paper-with-me

Papers

Rethinking Self-Attention: Towards Interpretability in Neural Parsing

2019-11-10 · Findings of the Association for Computational Linguistics 2020 · Khalil Mrini, Franck Dernoncourt, Quan Tran, Trung Bui, Walter Chang, Ndapa Nakashole

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent work has shown that model representations can benefit from label-specific information, while facilitating interpretation of predictions. We introduce the Label Attention Layer: a new form of self-attention where attention heads represent labels. We test our novel layer by running constituency and dependency parsing experiments and show our new model obtains new state-of-the-art results for both tasks on both the Penn Treebank (PTB) and Chinese Treebank. Additionally, our model requires fewer self-attention layers compared to existing work. Finally, we find that the Label Attention heads learn relations between syntactic categories and show pathways to analyze errors.

📄 PDF Abstract BibTeX arXiv:1911.03875

Code (2)

KhalilMrini/LAL-Parser 공식 구현 pytorch
kh8fb/LAL-Parser-Server pytorch

Tasks

Constituency ParsingDependency Parsing

Methods 이 논문이 사용한 방법론

Test 설명 없음
Interpretability 설명 없음

Similar Papers 제목 키워드 기반

UC Davis at SemEval-2019 Task 1: DAG Semantic Parsing with Attention-based Decoder

2019-06-01 · SEMEVAL 2019 6 · Dian Yu, Kenji Sagae

We present an encoder-decoder model for semantic parsing with UCCA SemEval 2019 Task 1. The encoder is a Bi-LSTM and the decoder uses recursive self-attention. The proposed model alleviates challenges and feature enginee…

DecoderFeature EngineeringSemantic Parsing

Unsupervised and Few-shot Parsing from Pretrained Language Models

2022-06-10 · Zhiyuan Zeng, Deyi Xiong

Pretrained language models are generally acknowledged to be able to encode syntax [Tenney et al., 2019, Jawahar et al., 2019, Hewitt and Manning, 2019]. In this article, we propose UPOA, an Unsupervised constituent Parsi…

Language Modelling

SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

2023-12-04 · Feng Wang, Jieru Mei, Alan Yuille

Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However…

SegmentationSemantic Segmentationzero-shot-classificationZero-Shot Learning+1

An Imitation Learning Approach to Unsupervised Parsing

2019-06-05 · ACL 2019 7 · Bowen Li, Lili Mou, Frank Keller

Recently, there has been an increasing interest in unsupervised parsers that optimize semantically oriented objectives, typically using reinforcement learning. Unfortunately, the learned trees often do not match actual s…

Imitation LearningLanguage ModelingLanguage ModellingNatural Language Inference+1

Multi-Scale Dual-Branch Fully Convolutional Network for Hand Parsing

2019-05-24 · Yang Lu, Xiaohui Liang, Frederick W. B. Li

Recently, fully convolutional neural networks (FCNs) have shown significant performance in image parsing, including scene parsing and object parsing. Different from generic object parsing tasks, hand parsing is more chal…

Multi-class ClassificationScene Parsing