Consistency regularization training for compositional generalization

Y Yin, J Zeng, Y Li, F Meng, J Zhou… - Proceedings of the 61st …, 2023 - aclanthology.org
Existing neural models have difficulty generalizing to unseen combinations of seen
components. To achieve compositional generalization, models are required to consistently …

Out-of-distribution generalization in natural language processing: Past, present, and future

L Yang, Y Song, X Ren, C Lyu, Y Wang… - Proceedings of the …, 2023 - aclanthology.org
Abstract Machine learning (ML) systems in natural language processing (NLP) face
significant challenges in generalizing to out-of-distribution (OOD) data, where the test …

Layer-Wise Representation Fusion for Compositional Generalization

Y Zheng, L Lin, S Li, Y Yuan, Z Lai, S Liu, B Fu… - Proceedings of the …, 2024 - ojs.aaai.org
Existing neural models are demonstrated to struggle with compositional generalization (CG),
ie, the ability to systematically generalize to unseen compositions of seen components. A …

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings

Y Jiang, X Zhou, M Bansal - arXiv preprint arXiv:2402.06492, 2024 - arxiv.org
Transformers generalize to novel compositions of structures and entities after being trained
on a complex dataset, but easily overfit on datasets of insufficient complexity. We observe …

Enhancing Neural Machine Translation with Semantic Units

L Huang, S Gu, Z Zhang, Y Feng - arXiv preprint arXiv:2310.11360, 2023 - arxiv.org
Conventional neural machine translation (NMT) models typically use subwords and words
as the basic units for model input and comprehension. However, complete words and …

Leveraging AI for Enhanced Semantic Interoperability in IoT: Insights from NER Models

MA Nemer, J Azar, A Makhoul… - … and Mobile Computing …, 2024 - ieeexplore.ieee.org
In Industry 4.0, achieving semantic interoperability is a significant problem due to the
complexities of current automation systems and the numerous standards involved. The study …

Effective Guidance in Zero-Shot Multilingual Translation via Multiple Language Prototypes

Y Zheng, L Lin, Y Yuan, X Shi - International Conference on Neural …, 2023 - Springer
In a multilingual neural machine translation model that fully shares parameters across all
languages, a popular approach is to use an artificial language token to guide translation into …

Inducing and Interpreting Compositionality in Neural NLP Models

Y Jiang - 2024 - search.proquest.com
Human intelligence demonstrates compositionality, the algebraic capacity that enables us to
understand and produce a potentially infinite number of novel combinations of known …