Ying Liu


2023

pdf bib
Adversarial Multi-task Learning for End-to-end Metaphor Detection
Shenglong Zhang | Ying Liu
Findings of the Association for Computational Linguistics: ACL 2023

Metaphor detection (MD) suffers from limited training data. In this paper, we started with a linguistic rule called Metaphor Identification Procedure and then proposed a novel multi-task learning framework to transfer knowledge in basic sense discrimination (BSD) to MD. BSD is constructed from word sense disambiguation (WSD), which has copious amounts of data. We leverage adversarial training to align the data distributions of MD and BSD in the same feature space, so task-invariant representations can be learned. To capture fine-grained alignment patterns, we utilize the multi-mode structures of MD and BSD. Our method is totally end-to-end and can mitigate the data scarcity problem in MD. Competitive results are reported on four public datasets. Our code and datasets are available.

pdf bib
Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation
Zhu Liu | Ying Liu
Findings of the Association for Computational Linguistics: ACL 2023

Word sense disambiguation (WSD), which aims to determine an appropriate sense for a target word given its context, is crucial for natural language understanding. Existing supervised methods treat WSD as a classification task and have achieved remarkable performance. However, they ignore uncertainty estimation (UE) in the real-world setting, where the data is always noisy and out of distribution. This paper extensively studies UE on the benchmark designed for WSD. Specifically, we first compare four uncertainty scores for a state-of-the-art WSD model and verify that the conventional predictive probabilities obtained at the end of the model are inadequate to quantify uncertainty. Then, we examine the capability of capturing data and model uncertainties by the model with the selected UE score on well-designed test scenarios and discover that the model reflects data uncertainty satisfactorily but underestimates model uncertainty. Furthermore, we explore numerous lexical properties that intrinsically affect data uncertainty and provide a detailed analysis of four critical aspects: the syntactic category, morphology, sense granularity, and semantic relations.

pdf bib
Always the Best Fit: Adaptive Domain Gap Filling from Causal Perspective for Few-Shot Relation Extraction
Ge Bai | Chenji Lu | Jiaxiang Geng | Shilong Li | Yidong Shi | Xiyan Liu | Ying Liu | Zhang Zhang | Ruifang Liu
Findings of the Association for Computational Linguistics: EMNLP 2023

Cross-domain Relation Extraction aims to transfer knowledge from a source domain to a different target domain to address low-resource challenges. However, the semantic gap caused by data bias between domains is a major challenge, especially in few-shot scenarios. Previous work has mainly focused on transferring knowledge between domains through shared feature representations without analyzing the impact of each factor that may produce data bias based on the characteristics of each domain. This work takes a causal perspective and proposes a new framework CausalGF. By constructing a unified structural causal model, we estimating the causal effects of factors such as syntactic structure, label distribution,and entities on the outcome. CausalGF calculates the causal effects among the factors and adjusts them dynamically based on domain characteristics, enabling adaptive gap filling. Our experiments show that our approach better fills the domain gap, yielding significantly better results on the cross-domain few-shot relation extraction task.

pdf bib
Granularity Matters: Pathological Graph-driven Cross-modal Alignment for Brain CT Report Generation
Yanzhao Shi | Junzhong Ji | Xiaodan Zhang | Liangqiong Qu | Ying Liu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

The automatic Brain CT reports generation can improve the efficiency and accuracy of diagnosing cranial diseases. However, current methods are limited by 1) coarse-grained supervision: the training data in image-text format lacks detailed supervision for recognizing subtle abnormalities, and 2) coupled cross-modal alignment: visual-textual alignment may be inevitably coupled in a coarse-grained manner, resulting in tangled feature representation for report generation. In this paper, we propose a novel Pathological Graph-driven Cross-modal Alignment (PGCA) model for accurate and robust Brain CT report generation. Our approach effectively decouples the cross-modal alignment by constructing a Pathological Graph to learn fine-grained visual cues and align them with textual words. This graph comprises heterogeneous nodes representing essential pathological attributes (i.e., tissue and lesion) connected by intra- and inter-attribute edges with prior domain knowledge. Through carefully designed graph embedding and updating modules, our model refines the visual features of subtle tissues and lesions and aligns them with textual words using contrastive learning. Extensive experimental results confirm the viability of our method. We believe that our PGCA model holds the potential to greatly enhance the automatic generation of Brain CT reports and ultimately contribute to improved cranial disease diagnosis.

