Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples

Apr 13, 2020
Maximilian Mozes, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin

While recent efforts have shown that neural text processing models are vulnerable to adversarial examples, comparatively little attention has been paid to explicitly characterize their effectiveness. To overcome this, we present analytical insights into the word frequency characteristics of word-level adversarial examples for neural text classification models. We show that adversarial attacks against CNN-, LSTM- and Transformer-based classification models perform token substitutions that are identifiable through word frequency differences between replaced words and their substitutions. Based on these findings, we propose frequency-guided word substitutions (FGWS) as a simple algorithm for the automatic detection of adversarially perturbed textual sequences. FGWS exploits the word frequency properties of adversarial word substitutions, and we assess its suitability for the automatic detection of adversarial examples generated from the SST-2 and IMDb sentiment datasets. Our method provides promising results by accurately detecting adversarial examples, with $F_1$ detection scores of up to 93.7% on adversarial examples against BERT-based classification models. We compare our approach against baseline detection approaches as well as a recently proposed perturbation discrimination framework, and show that we outperform existing approaches by up to 15.1% $F_1$ in our experiments.

* pre-print 

  Access Paper or Ask Questions

Annotation of Emotion Carriers in Personal Narratives

Feb 28, 2020
Aniruddha Tammewar, Alessandra Cervone, Eva-Maria Messner, Giuseppe Riccardi

We are interested in the problem of understanding personal narratives (PN) - spoken or written - recollections of facts, events, and thoughts. In PN, emotion carriers are the speech or text segments that best explain the emotional state of the user. Such segments may include entities, verb or noun phrases. Advanced automatic understanding of PNs requires not only the prediction of the user emotional state but also to identify which events (e.g. "the loss of relative" or "the visit of grandpa") or people ( e.g. "the old group of high school mates") carry the emotion manifested during the personal recollection. This work proposes and evaluates an annotation model for identifying emotion carriers in spoken personal narratives. Compared to other text genres such as news and microblogs, spoken PNs are particularly challenging because a narrative is usually unstructured, involving multiple sub-events and characters as well as thoughts and associated emotions perceived by the narrator. In this work, we experiment with annotating emotion carriers from speech transcriptions in the Ulm State-of-Mind in Speech (USoMS) corpus, a dataset of German PNs. We believe this resource could be used for experiments in the automatic extraction of emotion carriers from PN, a task that could provide further advancements in narrative understanding.

* To be published in LREC 2020 

  Access Paper or Ask Questions

Assessment of Amazon Comprehend Medical: Medication Information Extraction

Feb 02, 2020
Benedict Guzman, MS, Isabel Metzger, MS, Yindalon Aphinyanaphongs, M. D., Ph. D., Himanshu Grover, Ph. D

In November 27, 2018, Amazon Web Services (AWS) released Amazon Comprehend Medical (ACM), a deep learning based system that automatically extracts clinical concepts (which include anatomy, medical conditions, protected health information (PH)I, test names, treatment names, and medical procedures, and medications) from clinical text notes. Uptake and trust in any new data product relies on independent validation across benchmark datasets and tools to establish and confirm expected quality of results. This work focuses on the medication extraction task, and particularly, ACM was evaluated using the official test sets from the 2009 i2b2 Medication Extraction Challenge and 2018 n2c2 Track 2: Adverse Drug Events and Medication Extraction in EHRs. Overall, ACM achieved F-scores of 0.768 and 0.828. These scores ranked the lowest when compared to the three best systems in the respective challenges. To further establish the generalizability of its medication extraction performance, a set of random internal clinical text notes from NYU Langone Medical Center were also included in this work. And in this corpus, ACM garnered an F-score of 0.753.

  Access Paper or Ask Questions

Learning document embeddings along with their uncertainties

Aug 29, 2019
Santosh Kesiraju, Oldřich Plchot, Lukáš Burget, Suryakanth V Gangashetty

Majority of the text modelling techniques yield only point estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We present Bayesian subspace multinomial model (Bayesian SMM), a generative log-linear model that learns to represent documents in the form of Gaussian distributions, thereby encoding the uncertainty in its covariance. Additionally, in the proposed Bayesian SMM, we address a commonly encountered problem of intractability that appears during variational inference in mixed-logit models. We also present a generative Gaussian linear classifier for topic identification that exploits the uncertainty in document embeddings. Our intrinsic evaluation using perplexity measure shows that the proposed Bayesian SMM fits the data better as compared to variational auto-encoder based document model. Our topic identification experiments on speech (Fisher) and text (20Newsgroups) corpora show that the proposed Bayesian SMM is robust to over-fitting on unseen test data. The topic ID results show that the proposed model is significantly better than variational auto-encoder based methods and achieve similar results when compared to fully supervised discriminative models.

  Access Paper or Ask Questions

EAT2seq: A generic framework for controlled sentence transformation without task-specific training

Apr 08, 2019
Tommi Gröndahl, N. Asokan

We present EAT2seq: a novel method to architect automatic linguistic transformations for a number of tasks, including controlled grammatical or lexical changes, style transfer, text generation, and machine translation. Our approach consists in creating an abstract representation of a sentence's meaning and grammar, which we use as input to an encoder-decoder network trained to reproduce the original sentence. Manipulating the abstract representation allows the transformation of sentences according to user-provided parameters, both grammatically and lexically, in any combination. The same architecture can further be used for controlled text generation, and has additional promise for machine translation. This strategy holds the promise of enabling many tasks that were hitherto outside the scope of NLP techniques for want of sufficient training data. We provide empirical evidence for the effectiveness of our approach by reproducing and transforming English sentences, and evaluating the results both manually and automatically. A single model trained on monolingual data is used for all tasks without any task-specific training. For a model trained on 8.5 million sentences, we report a BLEU score of 74.45 for reproduction, and scores between 55.29 and 81.82 for back-and-forth grammatical transformations across 14 category pairs.

