scholarly journals Textual Backdoor Defense via Poisoned Sample Recognition

2021 ◽  
Vol 11 (21) ◽  
pp. 9938
Author(s):  
Kun Shao ◽  
Yu Zhang ◽  
Junan Yang ◽  
Hui Liu
Keyword(s):  
Success Rate ◽  
Language Processing ◽  
Training Data ◽  
Infection Model ◽  
Search Range ◽  
Word Level ◽  
Sentence Level ◽  
Preliminary Model ◽  
Sample Recognition ◽  
Better Than

Deep learning models are vulnerable to backdoor attacks. The success rate of textual backdoor attacks based on data poisoning in existing research is as high as 100%. In order to enhance the natural language processing model’s defense against backdoor attacks, we propose a textual backdoor defense method via poisoned sample recognition. Our method consists of two parts: the first step is to add a controlled noise layer after the model embedding layer, and to train a preliminary model with incomplete or no backdoor embedding, which reduces the effectiveness of poisoned samples. Then, we use the model to initially identify the poisoned samples in the training set so as to narrow the search range of the poisoned samples. The second step uses all the training data to train an infection model embedded in the backdoor, which is used to reclassify the samples selected in the first step, and finally identify the poisoned samples. Through detailed experiments, we have proved that our defense method can effectively defend against a variety of backdoor attacks (character-level, word-level and sentence-level backdoor attacks), and the experimental effect is better than the baseline method. For the BERT model trained by the IMDB dataset, this method can even reduce the success rate of word-level backdoor attacks to 0%.

scholarly journals Pseudotext Injection and Advance Filtering of Low-Resource Corpus for Neural Machine Translation

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Michael Adjeisah ◽  
Guohua Liu ◽  
Douglas Omwenga Nyabuga ◽  
Richard Nuetey Nortey ◽  
Jinling Song
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Training Data ◽  
Target Language ◽  
Similarity Metrics ◽  
Mahalanobis Distances ◽  
Parallel Corpora ◽  
Parallel Corpus ◽  
Low Resource ◽  
Sentence Level

Scaling natural language processing (NLP) to low-resourced languages to improve machine translation (MT) performance remains enigmatic. This research contributes to the domain on a low-resource English-Twi translation based on filtered synthetic-parallel corpora. It is often perplexing to learn and understand what a good-quality corpus looks like in low-resource conditions, mainly where the target corpus is the only sample text of the parallel language. To improve the MT performance in such low-resource language pairs, we propose to expand the training data by injecting synthetic-parallel corpus obtained by translating a monolingual corpus from the target language based on bootstrapping with different parameter settings. Furthermore, we performed unsupervised measurements on each sentence pair engaging squared Mahalanobis distances, a filtering technique that predicts sentence parallelism. Additionally, we extensively use three different sentence-level similarity metrics after round-trip translation. Experimental results on a diverse amount of available parallel corpus demonstrate that injecting pseudoparallel corpus and extensive filtering with sentence-level similarity metrics significantly improves the original out-of-the-box MT systems for low-resource language pairs. Compared with existing improvements on the same original framework under the same structure, our approach exhibits tremendous developments in BLEU and TER scores.

scholarly journals Textual Adversarial Attacking with Limited Queries

Electronics ◽  
2021 ◽  
Vol 10 (21) ◽  
pp. 2671
Author(s):  
Yu Zhang ◽  
Junan Yang ◽  
Xiaoshuai Li ◽  
Hui Liu ◽  
Kun Shao
Keyword(s):  
Language Processing ◽  
Main Idea ◽  
Local Model ◽  
Small Perturbations ◽  
Target Model ◽  
Word Level ◽  
Sentence Level ◽  
Adversarial Examples ◽  
Reducing Costs ◽  
The Cost

Recent studies have shown that natural language processing (NLP) models are vulnerable to adversarial examples, which are maliciously designed by adding small perturbations to benign inputs that are imperceptible to the human eye, leading to false predictions by the target model. Compared to character- and sentence-level textual adversarial attacks, word-level attack can generate higher-quality adversarial examples, especially in a black-box setting. However, existing attack methods usually require a huge number of queries to successfully deceive the target model, which is costly in a real adversarial scenario. Hence, finding appropriate models is difficult. Therefore, we propose a novel attack method, the main idea of which is to fully utilize the adversarial examples generated by the local model and transfer part of the attack to the local model to complete ahead of time, thereby reducing costs related to attacking the target model. Extensive experiments conducted on three public benchmarks show that our attack method can not only improve the success rate but also reduce the cost, while outperforming the baselines by a significant margin.

