732 citations · 973 across the 15 of their papers we have counts for
16 papers
Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling
Di Jin, Seokhwan Kim, Dilek Hakkani-Tur
Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs…
Adversarial Contrastive Pre-training for Protein Sequences
Matthew B. A. McDermott, Brendan Yap, Harry Hsu +2
Recent developments in Natural Language Processing (NLP) demonstrate that large-scale, self-supervised pre-training can be extremely beneficial for downstream tasks. These ideas ha…
Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search
Ziyang Liu, Zhaomeng Cheng, Yunjiang Jiang +5
Result relevance prediction is an essential task of e-commerce search engines to boost the utility of search engines and ensure smooth user experience. The last few years eyewitnes…
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…
MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension
Di Jin, Shuyang Gao, Jiun-Yu Kao +2
Machine Reading Comprehension (MRC) for question answering (QA), which aims to answer a question given the relevant context passages, is an important way to test the ability of int…
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…
Publicly Available Clinical BERT Embeddings
Emily Alsentzer, John R. Murphy, Willie Boag +4
Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP)…
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…
High-throughput, high-resolution registration-free generated adversarial network microscopy
Hao Zhang, Xinlin Xie, Chunyu Fang +3
We combine generative adversarial network (GAN) with light microscopy to achieve deep learning super-resolution under a large field of view (FOV). By appropriately adopting prior m…