Ying Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ying Liu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
Haiyan Wu
Tsinghua University
2 shared publications- Chao Zhang
Department of Electronic Engineering, Tsinghua University, Beijing, China
1 shared publication - Haiyan Wu
Zhejiang University of Finance and Economics
1 shared publication - Lin Chen
Department of Chinese Language and Literature, Tsinghua University, Beijing, China, 100084
1 shared publication - Mathias Payer
EPFL, Lausanne, Switzerland
1 shared publication Panpan Liao
Department of Chinese Language and Literature, Tsinghua University, Beijing, China, 100084, 86-10-62788647
1 shared publication
Latest Publications
- Open Access
Adversarial Multi-task Learning for End-to-end Metaphor Detection
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.
Open AccessAdversarial Multi-task Learning for End-to-end Metaphor Detection
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.
- Open Access
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1901-1915
PACMem
Memory safety is a key security property that stops memory corruption vulnerabilities. Different types of memory safety enforcement solutions have been proposed and adopted by sanitizers or mitigations to catch and stop such bugs, at the development or deployment phase. However, existing solutions either provide partial memory safety or have overwhelmingly high performance overheads. In this paper, we present a novel sanitizer PACMem to efficiently catch spatial and temporal memory safety bugs. PACMem removes the majority of the overheads by sealing metadata in pointers through the COTS hardware feature -- ARM PA (Pointer Authentication) and saving the overhead of pointer metadata tracking. We have developed a prototype of PACMem and systematically evaluated its security and performance on the Magma, Juliet, Nginx, and SPEC CPU2017 test suites. In our evaluation, PACMem shows no false positives together with negligible false negatives, while introducing stronger bug detection capabilities and lower performance overheads than state-of-the-art sanitizers, including HWASan, ASan, SoftBound+CETS, Memcheck, LowFat, and PTAuth. Compared to the widely deployed ASan, PACMem has no false positives and much fewer false negatives and reduces the runtime overheads by 15.80% and the memory overheads by 71.58%.
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1901-1915
Open AccessPACMem
Memory safety is a key security property that stops memory corruption vulnerabilities. Different types of memory safety enforcement solutions have been proposed and adopted by sanitizers or mitigations to catch and stop such bugs, at the development or deployment phase. However, existing solutions either provide partial memory safety or have overwhelmingly high performance overheads. In this paper, we present a novel sanitizer PACMem to efficiently catch spatial and temporal memory safety bugs. PACMem removes the majority of the overheads by sealing metadata in pointers through the COTS hardware feature -- ARM PA (Pointer Authentication) and saving the overhead of pointer metadata tracking. We have developed a prototype of PACMem and systematically evaluated its security and performance on the Magma, Juliet, Nginx, and SPEC CPU2017 test suites. In our evaluation, PACMem shows no false positives together with negligible false negatives, while introducing stronger bug detection capabilities and lower performance overheads than state-of-the-art sanitizers, including HWASan, ASan, SoftBound+CETS, Memcheck, LowFat, and PTAuth. Compared to the widely deployed ASan, PACMem has no false positives and much fewer false negatives and reduces the runtime overheads by 15.80% and the memory overheads by 71.58%.
- Open Access
- 17 May 2021
- Published by Wiley in Journal of Applied Mathematics
- Vol. 2021, 1-16
Key n -Gram Extractions and Analyses of Different Registers Based on Attention Network
Key-gram extraction can be seen as extracting -grams which can distinguish different registers. Keyword (as , 1-gram is the keyword) extraction models are generally carried out from two aspects, the feature extraction and the model design. By summarizing the advantages and disadvantages of existing models, we propose a novel key -gram extraction model “attentive -gram network” (ANN) based on the attention mechanism and multilayer perceptron, in which the attention mechanism scores each -gram in a sentence by mining the internal semantic relationship between words, and their importance is given by the scores. Experimental results on the real corpus show that the key -gram extracted from our model can distinguish a novel, news, and text book very well; the accuracy of our model is significantly higher than the baseline model. Also, we conduct experiments on key -grams extracted from these registers, which turned out to be well clustered. Furthermore, we make some statistical analyses of the results of key -gram extraction. We find that the key -grams extracted by our model are very explanatory in linguistics.
