scholarly journals DPAEG: A Dependency Parse-Based Adversarial Examples Generation Method for Intelligent Q&A Robots

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Mingfu Xue ◽  
Chengxiang Yuan ◽  
Jian Wang ◽  
Weiqiang Liu
Keyword(s):  
Natural Language Processing ◽  
Language Processing ◽  
Correct Answer ◽  
State Of The Art ◽  
Black Box ◽  
Security Evaluation ◽  
Test Dataset ◽  
Human Evaluation ◽  
Extraction Algorithm ◽  
Adversarial Examples

Recently, the natural language processing- (NLP-) based intelligent question and answer (Q&A) robots have been used ubiquitously. However, the robustness and security of current Q&A robots are still unsatisfactory, e.g., a slight typo in the user’s question may cause the Q&A robot unable to return the correct answer. In this paper, we propose a fast and automatic test dataset generation method for the robustness and security evaluation of current Q&A robots, which can work in black-box scenarios and thus can be applied to a variety of different Q&A robots. Specifically, we propose a dependency parse-based adversarial examples generation (DPAEG) method for Q&A robots. DPAEG first uses the proposed dependency parse-based keywords extraction algorithm to extract keywords from a question. Then, the proposed algorithm generates adversarial words according to the extracted keywords, which include typos and words that are spelled similarly to the keywords. Finally, these adversarial words are used to generate a large number of adversarial questions. The generated adversarial questions which are similar to the original questions do not affect human’s understanding, but the Q&A robots cannot answer these adversarial questions correctly. Moreover, the proposed method works in a black-box scenario, which means it does not need the knowledge of the target Q&A robots. Experiment results show that the generated adversarial examples have a high success rate on two state-of-the-art Q&A robots, DrQA and Google Assistant. In addition, the generated adversarial examples not only affect the correct answer (top-1) returned by DrQA but also affect the top-k candidate answers returned by DrQA. The adversarial examples make the top-k candidate answers contain fewer correct answers and make the correct answers rank lower in the top-k candidate answers. The human evaluation results show that participants with different genders, ages, and mother tongues can understand the meaning of most of the generated adversarial examples, which means that the generated adversarial examples do not affect human’s understanding.

scholarly journals Local Post-hoc Explainable Methods for Adversarial Text Attacks

2021 ◽  
Author(s):  
Yidong Chai ◽  
Ruicheng Liang ◽  
Hongyi Zhu ◽  
Sagar Samtani ◽  
Meng Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Language Processing ◽  
Black Box ◽  
Learning Models ◽  
Two Phase ◽  
Sensitivity Estimation ◽  
Execution Phase ◽  
Adversarial Examples ◽  
Post Hoc

Deep learning models have significantly advanced various natural language processing tasks. However, they are strikingly vulnerable to adversarial text attacks, even in the black-box setting where no model knowledge is accessible to hackers. Such attacks are conducted with a two-phase framework: 1) a sensitivity estimation phase to evaluate each element’s sensitivity to the target model’s prediction, and 2) a perturbation execution phase to craft the adversarial examples based on estimated element sensitivity. This study explored the connections between the local post-hoc explainable methods for deep learning and black-box adversarial text attacks and proposed a novel eXplanation-based method for crafting Adversarial Text Attacks (XATA). XATA leverages local post-hoc explainable methods (e.g., LIME or SHAP) to measure input elements’ sensitivity and adopts the word replacement perturbation strategy to craft adversarial examples. We evaluated the attack performance of the proposed XATA on three commonly used text-based datasets: IMDB Movie Review, Yelp Reviews-Polarity, and Amazon Reviews-Polarity. The proposed XATA outperformed existing baselines in various target models, including LSTM, GRU, CNN, and BERT. Moreover, we found that improved local post-hoc explainable methods (e.g., SHAP) lead to more effective adversarial attacks. These findings showed that when researchers constantly advance the explainability of deep learning models with local post-hoc methods, they also provide hackers with weapons to craft more targeted and dangerous adversarial attacks.

scholarly journals Argot: Generating Adversarial Readable Chinese Texts

2020 ◽  
Author(s):  
Zihan Zhang ◽  
Mingxuan Liu ◽  
Chao Zhang ◽  
Yiming Zhang ◽  
Zhou Li ◽  
...  
Keyword(s):  
Image Processing ◽  
Natural Language Processing ◽  
Success Rate ◽  
Language Processing ◽  
Black Box ◽  
Essential Step ◽  
Chinese Characteristics ◽  
Adversarial Examples ◽  
Chinese Texts ◽  
Chinese And English

