This paper describes the system submitted by ANA Team for the SemEval-2019 Task 3: EmoContext. We propose a novel Hierarchical LSTMs for Contextual Emotion Detection (HRLCE) model. It classifies the emotion of an utterance given its conversational context. The results show that, in this task, our HRCLE outperforms the most recent state-of-the-art text classification framework: BERT. We combine the results generated by BERT and HRCLE to achieve an overall score of 0.7709 which ranked 5th on the final leader board of the competition among 165 Teams.
Insufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification. Recognising text documents of classes that have never been seen in the learning stage, so-called zero-shot text classification, is therefore difficult and only limited previous works tackled this problem. In this paper, we propose a two-phase framework together with data augmentation and feature augmentation to solve this problem. Four kinds of semantic knowledge (word embeddings, class descriptions, class hierarchy, and a general knowledge graph) are incorporated into the proposed framework to deal with instances of unseen classes effectively. Experimental results show that each and the combination of the two phases achieve the best overall accuracy compared with baselines and recent approaches in classifying real-world texts under the zero-shot scenario.
State-of-the-art methods for text classification include several distinct steps of pre-processing, feature extraction and post-processing. In this work, we focus on end-to-end neural architectures and show that the best performance in text classification is obtained by combining information from different neural modules. Concretely, we combine convolution, recurrent and attention modules with ensemble methods and show that they are complementary. We introduce ECGA, an end-to-end go-to architecture for novel text classification tasks. We prove that it is efficient and robust, as it attains or surpasses the state-of-the-art on varied datasets, including both low and high data regimes.
In information retrieval (IR) and related tasks, term weighting approaches typically consider the frequency of the term in the document and in the collection in order to compute a score reflecting the importance of the term for the document. In tasks characterized by the presence of training data (such as text classification) it seems logical that the term weighting function should take into account the distribution (as estimated from training data) of the term across the classes of interest. Although `supervised term weighting' approaches that use this intuition have been described before, they have failed to show consistent improvements. In this article we analyse the possible reasons for this failure, and call consolidated assumptions into question. Following this criticism we propose a novel supervised term weighting approach that, instead of relying on any predefined formula, learns a term weighting function optimised on the training set of interest; we dub this approach \emph{Learning to Weight} (LTW). The experiments that we run on several well-known benchmarks, and using different learning methods, show that our method outperforms previous term weighting approaches in text classification.
Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the artificial intelligence (AI) divide. Transfer-based approaches, such as Cross-Lingual Text Classification (CLTC) - the task of categorizing texts written in different languages into a common taxonomy, are a promising solution to the emerging AI divide. Recent work on CLTC has focused on demonstrating the benefits of using bilingual word embeddings as features, relegating the CLTC problem to a mere benchmark based on a simple averaged perceptron. In this paper, we explore more extensively and systematically two flavors of the CLTC problem: news topic classification and textual churn intent detection (TCID) in social media. In particular, we test the hypothesis that embeddings with context are more effective, by multi-tasking the learning of multilingual word embeddings and text classification; we explore neural architectures for CLTC; and we move from bi- to multi-lingual word embeddings. For all architectures, types of word embeddings and datasets, we notice a consistent gain trend in favor of multilingual joint training, especially for low-resourced languages.
In computer vision, virtually every state-of-the-art deep learning system is trained with data augmentation. In text classification, however, data augmentation is less widely practiced because it must be performed before training and risks introducing label noise. We augment the IMDB movie reviews dataset with examples generated by two families of techniques: random token perturbations introduced by Wei and Zou [2019] and backtranslation -- translating to a second language then back to English. In low resource environments, backtranslation generates significant improvement on top of the state of-the-art ULMFit model. A ULMFit model pretrained on wikitext103 and then fine-tuned on only 50 IMDB examples and 500 synthetic examples generated by backtranslation achieves 80.6% accuracy, an 8.1% improvement over the augmentation-free baseline with only 9 minutes of additional training time. Random token perturbations do not yield any improvements but incur equivalent computational cost. The benefits of training with backtranslated examples decreases with the size of the available training data. On the full dataset, neither augmentation technique improves upon ULMFit's state of the art performance. We address this by using backtranslations as a form of test time augmentation as well as ensembling ULMFit with other models, and achieve small improvements.
Online reviews have become a vital source of information in purchasing a service (product). Opinion spammers manipulate reviews, affecting the overall perception of the service. A key challenge in detecting opinion spam is obtaining ground truth. Though there exists a large set of reviews online, only a few of them have been labeled spam or non-spam. In this paper, we propose spamGAN, a generative adversarial network which relies on limited set of labeled data as well as unlabeled data for opinion spam detection. spamGAN improves the state-of-the-art GAN based techniques for text classification. Experiments on TripAdvisor dataset show that spamGAN outperforms existing spam detection techniques when limited labeled data is used. Apart from detecting spam reviews, spamGAN can also generate reviews with reasonable perplexity.