2022

pdf bib
Cross-modal Contrastive Attention Model for Medical Report Generation
Xiao Song | Xiaodan Zhang | Junzhong Ji | Ying Liu | Pengxu Wei
Proceedings of the 29th International Conference on Computational Linguistics

Medical report automatic generation has gained increasing interest recently as a way to help radiologists write reports more efficiently. However, this image-to-text task is rather challenging due to the typical data biases: 1) Normal physiological structures dominate the images, with only tiny abnormalities; 2) Normal descriptions accordingly dominate the reports. Existing methods have attempted to solve these problems, but they neglect to exploit useful information from similar historical cases. In this paper, we propose a novel Cross-modal Contrastive Attention (CMCA) model to capture both visual and semantic information from similar cases, with mainly two modules: a Visual Contrastive Attention Module for refining the unique abnormal regions compared to the retrieved case images; a Cross-modal Attention Module for matching the positive semantic information from the case reports. Extensive experiments on two widely-used benchmarks, IU X-Ray and MIMIC-CXR, demonstrate that the proposed model outperforms the state-of-the-art methods on almost all metrics. Further analyses also validate that our proposed model is able to improve the reports with more accurate abnormal findings and richer descriptions.

pdf bib
Metaphor Detection via Linguistics Enhanced Siamese Network
Shenglong Zhang | Ying Liu
Proceedings of the 29th International Conference on Computational Linguistics

In this paper we present MisNet, a novel model for word level metaphor detection. MisNet converts two linguistic rules, i.e., Metaphor Identification Procedure (MIP) and Selectional Preference Violation (SPV) into semantic matching tasks. MIP module computes the similarity between the contextual meaning and the basic meaning of a target word. SPV module perceives the incongruity between target words and their contexts. To better represent basic meanings, MisNet utilizes dictionary resources. Empirical results indicate that MisNet achieves competitive performance on several datasets.

pdf bib
中文自然语言处理多任务中的职业性别偏见测量(Measurement of Occupational Gender Bias in Chinese Natural Language Processing Tasks)
Mengqing Guo (郭梦清) | Jiali Li (李加厉) | Jishun Zhao (赵继舜) | Shucheng Zhu (朱述承) | Ying Liu (刘颖) | Pengyuan Liu (刘鹏远)
Proceedings of the 21st Chinese National Conference on Computational Linguistics

“尽管悲观者认为,职场中永远不可能存在性别平等。但随着人们观念的转变,愈来愈多的人们相信,职业的选择应只与个人能力相匹配,而不应由个体的性别决定。目前已经发现自然语言处理的各个任务中都存在着职业性别偏见。但这些研究往往只针对特定的英文任务,缺乏针对中文的、综合多任务的职业性别偏见测量研究。本文基于霍兰德职业模型,从中文自然语言处理中常见的三个任务出发,测量了词向量、共指消解和文本生成中的职业性别偏见,发现不同任务中的职业性别偏见既有一定的共性,又存在着独特的差异性。总体来看,不同任务中的职业性别偏见反映了现实生活中人们对于不同性别所选择职业的刻板印象。此外,在设计不同任务的偏见测量指标时,还需要考虑如语体、词序等语言学要素的影响。”

pdf bib
Analysis of Gender Bias in Social Perception and Judgement Using Chinese Word Embeddings
Jiali Li | Shucheng Zhu | Ying Liu | Pengyuan Liu
Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)

Gender is a construction in line with social perception and judgment. An important means of this construction is through languages. When natural language processing tools, such as word embeddings, associate gender with the relevant categories of social perception and judgment, it is likely to cause bias and harm to those groups that do not conform to the mainstream social perception and judgment. Using 12,251 Chinese word embeddings as intermedium, this paper studies the relationship between social perception and judgment categories and gender. The results reveal that these grammatical gender-neutral Chinese word embeddings show a certain gender bias, which is consistent with the mainstream society’s perception and judgment of gender. Men are judged by their actions and perceived as bad, easily-disgusted, bad-tempered and rational roles while women are judged by their appearances and perceived as perfect, either happy or sad, and emotional roles.

2021

pdf bib
Native Language Identification and Reconstruction of Native Language Relationship Using Japanese Learner Corpus
Mitsuhiro Nishijima | Ying Liu
Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation

pdf bib
K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce
Song Xu | Haoran Li | Peng Yuan | Yujia Wang | Youzheng Wu | Xiaodong He | Ying Liu | Bowen Zhou
Findings of the Association for Computational Linguistics: EMNLP 2021

Existing pre-trained language models (PLMs) have demonstrated the effectiveness of self-supervised learning for a broad range of natural language processing (NLP) tasks. However, most of them are not explicitly aware of domain-specific knowledge, which is essential for downstream tasks in many domains, such as tasks in e-commerce scenarios. In this paper, we propose K-PLUG, a knowledge-injected pre-trained language model based on the encoder-decoder transformer that can be transferred to both natural language understanding and generation tasks. Specifically, we propose five knowledge-aware self-supervised pre-training objectives to formulate the learning of domain-specific knowledge, including e-commerce domain-specific knowledge-bases, aspects of product entities, categories of product entities, and unique selling propositions of product entities. We verify our method in a diverse range of e-commerce scenarios that require domain-specific knowledge, including product knowledge base completion, abstractive product summarization, and multi-turn dialogue. K-PLUG significantly outperforms baselines across the board, which demonstrates that the proposed method effectively learns a diverse set of domain-specific knowledge for both language understanding and generation tasks. Our code is available.

pdf bib
SaGE: 基于句法感知图卷积神经网络和ELECTRA的中文隐喻识别模型(SaGE: Syntax-aware GCN with ELECTRA for Chinese Metaphor Detection)
Shenglong Zhang (张声龙) | Ying Liu (刘颖) | Yanjun Ma (马艳军)
Proceedings of the 20th Chinese National Conference on Computational Linguistics

