Xiang Ren

is this you? claim profile

∙ 0 followers
University of Southern California ∙ University of Illinois at Urbana-Champaign

ssistant Professor of Computer Science at University of Southern California

AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding

Automatic extraction of product attribute values is an important enablin...
06/04/2021 ∙ by Jun Yan, et al. ∙ 0 ∙ share

read it
X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering

Multilingual models, such as M-BERT and XLM-R, have gained increasing po...
04/20/2021 ∙ by Meryem M'hamdi, et al. ∙ 11 ∙ share

read it
On the Influence of Masking Policies in Intermediate Pre-training

Current NLP models are predominantly trained through a pretrain-then-fin...
04/18/2021 ∙ by Qinyuan Ye, et al. ∙ 0 ∙ share

read it
Lifelong Learning of Few-shot Learners across NLP Tasks

Recent advances in large pre-trained language models have greatly improv...
04/18/2021 ∙ by Xisen Jin, et al. ∙ 0 ∙ share

read it
SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning

Augmenting pre-trained language models with knowledge graphs (KGs) has a...
04/18/2021 ∙ by Aaron Chan, et al. ∙ 0 ∙ share

read it
On the Strengths of Cross-Attention in Pretrained Transformers for Machine Translation

We study the power of cross-attention in the Transformer architecture wi...
04/18/2021 ∙ by Mozhdeh Gheini, et al. ∙ 10 ∙ share

read it
Extract, Denoise, and Enforce: Evaluating and Predicting Lexical Constraints for Conditional Text Generation

Recently, pre-trained language models (PLMs) have dominated conditional ...
04/18/2021 ∙ by Yuning Mao, et al. ∙ 0 ∙ share

read it
Refining Neural Networks with Compositional Explanations

Neural networks are prone to learning spurious correlations from biased ...
03/18/2021 ∙ by Huihan Yao, et al. ∙ 0 ∙ share

read it
Modality-specific Distillation

Large neural networks are impractical to deploy on mobile devices due to...
01/06/2021 ∙ by Woojeong Jin, et al. ∙ 0 ∙ share

read it
Zero-shot Learning by Generating Task-specific Adapters

Pre-trained text-to-text transformers achieve impressive performance acr...
01/02/2021 ∙ by Qinyuan Ye, et al. ∙ 0 ∙ share

read it
Studying Strategically: Learning to Mask for Closed-book QA

Closed-book question-answering (QA) is a challenging task that requires ...
12/31/2020 ∙ by Qinyuan Ye, et al. ∙ 0 ∙ share

read it
DEER: A Data Efficient Language Model for Event Temporal Reasoning

Pretrained language models (LMs) such as BERT, RoBERTa, and ELECTRA are ...
12/30/2020 ∙ by Rujun Han, et al. ∙ 28 ∙ share

read it
Learning Contextualized Knowledge Structures for Commonsense Reasoning

Recently, neural-symbolic architectures have achieved success on commons...
10/24/2020 ∙ by Jun Yan, et al. ∙ 0 ∙ share

read it
Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation

Symbolic knowledge (e.g., entities, relations, and facts in a knowledge ...
10/24/2020 ∙ by Mrigank Raman, et al. ∙ 6 ∙ share

read it
Efficiently Mitigating Classification Bias via Transfer Learning

Prediction bias in machine learning models refers to unintended model be...
10/24/2020 ∙ by Xisen Jin, et al. ∙ 0 ∙ share

read it
Fair Hate Speech Detection through Evaluation of Social Group Counterfactuals

Approaches for mitigating bias in supervised models are designed to redu...
10/24/2020 ∙ by Aida Mostafazadeh Davani, et al. ∙ 0 ∙ share

read it
Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation

Summaries generated by abstractive summarization are supposed to only co...
10/24/2020 ∙ by Yuning Mao, et al. ∙ 0 ∙ share

read it
Will This Idea Spread Beyond Academia? Understanding Knowledge Transfer of Scientific Concepts across Text Corpora

What kind of basic research ideas are more likely to get applied in prac...
10/13/2020 ∙ by Hancheng Cao, et al. ∙ 0 ∙ share

read it
Semi-Automated Protocol Disambiguation and Code Generation

For decades, Internet protocols have been specified using natural langua...
10/09/2020 ∙ by Jane Yen, et al. ∙ 0 ∙ share

read it
Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning

While neural sequence learning methods have made significant progress in...
09/30/2020 ∙ by Yuning Mao, et al. ∙ 27 ∙ share

read it
Two Step Joint Model for Drug Drug Interaction Extraction

When patients need to take medicine, particularly taking more than one k...
08/28/2020 ∙ by Siliang Tang, et al. ∙ 0 ∙ share

read it
Gradient Based Memory Editing for Task-Free Continual Learning

Prior work on continual learning often operate in a "task-aware" manner,...
06/27/2020 ∙ by Xisen Jin, et al. ∙ 0 ∙ share

read it
Screenplay Quality Assessment: Can We Predict Who Gets Nominated?

