Infusing Finetuning with Semantic Dependencies
arXiv:2012.05395 · doi:10.1162/tacl_a_00363
Abstract
For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained" on large unannotated corpora: performance on application-inspired benchmarks (Peters et al., 2018, inter alia), and the emergence of syntactic abstractions in those representations (Tenney et al., 2019, inter alia). On the other hand, the lack of grounded supervision calls into question how well these representations can ever capture meaning (Bender and Koller, 2020). We apply novel probes to recent language models -- specifically focusing on predicate-argument structure as operationalized by semantic dependencies (Ivanova et al., 2012) -- and find that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning, yielding benefits to natural language understanding (NLU) tasks in the GLUE benchmark. This approach demonstrates the potential for general-purpose (rather than task-specific) linguistic supervision, above and beyond conventional pretraining and finetuning. Several diagnostics help to localize the benefits of our approach.
arXiv commentTACL 2021
References in corpus (5)
- Enhanced LSTM for Natural Language Inference
- SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation
- SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
- Question Answering on Freebase via Relation Extraction and Textual Evidence
- Exploring and Predicting Transferability across NLP Tasks