99 citations · 245 across the 10 of their papers we have counts for
11 papers
Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
Qipeng Guo, Zhijing Jin, Ziyu Wang +5
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched…
Deep Learning for Text Style Transfer: A Survey
Di Jin, Zhijing Jin, Zhiting Hu +2
Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and man…
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis
Xiaoyu Xing, Zhijing Jin, Di Jin +3
Aspect-based sentiment analysis (ABSA) aims to predict the sentiment towards a specific aspect in the text. However, existing ABSA test sets cannot be used to probe whether a model…
CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training
Qipeng Guo, Zhijing Jin, Xipeng Qiu +3
Two important tasks at the intersection of knowledge graphs and natural language processing are graph-to-text (G2T) and text-to-graph (T2G) conversion. Due to the difficulty and hi…
Relation of the Relations: A New Paradigm of the Relation Extraction Problem
Zhijing Jin, Yongyi Yang, Xipeng Qiu +1
In natural language, often multiple entities appear in the same text. However, most previous works in Relation Extraction (RE) limit the scope to identifying the relation between t…
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles
Di Jin, Zhijing Jin, Joey Tianyi Zhou +2
Current summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure. We propose a new task, S…
A Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation
Di Jin, Zhijing Jin, Joey Tianyi Zhou +1
State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible…
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Di Jin, Zhijing Jin, Joey Tianyi Zhou +1
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models…
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
Zhijing Jin, Di Jin, Jonas Mueller +2
Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This t…
GraphIE: A Graph-Based Framework for Information Extraction
Yujie Qian, Enrico Santus, Zhijing Jin +2
Most modern Information Extraction (IE) systems are implemented as sequential taggers and only model local dependencies. Non-local and non-sequential context is, however, a valuabl…
3D Traffic Simulation for Autonomous Vehicles in Unity and Python
Zhijing Jin, Tristan Swedish, Ramesh Raskar
Over the recent years, there has been an explosion of studies on autonomous vehicles. Many collected large amount of data from human drivers. However, compared to the tedious data…