Deng Cai

Stable Learning via Self-supervised Invariant Risk Minimization

2020 · arXiv (Cornell University)

Empirical Risk Minimization based methods are based on the consistency hypothesis that all data samples are generated i.i.d. However, this hypothesis cannot hold in many real-world applications. Consequently, simply minimizing training loss can lead the …

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems. Despite their success, existing methods often formulate this task as a cascaded generation problem which can lead to error accumulation across different …

DocBench: A Benchmark for Evaluating LLM-based Document Reading Systems

2025

Anni Zou, Wenhao Yu, Hongming Zhang, Kaixin Ma, Deng Cai, Zhuosheng Zhang, Hai Zhao, Dong Yu. Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing. 2025.

Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst

2025

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought.These longer intermediate reasoning rationales embody various meta-reasoning skills in …

MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension

2017 · arXiv (Cornell University)

Machine comprehension(MC) style question answering is a representative problem in natural language processing. Previous methods rarely spend time on the improvement of encoding layer, especially the embedding of syntactic information and name entity of the …

What to Do Next: Modeling User Behaviors by Time-LSTM

2017

Recently, Recurrent Neural Network (RNN) solutions for recommender systems (RS) are becoming increasingly popular. The insight is that, there exist some intrinsic patterns in the sequence of users' actions, and RNN has been proved to …

Dialogue Act Recognition via CRF-Attentive Structured Network

2018

Dialogue Act Recognition (DAR) is a challenging problem in dialogue interpretation, which aims to associate semantic labels to utterances and characterize the speaker's intention. Currently, many existing approaches formulate the DAR problem ranging from multi-classification …

Graph Transformer for Graph-to-Sequence Learning

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

The dominant graph-to-sequence transduction models employ graph neural networks for graph representation learning, where the structural information is reflected by the receptive field of neurons. Unlike graph neural networks that restrict the information exchange between …