Xian-Ling Mao

Complicated Table Structure Recognition

2019 · arXiv (Cornell University)

The task of table structure recognition aims to recognize the internal structure of a table, which is a key step to make machines understand tables. Currently, there are lots of studies on this task for …

Incorporating Domain Knowledge into Text Classification Diagnosis in Customer Service Dialogue Field

2021 · Journal of Physics Conference Series

Abstract The customer service dialogue process is an important way for consumers to communicate with manufacturers. In order to enhance the consumer experience as well as to assist the staff, we build a knowledge base …

Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment

2021 · arXiv (Cornell University)

The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task. Specifically, the model first …

Momentum Decoding: Open-ended Text Generation As Graph Exploration

2022 · arXiv (Cornell University)

Open-ended text generation with autoregressive language models (LMs) is one of the core tasks in natural language processing. However, maximization-based decoding methods (e.g., greedy/beam search) often lead to the degeneration problem, i.e., the generated text …

SNER-CS: Self-training Named Entity Recognition in Computer Science

2023 · Journal of Physics Conference Series

Abstract As the number of scientific publications grows, especially in computer science domain (CS), it is important to extract scientific entities from a large number of CS publications. Distantly supervised methods, generating distantly annotated training …

Global Context Enhanced Graph Neural Networks for Session-based Recommendation

2020

Session-based recommendation (SBR) is a challenging task, which aims at recommending items based on anonymous behavior sequences. Almost all the existing solutions for SBR model user preference only based on the current session without exploiting …