Shuohang Wang

A Compare-Aggregate Model for Matching Text Sequences

2016 · arXiv (Cornell University)

Many NLP tasks including machine comprehension, answer selection and text entailment require the comparison between sequences. Matching the important units between sequences is a key to solve these problems. In this paper, we present a …

Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives

2019 · arXiv (Cornell University)

This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse …

T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack

2019 · arXiv (Cornell University)

Adversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Though raised great concerns, such adversarial attacks can be leveraged to estimate the …

InfoBERT: Improving Robustness of Language Models from An Information\n Theoretic Perspective

2020 · arXiv (Cornell University)

Large-scale language models such as BERT have achieved state-of-the-art\nperformance across a wide range of NLP tasks. Recent studies, however, show\nthat such BERT-based models are vulnerable facing the threats of textual\nadversarial attacks. We aim to address …

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment

2023 · arXiv (Cornell University)

The quality of texts generated by natural language generation (NLG) systems is hard to measure automatically. Conventional reference-based metrics, such as BLEU and ROUGE, have been shown to have relatively low correlation with human judgments, …

APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning

2023

Soumya Sanyal, Yichong Xu, Shuohang Wang, Ziyi Yang, Reid Pryzant, Wenhao Yu, Chenguang Zhu, Xiang Ren. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy

2024 · arXiv (Cornell University)

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly with sequence length and …

Machine Comprehension Using Match-LSTM and Answer Pointer

2016 · arXiv (Cornell University)

Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans …

R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering

2017 · arXiv (Cornell University)

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et …

Learning Natural Language Inference with LSTM

2016

Natural language inference (NLI) is a fundamentally important task in natural language processing that has many applications. The recently released Stanford Natural Language Inference (SNLI) corpus has made it possible to develop and evaluate learning-centered …