Dependency Parsing as MRC-based Span-Span Prediction

by   Leilei Gan, et al.

Higher-order methods for dependency parsing can partially but not fully addresses the issue that edges in dependency tree should be constructed at the text span/subtree level rather than word level. incorrect span covered the corresponding tree rooted at a certain word though the word is correctly linked to its head. In this paper, we propose a new method for dependency parsing to address this issue. The proposed method constructs dependency trees by directly modeling span-span (in other words, subtree-subtree) relations. It consists of two modules: the text span proposal module which proposes candidate text spans, each of which represents a subtree in the dependency tree denoted by (root, start, end); and the span linking module, which constructs links between proposed spans. We use the machine reading comprehension (MRC) framework as the backbone to formalize the span linking module in an MRC setup, where one span is used as a query to extract the text span/subtree it should be linked to. The proposed method comes with the following merits: (1) it addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees; (2) the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans. Extensive experiments on the PTB, CTB and Universal Dependencies (UD) benchmarks demonstrate the effectiveness of the proposed method. We are able to achieve new SOTA performances on PTB and UD benchmarks, and competitive performances to previous SOTA models on the CTB dataset. Code is available at


page 1

page 2

page 3

page 4


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

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

Headed Span-Based Projective Dependency Parsing

We propose a headed span-based method for projective dependency parsing....

Coreference Resolution as Query-based Span Prediction

In this paper, we present an accurate and extensible approach for the co...

MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension

Span extraction is an essential problem in machine reading comprehension...

Improved Latent Tree Induction with Distant Supervision via Span Constraints

For over thirty years, researchers have developed and analyzed methods f...

Joint Chinese Word Segmentation and Span-based Constituency Parsing

In constituency parsing, span-based decoding is an important direction. ...

Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments

Semantic role labeling is a fundamental yet challenging task in the NLP ...

Please sign up or login with your details

Forgot password? Click here to reset