We present a new approach for pretraining a bi-directional transformer model that provides significant performance gains across a variety of language understanding problems. Our model solves a cloze-style word reconstruction task, where each word is ablated and must be predicted given the rest of the text. Experiments demonstrate large performance gains on GLUE and new state of the art results on NER as well as constituency parsing benchmarks, consistent with the concurrently introduced BERT model. We also present a detailed analysis of a number of factors that contribute to effective pretraining, including data domain and size, model capacity, and variations on the cloze objective.
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much attention, training text classification models have not. In this paper, we propose an approach to training deep networks that is robust to label noise. This approach introduces a non-linear processing layer (noise model) that models the statistics of the label noise into a convolutional neural network (CNN) architecture. The noise model and the CNN weights are learned jointly from noisy training data, which prevents the model from overfitting to erroneous labels. Through extensive experiments on several text classification datasets, we show that this approach enables the CNN to learn better sentence representations and is robust even to extreme label noise. We find that proper initialization and regularization of this noise model is critical. Further, by contrast to results focusing on large batch sizes for mitigating label noise for image classification, we find that altering the batch size does not have much effect on classification performance.
This thesis presents a language-independent text classification model by introduced two new encoding methods "BUNOW" and "BUNOC" used for feeding the raw text data into a new CNN spatial architecture with vertical and horizontal convolutional process instead of commonly used methods like one hot vector or word representation (i.e. word2vec) with temporal CNN architecture. The proposed model can be classified as hybrid word-character model in its work methodology because it consumes less memory space by using a fewer neural network parameters as in character level representation, in addition to providing much faster computations with fewer network layers depth, as in word level representation. A promising result achieved compared to state of art models in two different morphological benchmarked dataset one for Arabic language and one for English language.
Tabular data is the most commonly used form of data in industry. Gradient Boosting Trees, Support Vector Machine, Random Forest, and Logistic Regression are typically used for classification tasks on tabular data. DNN models using categorical embeddings are also applied in this task, but all attempts thus far have used one-dimensional embeddings. The recent work of Super Characters method using two-dimensional word embeddings achieved the state of art result in text classification tasks, showcasing the promise of this new approach. In this paper, we propose the SuperTML method, which borrows the idea of Super Characters method and two-dimensional embeddings to address the problem of classification on tabular data. For each input of tabular data, the features are first projected into two-dimensional embeddings like an image, and then this image is fed into fine-tuned two-dimensional CNN models for classification. Experimental results have shown that the proposed SuperTML method had achieved state-of-the-art results on both large and small datasets.
Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of threshold-agnostic metrics that provide a nuanced view of this unintended bias, by considering the various ways that a classifier's score distribution can vary across designated groups. We also introduce a large new test set of online comments with crowd-sourced annotations for identity references. We use this to show how our metrics can be used to find new and potentially subtle unintended bias in existing public models.
Product categorization using text data for eCommerce is a very challenging extreme classification problem with several thousands of classes and several millions of products to classify. Even though multi-class text classification is a well studied problem both in academia and industry, most approaches either deal with treating product content as a single pile of text, or only consider a few product attributes for modelling purposes. Given the variety of products sold on popular eCommerce platforms, it is hard to consider all available product attributes as part of the modeling exercise, considering that products possess their own unique set of attributes based on category. In this paper, we compare hierarchical models to flat models and show that in specific cases, flat models perform better. We explore two Deep Learning based models that extract features from individual pieces of unstructured data from each product and then combine them to create a product signature. We also propose a novel idea of using structured attributes and their values together in an unstructured fashion along with convolutional filters such that the ordering of the attributes and the differing attributes by product categories no longer becomes a modelling challenge. This approach is also more robust to the presence of faulty product attribute names and values and can elegantly generalize to use both closed list and open list attributes.
Text classification plays a vital role today especially with the intensive use of social networking media. Recently, different architectures of convolutional neural networks have been used for text classification in which one-hot vector, and word embedding methods are commonly used. This paper presents a new language independent word encoding method for text classification. The proposed model converts raw text data to low-level feature dimension with minimal or no preprocessing steps by using a new approach called binary unique number of word "BUNOW". BUNOW allows each unique word to have an integer ID in a dictionary that is represented as a k-dimensional vector of its binary equivalent. The output vector of this encoding is fed into a convolutional neural network (CNN) model for classification. Moreover, the proposed model reduces the neural network parameters, allows faster computation with few network layers, where a word is atomic representation the document as in word level, and decrease memory consumption for character level representation. The provided CNN model is able to work with other languages or multi-lingual text without the need for any changes in the encoding method. The model outperforms the character level and very deep character level CNNs models in terms of accuracy, network parameters, and memory consumption; the results show total classification accuracy 91.99% and error 8.01% using AG's News dataset compared to the state of art methods that have total classification accuracy 91.45% and error 8.55%, in addition to the reduction in input feature vector and neural network parameters by 62% and 34%, respectively.
