Jiacheng Xu

Jiacheng Xu

Auto-generated profile, based on publicly available information

Jiacheng Xu

Department of Computer Science The University of Texas at Austin

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2021
Verified
Conference Paper
Open access
PDF file
AGAditya Gupta
Aditya Gupta
JXJiacheng Xu
Jiacheng Xu
SUShyam Upadhyay
Shyam Upadhyay
DYDiyi Yang
Diyi Yang
MFManaal Faruqui
Manaal Faruqui
Aditya Gupta, Jiacheng Xu, Shyam Upadhyay, Diyi Yang, Manaal Faruqui. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.

1 January 2023
Verified
Conference Paper
Open access
PDF file
JXJiacheng Xu
Jiacheng Xu
CXCaiming Xiong
Caiming Xiong
SSSilvio Savarese
Silvio Savarese
YZYingbo Zhou
Yingbo Zhou
Jiacheng Xu, Caiming Xiong, Silvio Savarese, Yingbo Zhou. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

9 September 2019 in arXiv
Verified
Preprint
Open access
PDF file
JXJiacheng Xu
Jiacheng Xu
GDGreg Durrett
Greg Durrett
Recent neural network approaches to summarization are largely either selection-based extraction or generation-based abstraction. In this work, we present a neural model for single-document summarization based on joint extraction and syntactic compression. Our model chooses sentences from the document, identifies possible compressions based on constituency parses, and scores those compressions with a neural model to produce the final summary. For learning, we construct oracle extractive-compressive summaries, then learn both of our components jointly with this supervision. Experimental results on the CNN/Daily Mail and New York Times datasets show that our model achieves strong performance (comparable to state-of-the-art systems) as evaluated by ROUGE. Moreover, our approach outperforms an off-the-shelf compression module, and human and manual evaluation shows that our model's output generally remains grammatical.

1 January 2023
Verified
Conference Paper
Open access
PDF file
PSPrasann Singhal
Prasann Singhal
JXJiacheng Xu
Jiacheng Xu
XYXi Ye
Xi Ye
GDGreg Durrett
Greg Durrett
Prasann Singhal, Jiacheng Xu, Xi Ye, Greg Durrett. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

1 January 2021
Verified
Conference Paper
Open access
PDF file
GDGreg Durrett
Greg Durrett
JCJifan Chen
Jifan Chen
SDShrey Desai
Shrey Desai
TGTanya Goyal
Tanya Goyal
LKLucas Kabela
Lucas Kabela
JXJiacheng Xu
Jiacheng Xu
Greg Durrett, Jifan Chen, Shrey Desai, Tanya Goyal, Lucas Kabela, Yasumasa Onoe, Jiacheng Xu. Proceedings of the Fifth Workshop on Teaching NLP. 2021.

12 October 2018 in arXiv
Verified
Preprint
Open access
PDF file
JXJiacheng Xu
Jiacheng Xu
GDGreg Durrett
Greg Durrett
A hallmark of variational autoencoders (VAEs) for text processing is their combination of powerful encoder-decoder models, such as LSTMs, with simple latent distributions, typically multivariate Gaussians. These models pose a difficult optimization problem: there is an especially bad local optimum where the variational posterior always equals the prior and the model does not use the latent variable at all, a kind of "collapse" which is encouraged by the KL divergence term of the objective. In this work, we experiment with another choice of latent distribution, namely the von Mises-Fisher (vMF) distribution, which places mass on the surface of the unit hypersphere. With this choice of prior and posterior, the KL divergence term now only depends on the variance of the vMF distribution, giving us the ability to treat it as a fixed hyperparameter. We show that doing so not only averts the KL collapse, but consistently gives better likelihoods than Gaussians across a range of modeling conditions, including recurrent language modeling and bag-of-words document modeling. An analysis of the properties of our vMF representations shows that they learn richer and more nuanced structures in their latent representations than their Gaussian counterparts.