CTB

We investigate generalizations of the all- subtrees "DOP" approach to unsupervised parsing. Unsupervised DOP models assign all possible binary trees to a set of sentences and next use (a large …...

We propose a generalization of the super- vised DOP model to unsupervised learning. This new model, which we call U-DOP, initially assigns all possible unlabeled binary trees to a set …...

AbstractThis paper presents a sequence to sequence (seq2seq) dependency parser by directly predicting the relative position of head for each given word, which therefore results in a truly end-to-end seq2seq …...

AbstractWe propose a novel linearization of a constituent tree, together with a new locally normalized model. For each split point in a sentence, our model computes the normalizer on all …...

AbstractWe introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, …...

AbstractGraph-based methods, which decompose the score of a dependency tree into scores of dependency arcs, are popular in dependency parsing for decades. Recently, (CITATION) propose a headed-span-based method that decomposes …...

AbstractHigher-order methods for dependency parsing can partially but not fully address the issue that edges in dependency trees should be constructed at the text span/subtree level rather than word level. …...

AbstractWe propose a new method for projective dependency parsing based on headed spans. In a projective dependency tree, the largest subtree rooted at each word covers a contiguous sequence (i.e., …...