paper-with-me

홈 › Papers

Retrofitting Structure-aware Transformer Language Model for End Tasks

2020-09-16 · EMNLP 2020 11 · Hao Fei, Yafeng Ren, Donghong Ji

We consider retrofitting structure-aware Transformer-based language model for facilitating end tasks by proposing to exploit syntactic distance to encode both the phrasal constituency and dependency connection into the language model. A middle-layer structural learning strategy is leveraged for structure integration, accomplished with main semantic task training under multi-task learning scheme. Experimental results show that the retrofitted structure-aware Transformer language model achieves improved perplexity, meanwhile inducing accurate syntactic phrases. By performing structure-aware fine-tuning, our model achieves significant improvements for both semantic- and syntactic-dependent tasks.

📄 PDF Abstract BibTeX arXiv:2009.07408

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMulti-Task Learning

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting

2018-10-01 · EMNLP 2018 10 · Dirk Hovy, Christoph Purschke

Dialects are one of the main drivers of language variation, a major challenge for natural language processing tools. In most languages, dialects exist along a continuum, and are commonly discretized by combining the exte…

ClusteringDimensionality ReductionMachine TranslationRepresentation Learning

Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning

2023-10-29 · Sapan Shah, Sreedhar Reddy, Pushpak Bhattacharyya

We present a novel retrofitting method to induce emotion aspects into pre-trained language models (PLMs) such as BERT and RoBERTa. Our method updates pre-trained network weights using contrastive learning so that the tex…

Contrastive LearningFew-Shot LearningRetrievalSarcasm Detection+1

Expansional Retrofitting for Word Vector Enrichment

2018-08-22 · Hwiyeol Jo

Retrofitting techniques, which inject external resources into word representations, have compensated the weakness of distributed representations in semantic and relational knowledge between words. Implicitly retrofitting…

General Classificationtext-classificationText ClassificationWord Similarity

Differentiable Hierarchical Visual Tokenization

2025-11-04 · Marius Aasan, Martine Hjelkrem-Tan, Nico Catalano, Changkyu Choi 외 arxiv

Vision Transformers rely on fixed patch tokens that ignore the spatial and semantic structure of images. In this work, we introduce an end-to-end differentiable tokenizer that adapts to image content with pixel-level gra…

Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations

2017-08-01 · COLING 2018 8 · Benjamin J. Lengerich, Andrew L. Maas, Christopher Potts

Knowledge graphs are a versatile framework to encode richly structured data relationships, but it can be challenging to combine these graphs with unstructured data. Methods for retrofitting pre-trained entity representat…

Knowledge Graph CompletionKnowledge Graphs