Chronological Ordering Based on Context Overlap Detection

2012 ◽  
Vol 2 (4) ◽  
pp. 31-44
Author(s):  
Mohamed H. Haggag ◽  
Bassma M. Othman
Keyword(s):  
Language Processing ◽  
Linguistic Knowledge ◽  
Syntactic Analysis ◽  
Text Generation ◽  
Context Processing ◽  
Domain Specific ◽  
Word Level ◽  
Sentence Level ◽  
Proposed Model ◽  
Chronological Sequence

Context processing plays an important role in different Natural Language Processing applications. Sentence ordering is one of critical tasks in text generation. Following the same order of sentences in the row sources of text is not necessarily to be applied for the resulted text. Accordingly, a need for chronological sentence ordering is of high importance in this regard. Some researches followed linguistic syntactic analysis and others used statistical approaches. This paper proposes a new model for sentence ordering based on sematic analysis. Word level semantics forms a seed to sentence level sematic relations. The model introduces a clustering technique based on sentences senses relatedness. Following to this, sentences are chronologically ordered through two main steps; overlap detection and chronological cause-effect rules. Overlap detection drills down into each cluster to step through its sentences in chronological sequence. Cause-effect rules forms the linguistic knowledge controlling sentences relations. Evaluation of the proposed algorithm showed the capability of the proposed model to process size free texts, non-domain specific and open to extend the cause-effect rules for specific ordering needs.

A longitudinal neuroimaging dataset on language processing in children ages 5, 7, and 9 years old.

2021 ◽  
Author(s):  
Jin Wang ◽  
Marisa N. Lytle ◽  
Yael Weiss ◽  
Brianna L. Yamasaki ◽  
James R. Booth
Keyword(s):  
Language Processing ◽  
Semantic Processing ◽  
Longitudinal Design ◽  
Word Level ◽  
Sentence Level ◽  
Multiple Imaging ◽  
Educational Assessments ◽  
Magnetic Resonance Imaging Mri ◽  
Changes Over Time ◽  
Brain Behavior

This dataset examines language development with a longitudinal design and includes diffusion- and T1-weighted structural magnetic resonance imaging (MRI), task-based functional MRI (fMRI), and a battery of psycho-educational assessments and parental questionnaires. We collected data from 5.5-6.5-year-old children (ses-5) and followed them up when they were 7-8 years old (ses-7) and then again at 8.5-10 years old (ses-9). To increase the sample size at the older time points, another cohort of 7-8-year-old children (ses-7) were recruited and followed up when they were 8.5-10 years old (ses-9). In total, 322 children who completed at least one structural and functional scan were included. Children performed four fMRI tasks consisting of two word-level tasks examining phonological and semantic processing and two sentence-level tasks investigating semantic and syntactic processing. The MRI data is valuable for examining changes over time in interactive specialization due to the use of multiple imaging modalities and tasks in this longitudinal design. In addition, the extensive psycho-educational assessments and questionnaires provide opportunities to explore brain-behavior and brain-environment associations.

A Fast Histogram-Based Postprocessor That Improves Posterior Probability Estimates

1999 ◽  
Vol 11 (5) ◽  
pp. 1235-1248 ◽  
Author(s):  
Wei Wei ◽  
Todd K. Leen ◽  
Etienne Barnard
Keyword(s):  
Recognition System ◽  
Error Rates ◽  
Training Data ◽  
Word Level ◽  
Probability Estimates ◽  
Sentence Level ◽  
Optimization Routine ◽  
Calibration Accuracy ◽  
Neural Network Classifiers ◽  
The Cost

