Rule Augmented Unsupervised Constituency Parsing
| Autor: | Rishabh Iyer, Anshul Nasery, Atul Sahay, Ganesh Ramakrishnan, Ayush Maheshwari |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Grammar rules Computer Science - Machine Learning Computer Science - Computation and Language Parsing Source code Grammar Computer science business.industry media_common.quotation_subject Base (topology) computer.software_genre Machine Learning (cs.LG) TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES Reinforcement learning Artificial intelligence business Computation and Language (cs.CL) computer Natural language processing media_common |
| Zdroj: | ACL/IJCNLP (Findings) |
| DOI: | 10.18653/v1/2021.findings-acl.436 |
| Popis: | Recently, unsupervised parsing of syntactic trees has gained considerable attention. A prototypical approach to such unsupervised parsing employs reinforcement learning and auto-encoders. However, no mechanism ensures that the learnt model leverages the well-understood language grammar. We propose an approach that utilizes very generic linguistic knowledge of the language present in the form of syntactic rules, thus inducing better syntactic structures. We introduce a novel formulation that takes advantage of the syntactic grammar rules and is independent of the base system. We achieve new state-of-the-art results on two benchmarks datasets, MNLI and WSJ. The source code of the paper is available at https://github.com/anshuln/Diora_with_rules. Comment: Accepted at Findings of ACL 2021. 10 Pages, 5 Tables, 2 Figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|