TY - JOUR
T1 - Easy-first dependency parsing with hierarchical tree LSTMs
AU - Kiperwasser, Eliyahu
AU - Goldberg, Y.
PY - 2016
Y1 - 2016
N2 - We suggest a compositional vector representation of parse trees that relies on a recursive combination of recurrent-neural network encoders. To demonstrate its effectiveness, we use the representation as the backbone of a greedy, bottom-up dependency parser, achieving state-of-the-art accuracies for English and Chinese, without relying on external word embeddings. The parser's implementation is available for download at the first author's webpage.
AB - We suggest a compositional vector representation of parse trees that relies on a recursive combination of recurrent-neural network encoders. To demonstrate its effectiveness, we use the representation as the backbone of a greedy, bottom-up dependency parser, achieving state-of-the-art accuracies for English and Chinese, without relying on external word embeddings. The parser's implementation is available for download at the first author's webpage.
UR - https://scholar.google.co.il/scholar?q=Easy-first+Dependency+Parsing+with+Hierarchical+Tree+LSTMs&btnG=&hl=en&as_sdt=0%2C5
M3 - Article
VL - 4
SP - 445
EP - 461
JO - Transactions of the Association for Computational Linguistics
JF - Transactions of the Association for Computational Linguistics
ER -