Search Results for author: Yu Su

Found 32 papers, 16 papers with code

ReasonBERT: Pre-trained to Reason with Distant Supervision

1 code implementation10 Sep 2021 Xiang Deng, Yu Su, Alyssa Lees, You Wu, Cong Yu, Huan Sun

We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts.

Question Answering

A Systematic Investigation of KB-Text Embedding Alignment at Scale

1 code implementation ACL 2021 Vardaan Pahuja, Yu Gu, Wenhu Chen, Mehdi Bahrami, Lei Liu, Wei-Peng Chen, Yu Su

Knowledge bases (KBs) and text often contain complementary knowledge: KBs store structured knowledge that can support long range reasoning, while text stores more comprehensive and timely knowledge in an unstructured way.

Link Prediction

Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing

no code implementations15 Jan 2021 Haoyang Bi, Haiping Ma, Zhenya Huang, Yu Yin, Qi Liu, Enhong Chen, Yu Su, Shijin Wang

In this paper, we study a novel model-agnostic CAT problem, where we aim to propose a flexible framework that can adapt to different cognitive models.

Active Learning

Explainable Recommendation Systems by Generalized Additive Models with Manifest and Latent Interactions

no code implementations15 Dec 2020 Yifeng Guo, Yu Su, Zebin Yang, Aijun Zhang

In this paper, we propose the explainable recommendation systems based on a generalized additive model with manifest and latent interactions (GAMMLI).

Additive models Recommendation Systems

Understanding How BERT Learns to Identify Edits

1 code implementation28 Nov 2020 Samuel Stevens, Yu Su

Pre-trained transformer language models such as BERT are ubiquitous in NLP research, leading to work on understanding how and why these models work.

Classification General Classification

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

1 code implementation16 Nov 2020 Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, Yu Su

To facilitate the development of KBQA models with stronger generalization, we construct and release a new large-scale, high-quality dataset with 64, 331 questions, GrailQA, and provide evaluation settings for all three levels of generalization.

Question Answering

Marcus' electron transfer rate revisited via a Rice-Ramsperger-Kassel-Marcus analogue: A unified formalism for linear and nonlinear solvation scenarios

no code implementations10 Oct 2020 Yao Wang, Yu Su, Rui-Xue Xu, Xiao Zheng, YiJing Yan

In this work, on the basis of the thermodynamic solvation potentials analysis, we reexamine Marcus' formula with respect to the Rice-Ramsperger-Kassel-Marcus (RRKM) theory.

Chemical Physics

KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation

1 code implementation EMNLP 2020 Wenhu Chen, Yu Su, Xifeng Yan, William Yang Wang

We propose a knowledge-grounded pre-training (KGPT), which consists of two parts, 1) a general knowledge-grounded generation model to generate knowledge-enriched text.

KG-to-Text Generation Transfer Learning

Document Classification for COVID-19 Literature

1 code implementation Findings of the Association for Computational Linguistics 2020 Bernal Jiménez Gutiérrez, Juncheng Zeng, Dong-dong Zhang, Ping Zhang, Yu Su

The global pandemic has made it more important than ever to quickly and accurately retrieve relevant scientific literature for effective consumption by researchers in a wide range of fields.

Classification Document Classification +1

An Imitation Game for Learning Semantic Parsers from User Interaction

1 code implementation EMNLP 2020 Ziyu Yao, Yiqi Tang, Wen-tau Yih, Huan Sun, Yu Su

Despite the widely successful applications, bootstrapping and fine-tuning semantic parsers are still a tedious process with challenges such as costly data annotation and privacy risks.

Imitation Learning Text-To-Sql

Logical Natural Language Generation from Open-Domain Tables

1 code implementation ACL 2020 Wenhu Chen, Jianshu Chen, Yu Su, Zhiyu Chen, William Yang Wang

To facilitate the study of the proposed logical NLG problem, we use the existing TabFact dataset \cite{chen2019tabfact} featured with a wide range of logical/symbolic inferences as our testbed, and propose new automatic metrics to evaluate the fidelity of generation models w. r. t.\ logical inference.

