject-level heterogeneity produce individualized treatment rules (ITRs) that are often more cost-effective than one-size-fits-all treatment. Thus, it is of great interest to develop statistical tools for learning such a cost-effective ITR (CE-ITR) under the causal inference framework that allows proper handling of potential confounding and can be applied to both trials and observational studies. In this paper, we use the concept of net-monetary-benefit (NMB) to assess the trade-off between health benefits and related costs. We estimate CE-ITR as a function of patients' characteristics that, when implemented, optimizes the allocation of limited healthcare resources by maximizing health gains while minimizing treatment-related costs. We employ the conditional random forest approach and identify the optimal CE-ITR using NMB-based classification algorithms, where two partitioned estimators are proposed for the subject-specific weights to effectively incorporate information from censored individuals. We conduct simulation studies to evaluate the performance of our proposals. We apply our top-performing algorithm to the NIH-funded Systolic Blood Pressure Intervention Trial (SPRINT) to illustrate the CE gains of assigning customized intensive blood pressure therapy.

stat.ME↗

arXiv2022

Challenges for Open-domain Targeted Sentiment Analysis

Since previous studies on open-domain targeted sentiment analysis are limited in dataset domain variety and sentence level, we propose a novel dataset consisting of 6,013 human-labeled data to extend the data domains in topics of interest and document level. Furthermore, we offer a nested target annotation schema to extract the complete sentiment information in documents, boosting the practicality and effectiveness of open-domain targeted sentiment analysis. Moreover, we leverage the pre-trained model BART in a sequence-to-sequence generation method for the task. Benchmark results show that there exists large room for improvement of open-domain targeted sentiment analysis. Meanwhile, experiments have shown that challenges remain in the effective use of open-domain data, long documents, the complexity of target structure, and domain variances.

cs.CL↗

arXiv2022

Towards Fine-grained Causal Reasoning and QA

Understanding causality is key to the success of NLP applications, especially in high-stakes domains. Causality comes in various perspectives such as enable and prevent that, despite their importance, have been largely ignored in the literature. This paper introduces a novel fine-grained causal reasoning dataset and presents a series of novel predictive tasks in NLP, such as causality detection, event causality extraction, and Causal QA. Our dataset contains human annotations of 25K cause-effect event pairs and 24K question-answering pairs within multi-sentence samples, where each can have multiple causal relationships. Through extensive experiments and analysis, we show that the complex relations in our dataset bring unique challenges to state-of-the-art methods across all three tasks and highlight potential research opportunities, especially in developing "causal-thinking" methods.

cs.CL↗

arXiv2022

DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning

Optimizing the combustion efficiency of a thermal power generating unit (TPGU) is a highly challenging and critical task in the energy industry. We develop a new data-driven AI system, namely DeepThermal, to optimize the combustion control strategy for TPGUs. At its core, is a new model-based offline reinforcement learning (RL) framework, called MORE, which leverages historical operational data of a TGPU to solve a highly complex constrained Markov decision process problem via purely offline training. In DeepThermal, we first learn a data-driven combustion process simulator from the offline dataset. The RL agent of MORE is then trained by combining real historical data as well as carefully filtered and processed simulation data through a novel restrictive exploration scheme. DeepThermal has been successfully deployed in four large coal-fired thermal power plants in China. Real-world experiments show that DeepThermal effectively improves the combustion efficiency of TPGUs. We also report the superior performance of MORE by comparing with the state-of-the-art algorithms on the standard offline RL benchmarks.

cs.LG↗

arXiv2022

Investigating Non-local Features for Neural Constituency Parsing

Thanks to the strong representation power of neural encoders, neural chart-based parsers have achieved highly competitive performance by using local features. Recently, it has been shown that non-local features in CRF structures lead to improvements. In this paper, we investigate injecting non-local features into the training process of a local span-based parser, by predicting constituent n-gram non-local patterns and ensuring consistency between non-local patterns and local constituents. Results show that our simple method gives better results than the self-attentive parser on both PTB and CTB. Besides, our method achieves state-of-the-art BERT-based performance on PTB (95.92 F1) and strong performance on CTB (92.31 F1). Our parser also achieves better or competitive performance in multilingual and zero-shot cross-domain settings compared with the baseline.

cs.CL↗

arXiv2022

Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis

While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that may exist in their training and test data. Such issues come to be manifest in performance problems when faced with out-of-distribution data in the field. One recent solution has been to use counterfactually augmented datasets in order to reduce any reliance on spurious patterns that may exist in the original data. Producing high-quality augmented data can be costly and time-consuming as it usually needs to involve human feedback and crowdsourcing efforts. In this work, we propose an alternative by describing and evaluating an approach to automatically generating counterfactual data for data augmentation and explanation. A comprehensive evaluation on several different datasets and using a variety of state-of-the-art benchmarks demonstrate how our approach can achieve significant improvements in model performance when compared to models training on the original data and even when compared to models trained with the benefit of human-generated augmented data.

cs.CL↗

arXiv2022

A Rationale-Centric Framework for Human-in-the-loop Machine Learning

We present a novel rationale-centric framework with human-in-the-loop -- Rationales-centric Double-robustness Learning (RDL) -- to boost model out-of-distribution performance in few-shot learning scenarios. By using static semi-factual generation and dynamic human-intervened correction, RDL exploits rationales (i.e. phrases that cause the prediction), human interventions and semi-factual augmentations to decouple spurious associations and bias models towards generally applicable underlying distributions, which enables fast and accurate generalisation. Experimental results show that RDL leads to significant prediction benefits on both in-distribution and out-of-distribution tests compared to many state-of-the-art benchmarks -- especially for few-shot learning scenarios. We also perform extensive ablation studies to support in-depth analyses of each component in our framework.

cs.AI↗

arXiv2022

Guts in Sutured Decompositions and the Thurston Norm

We construct an invariant called guts for second homology classes in irreducible 3-manifolds with toral boundary and non-degenerate Thurston norm. We prove that the guts of second homology classes in each Thurston cone are invariant under a natural condition. We show that the guts of different homology classes are related by sutured decompositions. As an application, an invariant of knot complements is given and is computed in a few interesting cases. Besides, we show that the dimension of a maximal simplex in a Kakimizu Complex is an invariant.

math.GT↗