Although the outputs of neural network classifiers are often considered to be estimates of posterior class probabilities, the literature that assesses the calibration accuracy of these estimates illustrates that practical networks often fall far short of being ideal estimators. The theorems used to justify treating network outputs as good posterior estimates are based on several assumptions: that the network is sufficiently complex to model the posterior distribution accurately, that there are sufficient training data to specify the network, and that the optimization routine is capable of finding the global minimum of the cost function. Any or all of these assumptions may be violated in practice. This article does three things. First, we apply a simple, previously used histogram technique to assess graphically the accuracy of posterior estimates with respect to individual classes. Second, we introduce a simple and fast remapping procedure that transforms network outputs to provide better estimates of posteriors. Third, we use the remapping in a real-world telephone speech recognition system. The remapping results in a 10% reduction of both word-level error rates (from 4.53% to 4.06%) and sentence-level error rates (from 16.38% to 14.69%) on one corpus, and a 29% reduction at sentence-level error (from 6.3% to 4.5%) on another. The remapping required negligible additional overhead (in terms of both parameters and calculations). McNemar's test shows that these levels of improvement are statistically significant.

scholarly journals Enhancing the Performance of Telugu Named Entity Recognition Using Gazetteer Features

Information ◽  
2020 ◽  
Vol 11 (2) ◽  
pp. 82
Author(s):  
SaiKiranmai Gorla ◽  
Lalita Bhanu Murthy Neti ◽  
Aruna Malapati
Keyword(s):  
Language Processing ◽  
Conditional Random Field ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Limited Resources ◽  
Support Vector ◽  
Named Entity ◽  
Word Level ◽  
Asian Languages ◽  
Better Than

Named entity recognition (NER) is a fundamental step for many natural language processing tasks and hence enhancing the performance of NER models is always appreciated. With limited resources being available, NER for South-East Asian languages like Telugu is quite a challenging problem. This paper attempts to improve the NER performance for Telugu using gazetteer-related features, which are automatically generated using Wikipedia pages. We make use of these gazetteer features along with other well-known features like contextual, word-level, and corpus features to build NER models. NER models are developed using three well-known classifiers—conditional random field (CRF), support vector machine (SVM), and margin infused relaxed algorithms (MIRA). The gazetteer features are shown to improve the performance, and theMIRA-based NER model fared better than its counterparts SVM and CRF.

scholarly journals Similarity-Driven Semantic Role Induction via Graph Partitioning

2014 ◽  
Vol 40 (3) ◽  
pp. 633-669 ◽  
Author(s):  
Joel Lang ◽  
Mirella Lapata
Keyword(s):  
Language Processing ◽  
Graph Partitioning ◽  
Clustering Algorithms ◽  
Training Data ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Unique Role ◽  
Role Induction ◽  
Partitioning Problem ◽  
Better Than

As in many natural language processing tasks, data-driven models based on supervised learning have become the method of choice for semantic role labeling. These models are guaranteed to perform well when given sufficient amount of labeled training data. Producing this data is costly and time-consuming, however, thus raising the question of whether unsupervised methods offer a viable alternative. The working hypothesis of this article is that semantic roles can be induced without human supervision from a corpus of syntactically parsed sentences based on three linguistic principles: (1) arguments in the same syntactic position (within a specific linking) bear the same semantic role, (2) arguments within a clause bear a unique role, and (3) clusters representing the same semantic role should be more or less lexically and distributionally equivalent. We present a method that implements these principles and formalizes the task as a graph partitioning problem, whereby argument instances of a verb are represented as vertices in a graph whose edges express similarities between these instances. The graph consists of multiple edge layers, each one capturing a different aspect of argument-instance similarity, and we develop extensions of standard clustering algorithms for partitioning such multi-layer graphs. Experiments for English and German demonstrate that our approach is able to induce semantic role clusters that are consistently better than a strong baseline and are competitive with the state of the art.

