Paper Reading AI Learner

Superbizarre Is Not Superb: Improving BERT's Interpretations of Complex Words with Derivational Morphology

2021-01-02 08:36:48
Valentin Hofmann, Janet B. Pierrehumbert, Hinrich Schütze
arXiv_CL
       
Abstract

How does the input segmentation of pretrained language models (PLMs) affect their generalization capabilities? We present the first study investigating this question, taking BERT as the example PLM and focusing on the semantic representations of derivationally complex words. We show that PLMs can be interpreted as serial dual-route models, i.e., the meanings of complex words are either stored or else need to be computed from the subwords, which implies that maximally meaningful input tokens should allow for the best generalization on new words. This hypothesis is confirmed by a series of semantic probing tasks on which derivational segmentation consistently outperforms BERT's WordPiece segmentation by a large margin. Our results suggest that the generalization capabilities of PLMs could be further improved if a morphologically-informed vocabulary of input tokens were used.

Abstract (translated)

URL

https://arxiv.org/abs/2101.00403

PDF

https://arxiv.org/pdf/2101.00403.pdf

Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot