DeepAI AI Chat
Log In Sign Up

On Finding the K-best Non-projective Dependency Trees

by   Ran Zmigrod, et al.

The connection between the maximum spanning tree in a directed graph and the best dependency tree of a sentence has been exploited by the NLP community. However, for many dependency parsing schemes, an important detail of this approach is that the spanning tree must have exactly one edge emanating from the root. While work has been done to efficiently solve this problem for finding the one-best dependency tree, no research has attempted to extend this solution to finding the K-best dependency trees. This is arguably a more important extension as a larger proportion of decoded trees will not be subject to the root constraint of dependency trees. Indeed, we show that the rate of root constraint violations increases by an average of 13 times when decoding with K=50 as opposed to K=1. In this paper, we provide a simplification of the K-best spanning tree algorithm of Camerini et al. (1980). Our simplification allows us to obtain a constant time speed-up over the original algorithm. Furthermore, we present a novel extension of the algorithm for decoding the K-best dependency trees of a graph which are subject to a root constraint.


page 1

page 2

page 3

page 4


Efficient Sampling of Dependency Structures

Probabilistic distributions over spanning trees in directed graphs are a...

Please Mind the Root: Decoding Arborescences for Dependency Parsing

The connection between dependency trees and spanning trees is exploited ...

Unbiased and Efficient Sampling of Dependency Trees

Distributions over spanning trees are the most common way of computation...

A New Dynamic Programming Approach for Spanning Trees with Chain Constraints and Beyond

Short spanning trees subject to additional constraints are important bui...

Leaping through tree space: continuous phylogenetic inference for rooted and unrooted trees

Phylogenetics is now fundamental in life sciences, providing insights in...

With Great Speed Come Small Buffers: Space-Bandwidth Tradeoffs for Routing

We consider the Adversarial Queuing Theory (AQT) model, where packet arr...

Dependency Parsing as Head Selection

Conventional graph-based dependency parsers guarantee a tree structure b...

Code Repositories


Code Repository for "Please Mind the Root: Decoding Arborescences for Dependency Parsing"

view repo