Ji Wu


2022

pdf bib
Table-based Fact Verification with Self-adaptive Mixture of Experts
Yuxuan Zhou | Xien Liu | Kaiyin Zhou | Ji Wu
Findings of the Association for Computational Linguistics: ACL 2022

The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem. It inherently requires informative reasoning over natural language together with different numerical and logical reasoning on tables (e.g., count, superlative, comparative). Considering that, we exploit mixture-of-experts and present in this paper a new method: Self-adaptive Mixture-of-Experts Network (SaMoE). Specifically, we have developed a mixture-of-experts neural network to recognize and execute different types of reasoning—the network is composed of multiple experts, each handling a specific part of the semantics for reasoning, whereas a management module is applied to decide the contribution of each expert network to the verification result. A self-adaptive method is developed to teach the management module combining results of different experts more efficiently without external knowledge. The experimental results illustrate that our framework achieves 85.1% accuracy on the benchmark dataset TabFact, comparable with the previous state-of-the-art models. We hope our framework can serve as a new baseline for table-based verification. Our code is available at https://github.com/THUMLP/SaMoE.

2021

pdf bib
THiFly_Queens at SemEval-2021 Task 9: Two-stage Statement Verification with Adaptive Ensembling and Slot-based Operation
Yuxuan Zhou | Kaiyin Zhou | Xien Liu | Ji Wu | Xiaodan Zhu
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

This paper describes our system for verifying statements with tables at SemEval-2021 Task 9. We developed a two-stage verifying system based on the latest table-based pre-trained model GraPPa. Multiple networks are devised to verify different types of statements in the competition dataset and an adaptive model ensembling technique is applied to ensemble models in both stages. A statement-slot-based symbolic operation module is also used in our system to further improve the performance and stability of the system. Our model achieves second place in the 3-way classification and fourth place in the 2-way classification evaluation. Several ablation experiments show the effectiveness of different modules proposed in this paper.

2019

pdf bib
Delta Embedding Learning
Xiao Zhang | Ji Wu | Dejing Dou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Unsupervised word embeddings have become a popular approach of word representation in NLP tasks. However there are limitations to the semantics represented by unsupervised embeddings, and inadequate fine-tuning of embeddings can lead to suboptimal performance. We propose a novel learning technique called Delta Embedding Learning, which can be applied to general NLP tasks to improve performance by optimized tuning of the word embeddings. A structured regularization is applied to the embeddings to ensure they are tuned in an incremental way. As a result, the tuned word embeddings become better word representations by absorbing semantic information from supervision without “forgetting.” We apply the method to various NLP tasks and see a consistent improvement in performance. Evaluation also confirms the tuned word embeddings have better semantic properties.

2016

pdf bib
Hidden Softmax Sequence Model for Dialogue Structure Analysis
Zhiyang He | Xien Liu | Ping Lv | Ji Wu
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)