- 17 May 2021
- Published by Wiley in Journal of Applied Mathematics
- Vol. 2021, 1-16
Open AccessKey n -Gram Extractions and Analyses of Different Registers Based on Attention Network
Key-gram extraction can be seen as extracting -grams which can distinguish different registers. Keyword (as , 1-gram is the keyword) extraction models are generally carried out from two aspects, the feature extraction and the model design. By summarizing the advantages and disadvantages of existing models, we propose a novel key -gram extraction model “attentive -gram network” (ANN) based on the attention mechanism and multilayer perceptron, in which the attention mechanism scores each -gram in a sentence by mining the internal semantic relationship between words, and their importance is given by the scores. Experimental results on the real corpus show that the key -gram extracted from our model can distinguish a novel, news, and text book very well; the accuracy of our model is significantly higher than the baseline model. Also, we conduct experiments on key -grams extracted from these registers, which turned out to be well clustered. Furthermore, we make some statistical analyses of the results of key -gram extraction. We find that the key -grams extracted by our model are very explanatory in linguistics.
- 13 October 2019
- Published by Springer Nature
- p. 40-52
Association Relationship Analyses of Stylistic Syntactic Structures
- 13 October 2019
- Published by Springer Nature
- p. 40-52
Association Relationship Analyses of Stylistic Syntactic Structures
- 7 October 2018
- Published by Springer Nature
- p. 12-23
Syntax Enhanced Research Method of Stylistic Features
- 7 October 2018
- Published by Springer Nature
- p. 12-23
Syntax Enhanced Research Method of Stylistic Features
- 1 September 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 561-566
Hybrid Chinese Text Chunking
Text chunking is an effective method to decrease the difficulty of natural language parsing. In this paper, a statistical method based on hidden Markov model (HMM) is used for Chinese text chunking. Moreover, a transformation based error-driven learning approach is adopted to improve the performance. The definition of transformation rule templates is the key problem of this machine learning approach. All the templates are learned from the corpus automatically in this paper. The precision using HMM is 88.19% and the precision is 92.67% combining HMM and transformation based error-driven learning
- 1 September 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 561-566
Hybrid Chinese Text Chunking
Text chunking is an effective method to decrease the difficulty of natural language parsing. In this paper, a statistical method based on hidden Markov model (HMM) is used for Chinese text chunking. Moreover, a transformation based error-driven learning approach is adopted to improve the performance. The definition of transformation rule templates is the key problem of this machine learning approach. All the templates are learned from the corpus automatically in this paper. The precision using HMM is 88.19% and the precision is 92.67% combining HMM and transformation based error-driven learning
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2480-2485
Improving Chinese text Chunkings precision using Transformation-based Learning
Based on text chunking using HMM, transformation-based learning is made use of to improve the precision of chunk tags further. The training data and the test data are from Penn treebank 4.0, and 13 text chunks are used. Rules are learned automatically according to the rule templates. The precision is improved 4.48%. The detailed analysis that affects the text chunking is given. Different threshold, different scale of training data, different learning equation and different rule templates can affect the precision of the text chunking.
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2480-2485
Improving Chinese text Chunkings precision using Transformation-based Learning
Based on text chunking using HMM, transformation-based learning is made use of to improve the precision of chunk tags further. The training data and the test data are from Penn treebank 4.0, and 13 text chunks are used. Rules are learned automatically according to the rule templates. The precision is improved 4.48%. The detailed analysis that affects the text chunking is given. Different threshold, different scale of training data, different learning equation and different rule templates can affect the precision of the text chunking.