An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks
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.
Code (1)
Tasks
Language ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training
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+2Revisiting Acceptability Judgements
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 AcceptabilityMachine Unlearning for Masked Diffusion Language Models
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
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 CaptioningA Set of Recommendations for Assessing Human-Machine Parity in Language Translation
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