Learning class-specific word embeddings

Recent years have seen the success of applying word embedding algorithms to natural language processing (NLP) tasks. Most word embedding algorithms only produce a single embedding per word. This makes the learned embeddings indiscriminative since many words are polysemous. Some prior work utilizes the context in which the word resides to learn multiple word embeddings. However, context-based solutions are problematic for short texts, such as tweets, which have limited context. Moreover, existing approaches tend to enumerate all possible context types of a particular word regardless of their target applications. Applying multiple vector representations per word in NLP tasks can be computationally expensive because all possible combinations of senses of words in a snippet need to be considered. Sometimes, a word sense can be captured when the class information or label of the short text is presented. For example, in a disaster-related dataset, when a text snippet is labeled as "hurricane related", the word "water" in the snippet is more likely to be interpreted as rain and flood; when a snippet is labeled as "hurricane unrelated", the word "water" can be interpreted as its more general meaning. In this work, we propose to use class information to enhance the discriminativeness of words. Instead of enumerating all potential senses per word in the text, the number of vector representations per word should be a function of the future classification task. We show that learning the number of vector representations per word according to the number of classes in the classification task is often sufficient to clarify the polysemy. Word embeddings learned from neural language models typically have the property of good linear compositionality. We utilize this property to encode class information into the vector representation of a word. We explore four approaches to train class-specific embeddings to encode class information by utilizing the label information and the linear compositionality property of word embeddings. We present a general framework consisting of a pair of convolutional neural networks to utilize the learned class-specific word embeddings as input for text classification tasks. We evaluate our approach and framework on topic classification of a disaster-focused Twitter dataset and a benchmark Twitter sentiment classification dataset from SemEval 2013. Our results show a relative accuracy improvement of 3-4% over a recent baseline.