1 code implementation • 7 Dec 2017 • Han He, Lei Wu, Hua Yan, Zhimin Gao, Yi Feng, George Townsend
We present a simple yet elegant solution to train a single joint model on multi-criteria corpora for Chinese Word Segmentation (CWS).
1 code implementation • 23 Dec 2017 • Han He, Lei Wu, Xiaokun Yang, Hua Yan, Zhimin Gao, Yi Feng, George Townsend
To build a concrete study and substantiate the efficiency of our neural architecture, we take Chinese Word Segmentation as a research case example.
1 code implementation • 14 Aug 2019 • Han He, Jinho D. Choi
This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT.
no code implementations • 2 Nov 2019 • Changmao Li, Han He, Yunze Hao, Caleb Ziems
This report assesses different machine learning approaches to 10-year survival prediction of breast cancer patients.
no code implementations • WS 2020 • Tae Hwan Oh, Ji Yoon Han, Hyonsu Choe, Seokwon Park, Han He, Jinho D. Choi, Na-Rae Han, Jena D. Hwang, Hansaem Kim
In this paper, we first open on important issues regarding the Penn Korean Universal Treebank (PKT-UD) and address these issues by revising the entire corpus manually with the aim of producing cleaner UD annotations that are more faithful to Korean grammar.
no code implementations • WS 2020 • Han He, Jinho D. Choi
Our results show that models using the multilingual encoder outperform ones using the language specific encoders for most languages.
no code implementations • 6 Aug 2020 • Leevi Raivio, Han He, Johanna Virkki, Heikki Huttunen
The data is collected sequentially, such that we record both the stroke order and the resulting bitmap.
1 code implementation • ACL (IWPT) 2021 • Han He, Jinho D. Choi
Coupled with biaffine decoders, transformers have been effectively adapted to text-to-graph transduction and achieved state-of-the-art performance on AMR parsing.
Ranked #18 on AMR Parsing on LDC2017T10
1 code implementation • 8 Sep 2021 • Han He, Liyan Xu, Jinho D. Choi
We introduce ELIT, the Emory Language and Information Toolkit, which is a comprehensive NLP framework providing transformer-based end-to-end models for core tasks with a special focus on memory efficiency while maintaining state-of-the-art accuracy and speed.
1 code implementation • EMNLP 2021 • Han He, Jinho D. Choi
Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or not it would perform as well on tasks that are distinct in nature.
no code implementations • 31 Oct 2021 • Sarah E. Finch, James D. Finch, Daniil Huryn, William Hutsell, Xiaoyuan Huang, Han He, Jinho D. Choi
In the third and final stage, our bot selects a small subset of predicates and translates them into an English response.
1 code implementation • 4 Dec 2022 • Han He, Song Feng, Daniele Bonadiman, Yi Zhang, Saab Mansour
DataFlow has been emerging as a new paradigm for building task-oriented chatbots due to its expressive semantic representations of the dialogue tasks.
1 code implementation • 5 Feb 2023 • Han He, Jinho D. Choi
Sequence-to-Sequence (S2S) models have achieved remarkable success on various text generation tasks.
no code implementations • 12 Sep 2023 • Lydia Feng, Gregor Williamson, Han He, Jinho D. Choi
Despite its strengths, AMR is not easily applied to languages or domains without predefined semantic frames, and its use of numbered arguments results in semantic role labels, which are not directly interpretable and are semantically overloaded for parsers.