Enhancing Language Representation with Constructional Information for Natural Language Understanding
arXiv:2306.02819 · doi:10.18653/v1/2023.acl-long.258
Abstract
Natural language understanding (NLU) is an essential branch of natural language processing, which relies on representations generated by pre-trained language models (PLMs). However, PLMs primarily focus on acquiring lexico-semantic information, while they may be unable to adequately handle the meaning of constructions. To address this issue, we introduce construction grammar (CxG), which highlights the pairings of form and meaning, to enrich language representation. We adopt usage-based construction grammar as the basis of our work, which is highly compatible with statistical models such as PLMs. Then a HyCxG framework is proposed to enhance language representation through a three-stage solution. First, all constructions are extracted from sentences via a slot-constraints approach. As constructions can overlap with each other, bringing redundancy and imbalance, we formulate the conditional max coverage problem for selecting the discriminative constructions. Finally, we propose a relational hypergraph attention network to acquire representation from constructional information by capturing high-order word interactions among constructions. Extensive experiments demonstrate the superiority of the proposed model on a variety of NLU tasks.
arXiv commentLong paper, accepted at the ACL 2023
References in corpus (5)
- Decoupled Weight Decay Regularization
- Learn from Structural Scope: Improving Aspect-Level Sentiment Analysis with Hybrid Graph Convolutional Networks
- Construction Grammar Provides Unique Insight into Neural Language Models
- Stability of Syntactic Dialect Classification Over Space and Time
- Exploring the Constructicon: Linguistic Analysis of a Computational CxG