Text Generation

Decision Propagation Networks for Image Classification

no code implementations27 Nov 2019 Keke Tang, Peng Song, Yuexin Ma, Zhaoquan Gu, Yu Su, Zhihong Tian, Wenping Wang

High-level (e. g., semantic) features encoded in the latter layers of convolutional neural networks are extensively exploited for image classification, leaving low-level (e. g., color) features in the early layers underexplored.

Classification General Classification +1

Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study

2 code implementations IJCNLP 2019 Ziyu Yao, Yu Su, Huan Sun, Wen-tau Yih

As a promising paradigm, interactive semantic parsing has shown to improve both semantic parsing accuracy and user confidence in the results.

Semantic Parsing Text-To-Sql

EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction

1 code implementation7 Jun 2019 Qi Liu, Zhenya Huang, Yu Yin, Enhong Chen, Hui Xiong, Yu Su, Guoping Hu

In EERNN, we simply summarize each student's state into an integrated vector and trace it with a recurrent neural network, where we design a bidirectional LSTM to learn the encoding of each exercise's content.

Knowledge Tracing

Global Textual Relation Embedding for Relational Understanding

1 code implementation ACL 2019 Zhiyu Chen, Hanwen Zha, Honglei Liu, Wenhu Chen, Xifeng Yan, Yu Su

Pre-trained embeddings such as word embeddings and sentence embeddings are fundamental tools facilitating a wide range of downstream NLP tasks.

Action Classification Sentence Embeddings +1

QuesNet: A Unified Representation for Heterogeneous Test Questions

no code implementations27 May 2019 Yu Yin, Qi Liu, Zhenya Huang, Enhong Chen, Wei Tong, Shijin Wang, Yu Su

Then we propose a two-level hierarchical pre-training algorithm to learn better understanding of test questions in an unsupervised way.

Language Modelling

Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning

1 code implementation7 Nov 2018 Xin Wang, Jiawei Wu, Da Zhang, Yu Su, William Yang Wang

Although promising results have been achieved in video captioning, existing models are limited to the fixed inventory of activities in the training corpus, and do not generalize to open vocabulary scenarios.

Video Captioning

What It Takes to Achieve 100\% Condition Accuracy on WikiSQL

no code implementations EMNLP 2018 Semih Yavuz, Izzeddin Gur, Yu Su, Xifeng Yan

The SQL queries in WikiSQL are simple: Each involves one relation and does not have any join operation.

XL-NBT: A Cross-lingual Neural Belief Tracking Framework

1 code implementation EMNLP 2018 Wenhu Chen, Jianshu Chen, Yu Su, Xin Wang, Dong Yu, Xifeng Yan, William Yang Wang

Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data.

Transfer Learning

DialSQL: Dialogue Based Structured Query Generation

no code implementations ACL 2018 Izzeddin Gur, Semih Yavuz, Yu Su, Xifeng Yan

The recent advance in deep learning and semantic parsing has significantly improved the translation accuracy of natural language questions to structured queries.

Semantic Parsing

Aggregated Channels Network for Real-Time Pedestrian Detection

no code implementations1 Jan 2018 Farzin Ghorban, Javier Marín, Yu Su, Alessandro Colombo, Anton Kummert

Convolutional neural networks (CNNs) have demonstrated their superiority in numerous computer vision tasks, yet their computational cost results prohibitive for many real-time applications such as pedestrian detection which is usually performed on low-consumption hardware.

Pedestrian Detection

Recovering Question Answering Errors via Query Revision

no code implementations EMNLP 2017 Semih Yavuz, Izzeddin Gur, Yu Su, Xifeng Yan

The existing factoid QA systems often lack a post-inspection component that can help models recover from their own mistakes.

Question Answering Semantic Parsing

An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective

no code implementations EMNLP 2017 Jie Zhao, Yu Su, Ziyu Guan, Huan Sun

Given a question and a set of answer candidates, answer triggering determines whether the candidate set contains any correct answers.

Multiple Instance Learning Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.