Untitled

Wu, Bang Ye; Chao, Kun-Mao; Tang, Chuan Yi

doi:10.1023/a:1009885610075

Cited by 31 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More generally, the binary tree structure of a sequence with N tokens can be specified with a sequence of N − 1 syntactic distances. This definition of distance makes the syntactic distance an ultrametric (Holly, 2001;Wu et al, 1999), a concept which is important in the theory of hierarchical agglomerative clustering (Johnson, 1967) and was first explored in a linguistic setting by Levelt (1974).…”

Section: Ordered Neurons Lstmmentioning

confidence: 99%

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach

Lin

Shen

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic. In this paper, we make use of a multi-task objective, i.e., the models simultaneously predict words as well as ground truth parse trees in a form called "syntactic distances", where information between these two separate objectives shares the same intermediate representation. Experimental results on the Penn Treebank and Chinese Treebank datasets show that when ground truth parse trees are provided as additional training signals, the model is able to achieve lower perplexity and induce trees with better quality.

show abstract

Section: Ordered Neurons Lstmmentioning

confidence: 99%

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach

Lin

Shen

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

Solving Constrained Optimization Problems with Hybrid Evolutionary Algorithms

Cotta

Fernández

2008

Optimization Techniques for Solving Complex Problems

View full text Add to dashboard Cite

The minimum evolution problem: Overview and classification

Catanzaro

2008

Networks

View full text Add to dashboard Cite

Molecular phylogenetics studies the hierarchical evolutionary relationships among organisms by means of molecular data. These relationships are typically described by means of weighted trees, or phylogenies, whose leaves represent the observed organisms, internal vertices the intermediate ancestors, and edges the evolutionary relationships between pairs of organisms. Molecular phylogenetics provides several criteria for selecting one phylogeny from among plausible alternatives. Usually, such criteria can be expressed in terms of objective functions, and the phylogenies that optimize them are referred to as optimal. One of the most important criteria is the minimum evolution (ME) criterion, which states that the optimal phylogeny for a given set of organisms is the one whose sum of edge weights is minimal. Finding the phylogeny that satisfies the ME criterion involves solving an optimization problem, called the minimum evolution problem (MEP), which is notoriously N P-Hard. This article offers an overview of the MEP and discusses the different versions of it that occur in the literature.

show abstract

Untitled

Cited by 31 publications

References 15 publications

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach

Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach

Solving Constrained Optimization Problems with Hybrid Evolutionary Algorithms

The minimum evolution problem: Overview and classification

Contact Info

Product

Resources

About