Learned in Translation: Contextualized Word Vectors
This addresses the need for better initialization methods in NLP models, offering a novel approach that enhances performance across multiple common tasks, though it builds on existing translation techniques.
The paper tackled the problem of improving NLP task performance by using contextualized word vectors derived from a machine translation model, achieving state-of-the-art results on sentiment analysis and entailment tasks.
Computer vision has benefited from initializing multiple deep layers with weights pretrained on large supervised training sets like ImageNet. Natural language processing (NLP) typically sees initialization of only the lowest layer of deep models with pretrained word vectors. In this paper, we use a deep LSTM encoder from an attentional sequence-to-sequence model trained for machine translation (MT) to contextualize word vectors. We show that adding these context vectors (CoVe) improves performance over using only unsupervised word and character vectors on a wide variety of common NLP tasks: sentiment analysis (SST, IMDb), question classification (TREC), entailment (SNLI), and question answering (SQuAD). For fine-grained sentiment analysis and entailment, CoVe improves performance of our baseline models to the state of the art.