About

Hi I'm Viet Lai.

I am looking for internship opportunity for Summer 2022. Please drop me an email if you are interested.

I am a PhD student at Department of Computer and Information Sciences at University of Oregon. I am working with Thien Huu Nguyen in UofO Natural Language Processing group.

I obtained my M.S. degree in Computer Science from Japan Advanced Institute of Science and Technology (with Minh Le Nguyen) and bachelor degree in Computer Science from Posts and Telecommunications Institute of Science and Technology.

I interned at Adobe Research in Summer 2021 with Franck Dernoncourt. I work in projects involving video transcript understanding including: punctuation restoration, subtitle segmentation, and chitchat detection.

My research involves understanding of human languages that can be applied in computers to automate human-language cognitive tasks. Specifically, I focus on extracting and structurizing information from massive written text accross domains. My research topic lies in the intersection of Event Detection (ED) and Few-Shot Learning (FSL).

Contact me

Email

vietl AT cs . uoregon . edu

Office

343 Deschute Hall, University of Oregon, 1477 E 13th Ave, Eugene, OR 97403, USA

Other

Publications

2021

  • Learning Prototype Representations Across Few-Shot Tasks for Event Detection

    Viet Dac Lai, Franck Dernoncourt, and Thien Huu Nguyen | EMNLP 2021 | To appear soon

  • Event Extraction from Historical Texts: A New Dataset for Black Rebellions

    Viet Dac Lai, Minh Nguyen, Heidi Kaufman, and Thien Huu Nguyen | ACL-IJCNLP 2021 | pdf

  • Unleash GPT-2 Power for Event Detection

    Amir Pouran Ben Veyseh, Viet Dac Lai, Franck Dernoncourt and Thien Huu Nguyen | ACL-IJCNLP 2021 | pdf

  • Graph Learning Regularization and Transfer Learning for Few-Shot Event Detection

    Viet Dac Lai, Minh Nguyen, Thien Huu Nguyen and Franck Dernoncourt | SIGIR 2021 | pdf

  • Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing

    Minh Van Ngo, Viet Dac Lai, Amir Pouran Ben Veyseh and Thien Huu Nguyen | EACL 2021 | pdf | Demo | Docs

  • Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks

    Minh Van Nguyen, Viet Dac Lai and Thien Huu Nguyen | NAACL-HLT 2021 | pdf

2020

  • Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks

    Viet Dac Lai, Tuan Ngo Nguyen and Thien Huu Nguyen | EMNLP 2020 | pdf

  • Extensively Matching for Few-shot Learning Event Detection

    Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen | NUSE@ACL 2020 | pdf

  • Exploiting the Matching Information in the Support Set for Few Shot Event Classification

    Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen | PAKDD 2020 | pdf

2019

  • Extending Event Detection to New Types with Learning from Keywords

    Viet Dac Lai, Thien Huu Nguyen | W-NUT@EMNLP 2019 | pdf

2018 and before

  • TSix: A Human-involved-creation Dataset for Tweet Summarization

    Minh-Tien Nguyen, Viet Dac Lai, Huy-Tien Nguyen and Minh-Le Nguyen | LREC 2018 | pdf

  • Deletion-based sentence compression using Bi-enc-dec LSTM

    Viet Dac Lai, Nguyen Truong Son, Nguyen Le Minh | PACLING 2017 | pdf

  • VSoLSCSum: Building a vietnamese sentence-comment dataset for social context summarization

    Minh-Tien Nguyen, Viet Dac Lai, Phong-Khac Do, Duc-Vu Tran, Minh-Le Nguyen | ALR@COLING 2016 | pdf

Awards

Outstanding demo paper award, EACL 2021

Best Graduate Teaching Assitant, Dept. of Computer and Information Science, University of Oregon, 2021

Softwares

FourIE: A jointly trained model for Information Extraction. Demo is available here.


Trankit: A multilingual toolkit for fundamental taskse such as tokenization. Demo is available here.

-->