Log In Sign Up

Modeling Label Correlations for Second-Order Semantic Dependency Parsing with Mean-Field Inference

by   Songlin Yang, et al.

Second-order semantic parsing with end-to-end mean-field inference has been shown good performance. In this work we aim to improve this method by modeling label correlations between adjacent arcs. However, direct modeling leads to memory explosion because second-order score tensors have sizes of O(n^3L^2) (n is the sentence length and L is the number of labels), which is not affordable. To tackle this computational challenge, we leverage tensor decomposition techniques, and interestingly, we show that the large second-order score tensors have no need to be materialized during mean-field inference, thereby reducing the computational complexity from cubic to quadratic. We conduct experiments on SemEval 2015 Task 18 English datasets, showing the effectiveness of modeling label correlations. Our code is publicly available at


page 1

page 2

page 3

page 4


Second-Order Semantic Dependency Parsing with End-to-End Neural Networks

Semantic dependency parsing aims to identify semantic relationships betw...

Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs

Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCF...

Critical states in Political Trends. How much reliable is a poll on Twitter? A study by means of the Potts Model

In recent years, Twitter data related to political trends have tentative...

Combining (second-order) graph-based and headed span-based projective dependency parsing

Graph-based methods are popular in dependency parsing for decades. Recen...

Mean Field inference of CRFs based on GAT

In this paper we propose an improved mean-field inference algorithm for ...