隐喻是人类语言中经常出现的一种特殊现象,隐喻识别对于自然语言处理各项任务来说具有十分基础和重要的意义。针对中文领域的隐喻识别任务,我们提出了一种基于句法感知图卷积神经网络和ELECTRA的隐喻识别模型(Syntax-aware GCN withELECTRA SaGE)。该模型从语言学出发,使用ELECTRA和Transformer编码器抽取句子的语义特征,将句子按照依存关系组织成一张图并使用图卷积神经网络抽取其句法特征,在此基础上对两类特征进行融合以进行隐喻识别。我们的模型在CCL2018中文隐喻识别评测数据集上以85.22%的宏平均F1分数超越了此前的最佳成绩,验证了融合语义信息和句法信息对于隐喻识别任务具有重要作用。

2020

pdf bib
Modularized Syntactic Neural Networks for Sentence Classification
Haiyan Wu | Ying Liu | Shaoyun Shi
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

This paper focuses on tree-based modeling for the sentence classification task. In existing works, aggregating on a syntax tree usually considers local information of sub-trees. In contrast, in addition to the local information, our proposed Modularized Syntactic Neural Network (MSNN) utilizes the syntax category labels and takes advantage of the global context while modeling sub-trees. In MSNN, each node of a syntax tree is modeled by a label-related syntax module. Each syntax module aggregates the outputs of lower-level modules, and finally, the root module provides the sentence representation. We design a tree-parallel mini-batch strategy for efficient training and predicting. Experimental results on four benchmark datasets show that our MSNN significantly outperforms previous state-of-the-art tree-based methods on the sentence classification task.

pdf bib
用计量风格学方法考察《水浒传》的作者争议问题——以罗贯中《平妖传》为参照(Quantitive Stylistics Based Research on the Controversy of the Author of “Tales of the Marshes”: Comparing with “Pingyaozhuan” of Luo Guanzhong)
Li Song (宋丽) | Ying Liu (刘颖)
Proceedings of the 19th Chinese National Conference on Computational Linguistics

《水浒传》是独著还是合著,施耐庵和罗贯中是何关系一直存在争议。本文将其作者争议粗略归纳为施耐庵作、罗贯中作、施作罗续、罗作他续、施作罗改五种情况,以罗贯中的《平妖传》为参照,用假设检验、文本聚类、文本分类、波动风格计量等方法,结合对文本内容的分析,考察《水浒传》的写作风格,试图为其作者身份认定提供参考。结果显示,只有罗作他续的可能性大,即前70回为罗贯中所作,后由他人续写,其他四种情况可能性都较小。

2019

pdf bib
Relation Extraction with Temporal Reasoning Based on Memory Augmented Distant Supervision
Jianhao Yan | Lin He | Ruqin Huang | Jian Li | Ying Liu
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Distant supervision (DS) is an important paradigm for automatically extracting relations. It utilizes existing knowledge base to collect examples for the relation we intend to extract, and then uses these examples to automatically generate the training data. However, the examples collected can be very noisy, and pose significant challenge for obtaining high quality labels. Previous work has made remarkable progress in predicting the relation from distant supervision, but typically ignores the temporal relations among those supervising instances. This paper formulates the problem of relation extraction with temporal reasoning and proposes a solution to predict whether two given entities participate in a relation at a given time spot. For this purpose, we construct a dataset called WIKI-TIME which additionally includes the valid period of a certain relation of two entities in the knowledge base. We propose a novel neural model to incorporate both the temporal information encoding and sequential reasoning. The experimental results show that, compared with the best of existing models, our model achieves better performance in both WIKI-TIME dataset and the well-studied NYT-10 dataset.

2015

pdf bib
A Corpus-Based Study of zunshou and Its English Equivalents
Ying Liu
Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation

2014

pdf bib
A Corpus-Based Quantitative Study of Nominalizations across Chinese and British Media English
Ying Liu | Alex Chengyu Fang | Naixing Wei
Proceedings of the 28th Pacific Asia Conference on Language, Information and Computing

2013

pdf bib
UMLS::Similarity: Measuring the Relatedness and Similarity of Biomedical Concepts
Bridget McInnes | Ted Pedersen | Serguei Pakhomov | Ying Liu | Genevieve Melton-Meaux
Proceedings of the 2013 NAACL HLT Demonstration Session

2011

pdf bib
Using Second-order Vectors in a Knowledge-based Method for Acronym Disambiguation
Bridget T. McInnes | Ted Pedersen | Ying Liu | Serguei V. Pakhomov | Genevieve B. Melton
Proceedings of the Fifteenth Conference on Computational Natural Language Learning

pdf bib
The Ngram Statistics Package (Text::NSP) : A Flexible Tool for Identifying Ngrams, Collocations, and Word Associations
Ted Pedersen | Satanjeev Banerjee | Bridget McInnes | Saiyam Kohli | Mahesh Joshi | Ying Liu
Proceedings of the Workshop on Multiword Expressions: from Parsing and Generation to the Real World