* 32 pages 

  Access Paper or Ask Questions

Visual Question Answering as Reading Comprehension

Nov 29, 2018
Hui Li, Peng Wang, Chunhua Shen, Anton van den Hengel

Visual question answering (VQA) demands simultaneous comprehension of both the image visual content and natural language questions. In some cases, the reasoning needs the help of common sense or general knowledge which usually appear in the form of text. Current methods jointly embed both the visual information and the textual feature into the same space. However, how to model the complex interactions between the two different modalities is not an easy task. In contrast to struggling on multimodal feature fusion, in this paper, we propose to unify all the input information by natural language so as to convert VQA into a machine reading comprehension problem. With this transformation, our method not only can tackle VQA datasets that focus on observation based questions, but can also be naturally extended to handle knowledge-based VQA which requires to explore large-scale external knowledge base. It is a step towards being able to exploit large volumes of text and natural language processing techniques to address VQA problem. Two types of models are proposed to deal with open-ended VQA and multiple-choice VQA respectively. We evaluate our models on three VQA benchmarks. The comparable performance with the state-of-the-art demonstrates the effectiveness of the proposed method.

  Access Paper or Ask Questions

Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and L2-L1 Parallel Data

Aug 29, 2018
Zi Lin, Yuguang Duan, Yuanyuan Zhao, Weiwei Sun, Xiaojun Wan

This paper studies semantic parsing for interlanguage (L2), taking semantic role labeling (SRL) as a case task and learner Chinese as a case language. We first manually annotate the semantic roles for a set of learner texts to derive a gold standard for automatic SRL. Based on the new data, we then evaluate three off-the-shelf SRL systems, i.e., the PCFGLA-parser-based, neural-parser-based and neural-syntax-agnostic systems, to gauge how successful SRL for learner Chinese can be. We find two non-obvious facts: 1) the L1-sentence-trained systems performs rather badly on the L2 data; 2) the performance drop from the L1 data to the L2 data of the two parser-based systems is much smaller, indicating the importance of syntactic parsing in SRL for interlanguages. Finally, the paper introduces a new agreement-based model to explore the semantic coherency information in the large-scale L2-L1 parallel data. We then show such information is very effective to enhance SRL for learner texts. Our model achieves an F-score of 72.06, which is a 2.02 point improvement over the best baseline.

* EMNLP 2018 

  Access Paper or Ask Questions

Is a Picture Worth Ten Thousand Words in a Review Dataset?

Jun 23, 2016
Roberto Camacho Barranco, Laura M. Rodriguez, Rebecca Urbina, M. Shahriar Hossain

While textual reviews have become prominent in many recommendation-based systems, automated frameworks to provide relevant visual cues against text reviews where pictures are not available is a new form of task confronted by data mining and machine learning researchers. Suggestions of pictures that are relevant to the content of a review could significantly benefit the users by increasing the effectiveness of a review. We propose a deep learning-based framework to automatically: (1) tag the images available in a review dataset, (2) generate a caption for each image that does not have one, and (3) enhance each review by recommending relevant images that might not be uploaded by the corresponding reviewer. We evaluate the proposed framework using the Yelp Challenge Dataset. While a subset of the images in this particular dataset are correctly captioned, the majority of the pictures do not have any associated text. Moreover, there is no mapping between reviews and images. Each image has a corresponding business-tag where the picture was taken, though. The overall data setting and unavailability of crucial pieces required for a mapping make the problem of recommending images for reviews a major challenge. Qualitative and quantitative evaluations indicate that our proposed framework provides high quality enhancements through automatic captioning, tagging, and recommendation for mapping reviews and images.

* 10 pages, 11 figures, "for associated results, see http://" "submitted to DLRS 2016 workshop" 

  Access Paper or Ask Questions

Measuring Praise and Criticism: Inference of Semantic Orientation from Association

Sep 19, 2003
Peter D. Turney, Michael L. Littman

The evaluative character of a word is called its semantic orientation. Positive semantic orientation indicates praise (e.g., "honest", "intrepid") and negative semantic orientation indicates criticism (e.g., "disturbing", "superfluous"). Semantic orientation varies in both direction (positive or negative) and degree (mild to strong). An automated system for measuring semantic orientation would have application in text classification, text filtering, tracking opinions in online discussions, analysis of survey responses, and automated chat systems (chatbots). This paper introduces a method for inferring the semantic orientation of a word from its statistical association with a set of positive and negative paradigm words. Two instances of this approach are evaluated, based on two different statistical measures of word association: pointwise mutual information (PMI) and latent semantic analysis (LSA). The method is experimentally tested with 3,596 words (including adjectives, adverbs, nouns, and verbs) that have been manually labeled positive (1,614 words) and negative (1,982 words). The method attains an accuracy of 82.8% on the full test set, but the accuracy rises above 95% when the algorithm is allowed to abstain from classifying mild words.

* ACM Transactions on Information Systems (TOIS), (2003), 21 (4), 315-346 
* 37 pages, related work available at and 

  Access Paper or Ask Questions