Deciding which scripts to turn into movies is a costly and time-consumin...
05/13/2020 ∙ by Ming-Chang Chiu, et al. ∙ 0 ∙ share

read it
Contextualizing Hate Speech Classifiers with Post-hoc Explanation

Hate speech classifiers trained on imbalanced datasets struggle to deter...
05/05/2020 ∙ by Brendan Kennedy, et al. ∙ 0 ∙ share

read it
Teaching Machine Comprehension with Compositional Explanations

Advances in extractive machine reading comprehension (MRC) rely heavily ...
05/02/2020 ∙ by Qinyuan Ye, et al. ∙ 0 ∙ share

read it
ForecastQA: Machine Comprehension of Temporal Text for Answering Forecasting Questions

Textual data are often accompanied by time information (e.g., dates in n...
05/02/2020 ∙ by Woojeong Jin, et al. ∙ 12 ∙ share

read it
Visually Grounded Continual Learning of Compositional Semantics

Children's language acquisition from the visual world is a real-world ex...
05/02/2020 ∙ by Xisen Jin, et al. ∙ 0 ∙ share

read it
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Commonsense question answering (QA) requires the modeling of general bac...
05/02/2020 ∙ by Peifeng Wang, et al. ∙ 5 ∙ share

read it
Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning

Walk-based models have shown their unique advantages in knowledge graph ...
05/01/2020 ∙ by Deren Lei, et al. ∙ 6 ∙ share

read it
Generating Natural Language Adversarial Examples on a Large Scale with Generative Models

Today text classification models have been widely used. However, these c...
03/10/2020 ∙ by Yankun Ren, et al. ∙ 0 ∙ share

read it
Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution

Time series prediction is an important problem in machine learning. Prev...
03/09/2020 ∙ by Sankalp Garg, et al. ∙ 28 ∙ share

read it
Mining News Events from Comparable News Corpora: A Multi-Attribute Proximity Network Modeling Approach

We present ProxiModel, a novel event mining framework for extracting hig...
11/14/2019 ∙ by Hyungsul Kim, et al. ∙ 11 ∙ share

read it
Improving BERT Fine-tuning with Embedding Normalization

Large pre-trained sentence encoders like BERT start a new chapter in nat...
11/10/2019 ∙ by Wenxuan Zhou, et al. ∙ 0 ∙ share

read it
CommonGen: A Constrained Text Generation Dataset Towards Generative Commonsense Reasoning

Rational humans can generate sentences that cover a certain set of conce...
11/09/2019 ∙ by Bill Yuchen Lin, et al. ∙ 23 ∙ share

read it
Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models

The impressive performance of neural networks on natural language proces...
11/08/2019 ∙ by Xisen Jin, et al. ∙ 19 ∙ share

read it
Learning to Annotate: Modularizing Data Augmentation for Text Classifiers with Natural Language Explanations

Deep neural networks usually require massive labeled data, which restric...
11/04/2019 ∙ by Ziqi Wang, et al. ∙ 0 ∙ share

read it
Learning to Annotate: Modularizing Data Augmentation for TextClassifiers with Natural Language Explanations

Deep neural networks usually require massive labeled data, which restric...
11/04/2019 ∙ by Ziqi Wang, et al. ∙ 0 ∙ share

read it
HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion

Taxonomies are of great value to many knowledge-rich applications. As th...
10/17/2019 ∙ by Jiaming Shen, et al. ∙ 25 ∙ share

read it
SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemble

Corpus-based set expansion (i.e., finding the "complete" set of entities...
10/17/2019 ∙ by Jiaming Shen, et al. ∙ 0 ∙ share

read it
Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling

Sequence labeling is a fundamental framework for various natural languag...
10/09/2019 ∙ by Ouyu Lan, et al. ∙ 0 ∙ share

read it
Neural Rule Grounding for Low-Resource Relation Extraction

While deep neural models have gained successes on information extraction...
09/05/2019 ∙ by Wenxuan Zhou, et al. ∙ 0 ∙ share

read it
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

Commonsense reasoning aims to empower machines with the human ability to...
09/04/2019 ∙ by Bill Yuchen Lin, et al. ∙ 22 ∙ share

read it
Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes

Official reports of hate crimes in the US are under-reported relative to...
09/04/2019 ∙ by Aida Mostafazadeh Davani, et al. ∙ 0 ∙ share

read it
Learning Dynamic Context Augmentation for Global Entity Linking

Despite of the recent success of collective entity linking (EL) methods,...
09/04/2019 ∙ by Xiyuan Yang, et al. ∙ 0 ∙ share

read it
Collaborative Policy Learning for Open Knowledge Graph Reasoning

In recent years, there has been a surge of interests in interpretable gr...
08/31/2019 ∙ by Cong Fu, et al. ∙ 19 ∙ share

read it
Hierarchical Text Classification with Reinforced Label Assignment

While existing hierarchical text classification (HTC) methods attempt to...
08/27/2019 ∙ by Yuning Mao, et al. ∙ 0 ∙ share

read it
Facet-Aware Evaluation for Extractive Text Summarization

Commonly adopted metrics for extractive text summarization like ROUGE fo...
08/27/2019 ∙ by Yuning Mao, et al. ∙ 0 ∙ share

read it
Raw-to-End Name Entity Recognition in Social Media

Taking word sequences as the input, typical named entity recognition (NE...
08/14/2019 ∙ by Liyuan Liu, et al. ∙ 0 ∙ share

read it
Adversarial Representation Learning on Large-Scale Bipartite Graphs

Graph representation on large-scale bipartite graphs is central for a va...
06/27/2019 ∙ by Chaoyang He, et al. ∙ 3 ∙ share

read it
Eliciting Knowledge from Experts:Automatic Transcript Parsing for Cognitive Task Analysis

Cognitive task analysis (CTA) is a type of analysis in applied psycholog...
06/26/2019 ∙ by Junyi Du, et al. ∙ 0 ∙ share

read it

Xiang Ren

Featured Co-authors