Wang Ling

TL;DR: This work was sponsored in part by the U. S. Army Research Laboratory and the NSF CAREER grant IIS-1054319 and the European Commission.

TL;DR: The authors propose a stack LSTM to learn representations of parser states in transition-based dependency parsers, which can be used to learn a parser's state, including the buffer of incoming words, the history of actions taken by the parser, and the complete contents of the stack of partially built tree fragments.

TL;DR: A model for constructing vector representations of words by composing characters using bidirectional LSTMs that requires only a single vector per character type and a fixed set of parameters for the compositional model, which yields state- of-the-art results in language modeling and part-of-speech tagging.

Abstract: We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs. Relative to traditional word representation models that have independent vectors for each word type, our model requires only a single vector per character type and a fixed set of parameters for the compositional model. Despite the compactness of this model and, more importantly, the arbitrary nature of the form-function relationship in language, our "composed" word representations yield state-of-the-art results in language modeling and part-of-speech tagging. Benefits over traditional baselines are particularly pronounced in morphologically rich languages (e.g., Turkish).

TL;DR: Two simple modifications to the models in the popular Word2Vec tool are presented, in order to generate embeddings more suited to tasks involving syntax.