Ying Su


2022

pdf bib
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation
Ying Su | Zihao Wang | Tianqing Fang | Hongming Zhang | Yangqiu Song | Tong Zhang
Findings of the Association for Computational Linguistics: EMNLP 2022

Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning. In this paper, we propose to learn commonsense knowledge representation by MICO, a Multi-alternative contrastIve learning framework on COmmonsense knowledge graphs (MICO). MICO generates the commonsense knowledge representation by contextual interaction between entity nodes and relations with multi-alternative contrastive learning. In MICO, the head and tail entities in an (h,r,t) knowledge triple are converted to two relation-aware sequence pairs (a premise and an alternative) in the form of natural language. Semantic representations generated by MICO can benefit the following two tasks by simply comparing the similarity score between the representations: 1) zero-shot commonsense question answering tasks; 2) inductive commonsense knowledge graph completion tasks. Extensive experiments show the effectiveness of our method.

pdf bib
Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting
Ying Su | Hongming Zhang | Yangqiu Song | Tong Zhang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Word sense disambiguation (WSD) is a crucial problem in the natural language processing (NLP) community. Current methods achieve decent performance by utilizing supervised learning and large pre-trained language models. However, the imbalanced training dataset leads to poor performance on rare senses and zero-shot senses. There are more training instances and senses for words with top frequency ranks than those with low frequency ranks in the training dataset. We investigate the statistical relation between word frequency rank and word sense number distribution. Based on the relation, we propose a Z-reweighting method on the word level to adjust the training on the imbalanced dataset. The experiments show that the Z-reweighting strategy achieves performance gain on the standard English all words WSD benchmark. Moreover, the strategy can help models generalize better on rare and zero-shot senses.

pdf bib
Multilingual Word Sense Disambiguation with Unified Sense Representation
Ying Su | Hongming Zhang | Yangqiu Song | Tong Zhang
Proceedings of the 29th International Conference on Computational Linguistics

As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the fine-grained semantics of words under specific contexts. Benefited from the large-scale annotation, current WSD systems have achieved impressive performances in English by combining supervised learning with lexical knowledge. However, such success is hard to be replicated in other languages, where we only have very limited annotations. In this paper, based on that the multilingual lexicon BabelNet describing the same set of concepts across languages, we propose to build knowledge and supervised based Multilingual Word Sense Disambiguation (MWSD) systems. We build unified sense representations for multiple languages and address the annotation scarcity problem for MWSD by transferring annotations from rich sourced languages. With the unified sense representations, annotations from multiple languages can be jointly trained to benefit the MWSD tasks. Evaluations of SemEval-13 and SemEval-15 datasets demonstrate the effectiveness of our methodology.

2005

pdf bib
Design and Development of a Speech-driven Control for a In-car Personal Navigation System
Ying Su | Tao Bai | Catherine I. Watson
Proceedings of the Australasian Language Technology Workshop 2005