activity
20202022
most citedRetrofitting Structure-aware Transformer Language Model for End Tasks

22 citations · 29 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CL2022

Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph

Hao Fei, Shengqiong Wu, Meishan Zhang +2

Conversational semantic role labeling (CSRL) is a newly proposed task that uncovers the shallow semantic structures in a dialogue text. Unfortunately several important characterist…

cs.CL2021

Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledge

Shengqiong Wu, Hao Fei, Yafeng Ren +2

In this paper, we propose to enhance the pair-wise aspect and opinion terms extraction (PAOTE) task by incorporating rich syntactic knowledge. We first build a syntax fusion encode…

cs.CL2020

Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain

Bobo Li, Hao Fei, Yafeng Ren +1

Lexical chain consists of cohesion words in a document, which implies the underlying structure of a text, and thus facilitates downstream NLP tasks. Nevertheless, existing work foc…

cs.CL20203 cited

Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP

Hao Fei, Yafeng Ren, Donghong Ji

Syntax has been shown useful for various NLP tasks, while existing work mostly encodes singleton syntactic tree using one hierarchical neural network. In this paper, we investigate…

cs.CL202022 cited

Retrofitting Structure-aware Transformer Language Model for End Tasks

Hao Fei, Yafeng Ren, Donghong Ji

We consider retrofitting structure-aware Transformer-based language model for facilitating end tasks by proposing to exploit syntactic distance to encode both the phrasal constitue…

cs.CL20204 cited

High-order Refining for End-to-end Chinese Semantic Role Labeling

Hao Fei, Yafeng Ren, Donghong Ji

Current end-to-end semantic role labeling is mostly accomplished via graph-based neural models. However, these all are first-order models, where each decision for detecting any pre…