Natural language processing (NLP) models are known vulnerable to adversarial examples, similar to image processing models. Studying adversarial texts is an essential step to improve the robustness of NLP models. However, existing studies mainly focus on analyzing English texts and generating adversarial examples for English texts. There is no work studying the possibility and effect of the transformation to another language, e.g, Chinese. In this paper, we analyze the differences between Chinese and English, and explore the methodology to transform the existing English adversarial generation method to Chinese. We propose a novel black-box adversarial Chinese texts generation solution Argot, by utilizing the method for adversarial English samples and several novel methods developed on Chinese characteristics. Argot could effectively and efficiently generate adversarial Chinese texts with good readability. Furthermore, Argot could also automatically generate targeted Chinese adversarial text, achieving a high success rate and ensuring readability of the Chinese.

scholarly journals Local Post-hoc Explainable Methods for Adversarial Text Attacks

2021 ◽  
Author(s):  
Yidong Chai ◽  
Ruicheng Liang ◽  
Hongyi Zhu ◽  
Sagar Samtani ◽  
Meng Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Language Processing ◽  
Black Box ◽  
Learning Models ◽  
Two Phase ◽  
Sensitivity Estimation ◽  
Execution Phase ◽  
Adversarial Examples ◽  
Post Hoc

Deep learning models have significantly advanced various natural language processing tasks. However, they are strikingly vulnerable to adversarial text attacks, even in the black-box setting where no model knowledge is accessible to hackers. Such attacks are conducted with a two-phase framework: 1) a sensitivity estimation phase to evaluate each element’s sensitivity to the target model’s prediction, and 2) a perturbation execution phase to craft the adversarial examples based on estimated element sensitivity. This study explored the connections between the local post-hoc explainable methods for deep learning and black-box adversarial text attacks and proposed a novel eXplanation-based method for crafting Adversarial Text Attacks (XATA). XATA leverages local post-hoc explainable methods (e.g., LIME or SHAP) to measure input elements’ sensitivity and adopts the word replacement perturbation strategy to craft adversarial examples. We evaluated the attack performance of the proposed XATA on three commonly used text-based datasets: IMDB Movie Review, Yelp Reviews-Polarity, and Amazon Reviews-Polarity. The proposed XATA outperformed existing baselines in various target models, including LSTM, GRU, CNN, and BERT. Moreover, we found that improved local post-hoc explainable methods (e.g., SHAP) lead to more effective adversarial attacks. These findings showed that when researchers constantly advance the explainability of deep learning models with local post-hoc methods, they also provide hackers with weapons to craft more targeted and dangerous adversarial attacks.

Report on the 4th Joint Workshop on Bibliometric-Enhanced Information Retrieval and Natural Language Processing for Digital Libraries at SIGIR 2019

2019 ◽  
Vol 53 (2) ◽  
pp. 3-10
Author(s):  
Muthu Kumar Chandrasekaran ◽  
Philipp Mayr
Keyword(s):  
Information Retrieval ◽  
Natural Language Processing ◽  
Natural Language ◽  
Research And Development ◽  
Language Processing ◽  
Digital Libraries ◽  
State Of The Art ◽  
Shared Task ◽  
Processing Information ◽  
Joint Workshop

The 4 th joint BIRNDL workshop was held at the 42nd ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019) in Paris, France. BIRNDL 2019 intended to stimulate IR researchers and digital library professionals to elaborate on new approaches in natural language processing, information retrieval, scientometrics, and recommendation techniques that can advance the state-of-the-art in scholarly document understanding, analysis, and retrieval at scale. The workshop incorporated different paper sessions and the 5 th edition of the CL-SciSumm Shared Task.

News Headline Building using Hybrid Headline Generation Technique for Quick Gist

2017 ◽  
Vol 6 (1) ◽  
pp. 36-52
Author(s):  
Urmila Shrawankar ◽  
Kranti Wankhede
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Reading Time ◽  
News Article ◽  
Keyword Extraction ◽  
Keyphrase Extraction ◽  
Generation Technique ◽  
Extraction Algorithm ◽  
Key Terms

A considerable amount of time is required to interpret whole news article to get the gist of it. Therefore, in order to reduce the reading and interpretation time, headlines are necessary. The available techniques for news headline construction mainly includes extractive and abstractive headline generation techniques. In this paper, context based news headline is formed from long news article by using techniques of core Natural Language Processing (NLP) and key terms of news article. Key terms are retrieved from lengthy news article by using various approaches of keyword extraction. The keyphrases are picked out using Keyphrase Extraction Algorithm (KEA) which helps to construct headline syntax along with NLP's parsing technique. Sentence compression algorithm helps to generate compressed sentences from generated parse tree of leading sentences. Headline helps user for reducing cognitive burden of reader by reflecting important contents of news. The objective is to frame headline using key terms for reducing reading time and efforts of reader.