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving adversarial examples. First, we present a manifold learning method to capture the semantics of the inputs. The motivating principle is to learn the low-dimensional geometric summaries of the inputs via statistical inference. Then, we perturb the elements of the learned manifold using the Gram-Schmidt process to induce the perturbed elements to remain in the manifold. To produce adversarial examples, we propose an efficient algorithm whereby we leverage the semantics of the inputs as a source of knowledge upon which we impose adversarial constraints. We apply our approach on toy data, images and text, and show its effectiveness in producing semantics preserving adversarial examples which evade existing defenses against adversarial attacks.
We introduce the task of algorithm class prediction for programming word problems. A programming word problem is a problem written in natural language, which can be solved using an algorithm or a program. We define classes of various programming word problems which correspond to the class of algorithms required to solve the problem. We present four new datasets for this task, two multiclass datasets with 550 and 1159 problems each and two multilabel datasets having 3737 and 3960 problems each. We pose the problem as a text classification problem and train neural network and non-neural network-based models on this task. Our best performing classifier gets an accuracy of 62.7 percent for the multiclass case on the five class classification dataset, Codeforces Multiclass-5 (CFMC5). We also do some human-level analysis and compare human performance with that of our text classification models. Our best classifier has an accuracy only 9 percent lower than that of a human on this task. To the best of our knowledge, these are the first reported results on such a task. We make our code and datasets publicly available.
Voice-assistants text classification and named-entity recognition (NER) models are trained on millions of example utterances. Because of the large datasets, long training time is one of the bottlenecks for releasing improved models. In this work, we develop F10-SGD, a fast optimizer for text classification and NER elastic-net linear models. On internal datasets, F10-SGD provides 4x reduction in training time compared to the OWL-QN optimizer without loss of accuracy or increase in model size. Furthermore, we incorporate biased sampling that prioritizes harder examples towards the end of the training. As a result, in addition to faster training, we were able to obtain statistically significant accuracy improvements for NER. On public datasets, F10-SGD obtains 22% faster training time compared to FastText for text classification. And, 4x reduction in training time compared to CRFSuite OWL-QN for NER.
A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effective transfer learning approach that addresses the problem of catastrophic forgetting. Specifically, we combine the task-specific optimization function with an auxiliary language model objective, which is adjusted during the training process. This preserves language regularities captured by language models, while enabling sufficient adaptation for solving the target task. Our method does not require pretraining or finetuning separate components of the network and we train our models end-to-end in a single step. We present results on a variety of challenging affective and text classification tasks, surpassing well established transfer learning methods with greater level of complexity.
Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared to a small support set at the sample-wise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries. In this paper, we propose a novel Induction Network to learn such a generalized class-wise representation, by innovatively leveraging the dynamic routing algorithm in meta-learning. In this way, we find the model is able to induce and generalize better. We evaluate the proposed model on a well-studied sentiment classification dataset (English) and a real-world dialogue intent classification dataset (Chinese). Experiment results show that on both datasets, the proposed model significantly outperforms the existing state-of-the-art approaches, proving the effectiveness of class-wise generalization in few-shot text classification.
With the rapid development in deep learning, deep neural networks have been widely adopted in many real-life natural language applications. Under deep neural networks, a pre-defined vocabulary is required to vectorize text inputs. The canonical approach to select pre-defined vocabulary is based on the word frequency, where a threshold is selected to cut off the long tail distribution. However, we observed that such simple approach could easily lead to under-sized vocabulary or over-sized vocabulary issues. Therefore, we are interested in understanding how the end-task classification accuracy is related to the vocabulary size and what is the minimum required vocabulary size to achieve a specific performance. In this paper, we provide a more sophisticated variational vocabulary dropout (VVD) based on variational dropout to perform vocabulary selection, which can intelligently select the subset of the vocabulary to achieve the required performance. To evaluate different algorithms on the newly proposed vocabulary selection problem, we propose two new metrics: Area Under Accuracy-Vocab Curve and Vocab Size under X\% Accuracy Drop. Through extensive experiments on various NLP classification tasks, our variational framework is shown to significantly outperform the frequency-based and other selection baselines on these metrics.