Preserve Integrity in Realtime Event Summarization

2021 ◽  
Vol 15 (3) ◽  
pp. 1-29
Author(s):  
Chen Lin ◽  
Zhichao Ouyang ◽  
Xiaoli Wang ◽  
Hui Li ◽  
Zhenhua Huang
Keyword(s):  
Information Acquisition ◽  
Information Source ◽  
Training Data ◽  
Conflicting Information ◽  
Word Level ◽  
Text Streams ◽  
Sentence Level ◽  
Real World Datasets ◽  
Event Summarization ◽  
Consistent Information

Online text streams such as Twitter are the major information source for users when they are looking for ongoing events. Realtime event summarization aims to generate and update coherent and concise summaries to describe the state of a given event. Due to the enormous volume of continuously coming texts, realtime event summarization has become the de facto tool to facilitate information acquisition. However, there exists a challenging yet unexplored issue in current text summarization techniques: how to preserve the integrity, i.e., the accuracy and consistency of summaries during the update process. The issue is critical since online text stream is dynamic and conflicting information could spread during the event period. For example, conflicting numbers of death and injuries might be reported after an earthquake. Such misleading information should not appear in the earthquake summary at any timestamp. In this article, we present a novel realtime event summarization framework called IAEA (i.e., Integrity-Aware Extractive-Abstractive realtime event summarization). Our key idea is to integrate an inconsistency detection module into a unified extractive–abstractive framework. In each update, important new tweets are first extracted in an extractive module, and the extraction is refined by explicitly detecting inconsistency between new tweets and previous summaries. The extractive module is able to capture the sentence-level attention which is later used by an abstractive module to obtain the word-level attention. Finally, the word-level attention is leveraged to rephrase words. We conduct comprehensive experiments on real-world datasets. To reduce efforts required for building sufficient training data, we also provide automatic labeling steps of which the effectiveness has been empirically verified. Through experiments, we demonstrate that IAEA can generate better summaries with consistent information than state-of-the-art approaches.

scholarly journals CAWA: An Attention-Network for Credit Attribution

2020 ◽  
Vol 34 (05) ◽  
pp. 8472-8479
Author(s):  
Saurav Manchanda ◽  
George Karypis
Keyword(s):  
State Of The Art ◽  
Text Summarization ◽  
Training Data ◽  
Learning Framework ◽  
Distant Supervision ◽  
Sentence Level ◽  
Class Labels ◽  
The Individual ◽  
Traditional Approaches ◽  
Better Than

Credit attribution is the task of associating individual parts in a document with their most appropriate class labels. It is an important task with applications to information retrieval and text summarization. When labeled training data is available, traditional approaches for sequence tagging can be used for credit attribution. However, generating such labeled datasets is expensive and time-consuming. In this paper, we present Credit Attribution With Attention (CAWA), a neural-network-based approach, that instead of using sentence-level labeled data, uses the set of class labels that are associated with an entire document as a source of distant-supervision. CAWA combines an attention mechanism with a multilabel classifier into an end-to-end learning framework to perform credit attribution. CAWA labels the individual sentences from the input document using the resultant attention-weights. CAWA improves upon the state-of-the-art credit attribution approach by not constraining a sentence to belong to just one class, but modeling each sentence as a distribution over all classes, leading to better modeling of semantically-similar classes. Experiments on the credit attribution task on a variety of datasets show that the sentence class labels generated by CAWA outperform the competing approaches. Additionally, on the multilabel text classification task, CAWA performs better than the competing credit attribution approaches1.

scholarly journals A Variational Autoencoding Approach for Inducing Cross-lingual Word Embeddings

2017 ◽  
Author(s):  
Liangchen Wei ◽  
Zhi-Hong Deng
Keyword(s):  
Language Learning ◽  
Latent Variable ◽  
Training Data ◽  
Variational Model ◽  
Word Embeddings ◽  
Parallel Corpora ◽  
Word Level ◽  
Sentence Level ◽  
Cross Lingual ◽  
Traditional Approaches

Cross-language learning allows one to use training data from one language to build models for another language. Many traditional approaches require word-level alignment sentences from parallel corpora, in this paper we define a general bilingual training objective function requiring sentence level parallel corpus only. We propose a variational autoencoding approach for training bilingual word embeddings. The variational model introduces a continuous latent variable to explicitly model the underlying semantics of the parallel sentence pairs and to guide the generation of the sentence pairs. Our model restricts the bilingual word embeddings to represent words in exactly the same continuous vector space. Empirical results on the task of cross lingual document classification has shown that our method is effective.

Sign in / Sign up

Export Citation Format

Share Document