top of page
Mt Badly, CA
August 17, 2019

"THE BEST WAY TO PREDICT THE FUTURE IS TO IMPLEMENT IT."

yuchen

eleanor

jiang

ABOUT ME

Eleanor is the founder&CEO of AIWaves Inc. She was a Ph.D. researcher in the Institute of Machine Learning at ETH Zürich, where she was supervised by Ryan Cotterell and Mrinmaya Sachan. She was in the Direct Doctorate program and also obtained her Master’s in Computer Science at ETH Zürich. Previously, she did her undergraduate studies at Zhejiang University's Chu Kochen Honors College and spent some time at UCLA, supervised by Kai-Wei Chang. Before founding AIWaves, she was fortunate enough to work at Microsoft Research Asia (MSRA) in Beijing and National Institute of Advanced Industrial Science and Technology (AIST) in Tokyo, collaborating with brilliant minds like Ming Zhou, Dongdong Zhang and Hiroya Takamura.

 

Her research is focused on Natural Language Processing and Machine Learning. At the moment, she is mainly interested in self-evolving agents and life-long personal AI (LPA). She is also a big fan of fun applications of natural language generation (novel generation, etc.). 

​

When Eleanor is not busy honing large language models, she indulges in hobbies like skiing, hiking, playing the piano, and learning new languages.

​

Drop her a line at eleanorjiang630@gmail.com if you're up for building a cool NLP product together.

​

​

​

  • pngwing.com
  • googlescholar
  • github
  • Twitter
  • LinkedIn
  • blog
About

NEWS

news

Publications

BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation.

Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Jian Yang, Haoyang Huang, Rico Sennrich, Mrinmaya Sachan, Ryan Cotterell, Ming Zhou. [NAACL 2022 oral]

Keywords: machine translation; evaluation

A Structured Span Selector.

Tianyu Liu, Yuchen Eleanor Jiang, Mrinmaya Sachan, Ryan Cotterell. [NAACL 2022 oral]

  • A structured model which directly learns to select an optimal set of spans for various span selection problems, e.g. coreference resolution and semantic role labeling. [pdf][code]

Keywords: coreference resolution; semantic role labeling

Autoregressive Structured Prediction with Language Models

Tianyu Liu, Yuchen Eleanor Jiang, Nicholas Monath, Mrinmaya Sachan, Ryan Cotterell. [EMNLP 2022 findings]

  • An approach to model structures as sequences of actions in an autoregressive manner with pretrained language models, allowing in-structure dependencies to be learned without any loss. [pdf][code]

Keywords: entity and relation extraction; coreference resolution; NER

Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference

Vilém Zouhar, Shehzaad Dhuliawala, Wangchunshu Zhou, Nico Daheim, Tom Kocmi, Yuchen Eleanor Jiang, Mrinmaya Sachan. [EACL 2023 oral]

  • We propose a better approach to leverage monolingual data to boost machine translation performance, i.e. leveraging the metric estimation task for pre-training a quality estimation model.  [pdf][code]

Keywords: machine translation; quality estimation

A Bilingual Parallel Corpus with Discourse Annotations

Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Ryan Cotterell, Mrinmaya Sachan. [EMNLP 2023 oral]

  • The BWB corpus consists of Chinese novels translated by experts into English, and the annotated test set is designed to probe the ability of machine translation systems to model various discourse phenomena. [pdf][dataset]

Keywords: machine translation; discourse; narrative

RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

Wangchunshu Zhou*, Yuchen Eleanor Jiang*, Peng Cui, Tiannan Wang, Zhenxin Xiao, Yifan Hou, Ryan Cotterell, Mrinmaya Sachan

  • RecurrentGPT can be used to produce arbitrarily long content (AIGC), and can also be used to generate interactive fiction that directly interacts with consumers (AI As Contents, AIAC). [pdf]

Keywords: long text generation

Agents: An Open-source Framework for Autonomous Language Agents

Wangchunshu Zhou*, Yuchen Eleanor Jiang*, Long Li*, Jialong Wu*, Tiannan Wang, Shi Qiu, Jintian Zhang, Jing Chen, Ruipu Wu, Shuai Wang, Shiding Zhu, Jiyu Chen, Wentao Zhang, Xiangru Tang, Ningyu Zhang, Huajun Chen, Peng Cui, Mrinmaya Sachan

  • The first SOP-based Agent framework. [pdf][code]

Keywords: Agent DevTool

Symbolic Learning Enables Self-Evolving Agents

Wangchunshu Zhou, Yixin Ou, Shengwei Ding, Long Li, Jialong Wu, Tiannan Wang, Jiamin Chen, Shuai Wang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, Yuchen Eleanor Jiang

  • We introduce agent symbolic learning, a systematic framework that enables language agents to optimize themselves on their own in a data-centric way using symbolic optimizers. [pdf][code]

Keywords: data-centric agents

Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References

Tianyi Tang, Hongyuan Lu, Yuchen Jiang, Haoyang Huang, Dongdong Zhang, Xin Zhao, Tom Kocmi, Furu Wei [ACL 2023 oral]

  • We presents a simple and effective method, named Div-Ref, to enhance existing evaluation benchmarks by enriching the number of references. [pdf][code]

Keywords: NLG, evaluation

Weaver: Foundation Models for Creative Writing

Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, Huilin Wang, Zhaowei Gao, Chunzhao Xie, Chuou Xu, Jihong Dai, Yibin Liu, Jialong Wu, Shengwei Ding, Long Li, Zhiwei Huang, Xinle Deng, Teng Yu, Gangan Ma, Han Xiao, Zixin Chen, Danjun Xiang, Yunxia Wang, Yuanyuan Zhu, Yi Xiao, Jing Wang, Yiru Wang, Siran Ding, Jiayang Huang, Jiayi Xu, Yilihamu Tayier, Zhenyu Hu, Yuan Gao, Chengfeng Zheng, Yueshu Ye, Yihang Li, Lei Wan, Xinyue Jiang, Yujie Wang, Siyu Cheng, Zhule Song, Xiangru Tang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, Yuchen Eleanor Jiang, Wangchunshu Zhou

Keywords: LLM training, vertical model [pdf]

publcations
bottom of page