Wanxiang Che

3 paper cards in Mova's library · 2015–2021

Wanxiang Che wrote 3 of the papers Mova reads, in 2015–2021, most of them on Dependency parsing, Universal Dependencies, Machine translation; often with Bing Qin, Yijia Liu, Ivan Titov.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples (2021)
The paper attacks two English dependency parsers, a biaffine graph parser and a stack-pointer parser, by substituting words.
Parsing Tweets into Universal Dependencies (2018)
The authors extend the UD guidelines to tweets: emoticons and retweet markers become non-syntactic or discourse tokens, abbreviations such as "idc" stay unnormalized as single words, multiword expressions can be merged, and tweets can have several roots.
Transition-Based Syntactic Linearization (2015)
Syntactic linearization takes a bag of words and optional syntactic constraints and builds the sentence and its tree together.