Ya Guo


2023

pdf bib
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
Chong Zhang | Ya Guo | Yi Tu | Huan Chen | Jinyang Tang | Huijia Zhu | Qi Zhang | Tao Gui
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs), in which named entity recognition (NER) is treated as a sequence-labeling task of predicting the BIO entity tags for tokens, following the typical setting of NLP. However, BIO-tagging scheme relies on the correct order of model inputs, which is not guaranteed in real-world NER on scanned VrDs where text are recognized and arranged by OCR systems. Such reading order issue hinders the accurate marking of entities by BIO-tagging scheme, making it impossible for sequence-labeling methods to predict correct named entities. To address the reading order issue, we introduce Token Path Prediction (TPP), a simple prediction head to predict entity mentions as token sequences within documents. Alternative to token classification, TPP models the document layout as a complete directed graph of tokens, and predicts token paths within the graph as entities. For better evaluation of VrD-NER systems, we also propose two revised benchmark datasets of NER on scanned documents which can reflect real-world scenarios. Experiment results demonstrate the effectiveness of our method, and suggest its potential to be a universal solution to various information extraction tasks on documents.

pdf bib
LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding
Yi Tu | Ya Guo | Huan Chen | Jinyang Tang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Visually-rich Document Understanding (VrDU) has attracted much research attention over the past years. Pre-trained models on a large number of document images with transformer-based backbones have led to significant performance gains in this field. The major challenge is how to fusion the different modalities (text, layout, and image) of the documents in a unified model with different pre-training tasks. This paper focuses on improving text-layout interactions and proposes a novel multi-modal pre-training model, LayoutMask. LayoutMask uses local 1D position, instead of global 1D position, as layout input and has two pre-training objectives: (1) Masked Language Modeling: predicting masked tokens with two novel masking strategies; (2) Masked Position Modeling: predicting masked 2D positions to improve layout representation learning. LayoutMask can enhance the interactions between text and layout modalities in a unified model and produce adaptive and robust multi-modal representations for downstream tasks. Experimental results show that our proposed method can achieve state-of-the-art results on a wide variety of VrDU problems, including form understanding, receipt understanding, and document image classification.

2016

pdf bib
Generating Abbreviations for Chinese Named Entities Using Recurrent Neural Network with Dynamic Dictionary
Qi Zhang | Jin Qian | Ya Guo | Yaqian Zhou | Xuanjing Huang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2014

pdf bib
A Generative Model for Identifying Target Companies of Microblogs
Yeyun Gong | Yaqian Zhou | Ya Guo | Qi Zhang | Xuanjing Huang
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers