732 citations · 973 across the 15 of their papers we have counts for
8 papers · 1 filter
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…
BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search
Yunjiang Jiang, Yue Shang, Ziyang Liu +6
Relevance has significant impact on user experience and business profit for e-commerce search platform. In this work, we propose a data-driven framework for search relevance predic…
What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams
Di Jin, Eileen Pan, Nassim Oufattole +3
Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present t…
Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
Xuewen Yang, Heming Zhang, Di Jin +6
Generating accurate descriptions for online fashion items is important not only for enhancing customers' shopping experiences, but also for the increase of online sales. Besides th…
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…
From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
Shuyang Gao, Sanchit Agarwal, Tagyoung Chung +2
Dialogue state tracking (DST) is at the heart of task-oriented dialogue systems. However, the scarcity of labeled data is an obstacle to building accurate and robust state tracking…
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…