Language Models as Representations for Weakly Supervised NLP Tasks

Finding the right representations for words is critical for building accurate NLP systems when domain-specific labeled data for the task is scarce. This paper investigates language model representations, in which language models trained on unlabeled corpora are used to generate real-valued feature vectors for words. We investigate ngram models and probabilistic graphical models, including a novel lattice-structured Markov Random Field. Experiments indicate that language model representations outperform traditional representations, and that graphical model representations outperform ngram models, especially on sparse and polysemous words.