Xixi Zhou — accepted AI-conference papers

2024

Inversive-Reasoning Augmentation for Natural Language Inference

Xixi Zhou, Xin Jie, Sheng Zhou, Keyue Shi, Zhi Yu, Jiajun Bu +1

ICASSP 2024accepted

Natural language inference (NLI) aims to infer the relationship between two texts: premise and hypothesis. However, many existing methods overlook the problem of overestimation of model performance due to superficial correlation biases in NLI datasets. We study this problem and find that most curren…

Cited by 0 Source ↗Scholar ↗

2024

Matching Varying-Length Texts via Topic-Informed and Decoupled Sentence Embeddings

Xixi Zhou, Chunbin Gu, Xin Jie, Jiajun Bu, Haishuai Wang

NAACL 2024findings

Measuring semantic similarity between texts is a crucial task in natural language processing. While existing semantic text matching focuses on pairs of similar-length sequences, matching texts with non-comparable lengths has broader applications in specific domains, such as comparing professional do…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