paper-with-me

Papers

Structured Self-Attention Weights Encode Semantics in Sentiment Analysis

2020-10-10 · Zhengxuan Wu, Thanh-Son Nguyen, Desmond C. Ong

Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer encodes syntactic information; Here, we show that self-attention scores encode semantics by considering sentiment analysis tasks. In contrast to gradient-based feature attribution methods, we propose a simple and effective Layer-wise Attention Tracing (LAT) method to analyze structured attention weights. We apply our method to Transformer models trained on two tasks that have surface dissimilarities, but share common semantics---sentiment analysis of movie reviews and time-series valence prediction in life story narratives. Across both tasks, words with high aggregated attention weights were rich in emotional semantics, as quantitatively validated by an emotion lexicon labeled by human annotators. Our results show that structured attention weights encode rich semantics in sentiment analysis, and match human interpretations of semantics.

📄 PDF Abstract BibTeX arXiv:2010.04922

Code (1)

frankaging/LAT_for_Transformer 공식 구현 pytorch

Tasks

Sentiment AnalysisTime SeriesTime Series Analysis

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
Adam 설명 없음
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Structured Self-AttentionWeights Encode Semantics in Sentiment Analysis

2020-11-01 · EMNLP (BlackboxNLP) 2020 11 · Zhengxuan Wu, Thanh-Son Nguyen, Desmond Ong

Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in…

Sentiment AnalysisTime SeriesTime Series Analysis

Class Semantics-based Attention for Action Detection

2021-09-06 · ICCV 2021 10 · Deepak Sridhar, Niamul Quader, Srikanth Muralidharan, Yaoxin Li 외

Action localization networks are often structured as a feature encoder sub-network and a localization sub-network, where the feature encoder learns to transform an input video to features that are useful for the localiza…

Action DetectionAction Localization

HIRL: A General Framework for Hierarchical Image Representation Learning

2022-05-26 · Minghao Xu, Yuanfan Guo, Xuanyu Zhu, Jiawen Li 외

Learning self-supervised image representations has been broadly studied to boost various visual understanding tasks. Existing methods typically learn a single level of image semantics like pairwise semantic similarity or…

Image ClusteringRepresentation LearningSelf-Supervised LearningSemantic Similarity+1

An Analysis of Encoder Representations in Transformer-Based Machine Translation

2018-11-01 · WS 2018 11 · Aless Raganato, ro, J{\"o}rg Tiedemann

The attention mechanism is a successful technique in modern NLP, especially in tasks like machine translation. The recently proposed network architecture of the \textit{Transformer} is based entirely on attention mechani…

Feature EngineeringMachine TranslationTransfer LearningTranslation

DropKey

2022-08-04 · Bonan Li, Yinhan Hu, Xuecheng Nie, Congying Han 외

In this paper, we focus on analyzing and improving the dropout technique for self-attention layers of Vision Transformer, which is important while surprisingly ignored by prior works. In particular, we conduct researches…

Human-Object Interaction Detectionimage-classificationImage Classificationobject-detection+1