HLP$@$UPenn at SemEval-2017 Task 4A: A simple, self-optimizing text classification system combining dense and sparse vectors

Abstract

We present a simple supervised text classification system that combines sparse and dense vector representations of words, and the generalized representations of words via clusters. The sparse vectors are generated from word n-gram sequences (1-3). The dense vector representations of words (embeddings) are learned by training a neural network to predict neighboring words in a large unlabeled dataset. To classify a text segment, the different vector representations of it are concatenated, and the classification is performed using Support Vector Machines (SVMs). Our system is particularly intended for use by nonexperts of natural language processing and machine learning, and, therefore, the system does not require any manual tuning of parameters or weights. Given a training set, the system automatically generates the training vectors, optimizes the relevant hyper-parameters for the SVM classifier, and trains the classification model. We evaluated this system on the SemEval-2017 English sentiment analysis task. In terms of average F1-Score, our system obtained 8 th position out of 39 submissions (F1-Score: 0.632, average recall: 0.637, accuracy: 0.646).

Data-Driven Lexical Normalization for Medical Social Media

“…For all three tasks, extracted concepts could be matched exactly to the forum posts, thus negating the potential benefit of normalization. The exact matching can perhaps be explained by the fact that data collection and extraction from noisy text sources such as social media typically rely on keyword-based searching [54].…”

Evaluating the Accuracy and Efficiency of Sentiment Analysis Pipelines with UIMA

“…unigrams, bigrams or trigram, respectively. Sarker et al [15] and Pal and Gosh [11] used n-gram features for developing sentiment analysis methods and evaluated their methods against the same datasets that we use in this work. Here, we explore the fol-Table 2.…”

Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task

“…For all three tasks, extracted concepts could be matched exactly to the forum posts, thus negating the potential benefit of normalization. The exact matching can perhaps be explained by the fact that data collection and extraction from noisy text sources such as social media typically rely on keyword-based searching (Sarker and Gonzalez, 2017b).…”