Textual entailment graphs

2015 ◽  
Vol 21 (5) ◽  
pp. 699-724 ◽  
Author(s):  
LILI KOTLERMAN ◽  
IDO DAGAN ◽  
BERNARDO MAGNINI ◽  
LUISA BENTIVOGLI
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Gold Standard ◽  
State Of The Art ◽  
Text Analytics ◽  
Joint Work ◽  
Gold Standard Dataset ◽  
Textual Entailment ◽  
Interesting Task

AbstractIn this work, we present a novel type of graphs for natural language processing (NLP), namely textual entailment graphs (TEGs). We describe the complete methodology we developed for the construction of such graphs and provide some baselines for this task by evaluating relevant state-of-the-art technology. We situate our research in the context of text exploration, since it was motivated by joint work with industrial partners in the text analytics area. Accordingly, we present our motivating scenario and the first gold-standard dataset of TEGs. However, while our own motivation and the dataset focus on the text exploration setting, we suggest that TEGs can have different usages and suggest that automatic creation of such graphs is an interesting task for the community.

scholarly journals Improving Semantic Similarity with Cross-Lingual Resources: A Study in Bangla—A Low Resourced Language

Informatics ◽  
2019 ◽  
Vol 6 (2) ◽  
pp. 19 ◽  
Author(s):  
Rajat Pandit ◽  
Saptarshi Sengupta ◽  
Sudip Kumar Naskar ◽  
Niladri Sekhar Dash ◽  
Mohini Mohan Sardar
Keyword(s):  
Semantic Similarity ◽  
Language Processing ◽  
State Of The Art ◽  
Human Beings ◽  
Human Evaluation ◽  
Evaluation Scores ◽  
Similarity Calculation ◽  
Marked Enhancement ◽  
Cross Lingual ◽  
Standing Problem

Semantic similarity is a long-standing problem in natural language processing (NLP). It is a topic of great interest as its understanding can provide a look into how human beings comprehend meaning and make associations between words. However, when this problem is looked at from the viewpoint of machine understanding, particularly for under resourced languages, it poses a different problem altogether. In this paper, semantic similarity is explored in Bangla, a less resourced language. For ameliorating the situation in such languages, the most rudimentary method (path-based) and the latest state-of-the-art method (Word2Vec) for semantic similarity calculation were augmented using cross-lingual resources in English and the results obtained are truly astonishing. In the presented paper, two semantic similarity approaches have been explored in Bangla, namely the path-based and distributional model and their cross-lingual counterparts were synthesized in light of the English WordNet and Corpora. The proposed methods were evaluated on a dataset comprising of 162 Bangla word pairs, which were annotated by five expert raters. The correlation scores obtained between the four metrics and human evaluation scores demonstrate a marked enhancement that the cross-lingual approach brings into the process of semantic similarity calculation for Bangla.

scholarly journals Using Natural Language Processing and Artificial Intelligence to Explore the Nutrition and Sustainability of Recipes and Food

2021 ◽  
Vol 3 ◽  
Author(s):  
Marieke van Erp ◽  
Christian Reynolds ◽  
Diana Maynard ◽  
Alain Starke ◽  
Rebeca Ibáñez Martín ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Domain Knowledge ◽  
State Of The Art ◽  
Interdisciplinary Approach ◽  
Comprehensive Analysis ◽  
The State ◽  
Use Cases

In this paper, we discuss the use of natural language processing and artificial intelligence to analyze nutritional and sustainability aspects of recipes and food. We present the state-of-the-art and some use cases, followed by a discussion of challenges. Our perspective on addressing these is that while they typically have a technical nature, they nevertheless require an interdisciplinary approach combining natural language processing and artificial intelligence with expert domain knowledge to create practical tools and comprehensive analysis for the food domain.

scholarly journals Biomedical Concept Recognition Using Deep Neural Sequence Models

2019 ◽  
Author(s):  
Negacy D. Hailu ◽  
Michael Bada ◽  
Asmelash Teka Hadgu ◽  
Lawrence E. Hunter
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
State Of The Art ◽  
Conditional Random Field ◽  
Concept Recognition ◽  
Performance Improvements ◽  
Art Performance

AbstractBackgroundthe automated identification of mentions of ontological concepts in natural language texts is a central task in biomedical information extraction. Despite more than a decade of effort, performance in this task remains below the level necessary for many applications.Resultsrecently, applications of deep learning in natural language processing have demonstrated striking improvements over previously state-of-the-art performance in many related natural language processing tasks. Here we demonstrate similarly striking performance improvements in recognizing biomedical ontology concepts in full text journal articles using deep learning techniques originally developed for machine translation. For example, our best performing system improves the performance of the previous state-of-the-art in recognizing terms in the Gene Ontology Biological Process hierarchy, from a previous best F1 score of 0.40 to an F1 of 0.70, nearly halving the error rate. Nearly all other ontologies show similar performance improvements.ConclusionsA two-stage concept recognition system, which is a conditional random field model for span detection followed by a deep neural sequence model for normalization, improves the state-of-the-art performance for biomedical concept recognition. Treating the biomedical concept normalization task as a sequence-to-sequence mapping task similar to neural machine translation improves performance.

Sign in / Sign up

Export Citation Format

Share Document