paper-with-me

Papers

An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks

2022-10-24 · Changlong Yu, Tianyi Xiao, Lingpeng Kong, Yangqiu Song, Wilfred Ng

Though linguistic knowledge emerges during large-scale language model pretraining, recent work attempt to explicitly incorporate human-defined linguistic priors into task-specific fine-tuning. Infusing language models with syntactic or semantic knowledge from parsers has shown improvements on many language understanding tasks. To further investigate the effectiveness of structural linguistic priors, we conduct empirical study of replacing parsed graphs or trees with trivial ones (rarely carrying linguistic knowledge e.g., balanced tree) for tasks in the GLUE benchmark. Encoding with trivial graphs achieves competitive or even better performance in fully-supervised and few-shot settings. It reveals that the gains might not be significantly attributed to explicit linguistic priors but rather to more feature interactions brought by fusion layers. Hence we call for attention to using trivial graphs as necessary baselines to design advanced knowledge fusion methods in the future.

📄 PDF Abstract BibTeX arXiv:2210.13002

Code (1)

hkust-knowcomp/revisit-nlu-linguistic-knowledge 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training

2022-10-11 · Taolin Zhang, Junwei DOng, Jianing Wang, Chengyu Wang 외

Recently, knowledge-enhanced pre-trained language models (KEPLMs) improve context-aware representations via learning from structured relations in knowledge graphs, and/or linguistic knowledge from syntactic or dependency…

GPUKnowledge GraphsLanguage ModelingLanguage Modelling+2

Revisiting Acceptability Judgements

2023-05-23 · Hai Hu, Ziyin Zhang, Weifang Huang, Jackie Yan-Ki Lai 외

In this work, we revisit linguistic acceptability in the context of large language models. We introduce CoLAC - Corpus of Linguistic Acceptability in Chinese, the first large-scale acceptability dataset for a non-Indo-Eu…

Cross-Lingual TransferLinguistic Acceptability

Machine Unlearning for Masked Diffusion Language Models

2026-05-18 · Georu Lee, Seungwon Jeong, Hoki Kim, Jinseong Park 외 arxiv

Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models, which generate text sequentially, MDLM…

Linguistically Informed Multimodal Fusion for Vietnamese Scene-Text Image Captioning: Dataset, Graph Framework, and Phonological Attention

2026-04-30 · Nhi Ngoc-Yen Nguyen, Anh-Duc Nguyen, Nghia Hieu Nguyen, Kiet Van Nguyen 외 arxiv

Scene-text image captioning requires fusing three information streams -- visual features, OCR-detected text, and linguistic knowledge -- to generate descriptions that faithfully integrate text visible in images. Existing…

Image Captioning

A Set of Recommendations for Assessing Human-Machine Parity in Language Translation

2020-04-03 · Samuel Läubli, Sheila Castilho, Graham Neubig, Rico Sennrich 외

The quality of machine translation has increased remarkably over the past years, to the degree that it was found to be indistinguishable from professional human translation in a number of empirical investigations. We rea…

Machine TranslationTranslation