paper-with-me

Papers

Reflection-based Word Attribute Transfer

2020-07-06 · ACL 2020 6 · Yoichi Ishibashi, Katsuhito Sudoh, Koichiro Yoshino, Satoshi Nakamura

Word embeddings, which often represent such analogic relations as king - man + woman = queen, can be used to change a word's attribute, including its gender. For transferring king into queen in this analogy-based manner, we subtract a difference vector man - woman based on the knowledge that king is male. However, developing such knowledge is very costly for words and attributes. In this work, we propose a novel method for word attribute transfer based on reflection mappings without such an analogy operation. Experimental results show that our proposed method can transfer the word attributes of the given words without changing the words that do not have the target attributes.

📄 PDF Abstract BibTeX arXiv:2007.02598

Code (2)

ahclab/reflection 공식 구현 pytorch
yoichi1484/reflection 공식 구현 pytorch

Tasks

AttributeWord Attribute TransferWord Embeddings

Similar Papers 제목 키워드 기반

Rethinking Text Attribute Transfer: A Lexical Analysis

2019-09-26 · WS 2019 10 · Yao Fu, Hao Zhou, Jiaze Chen, Lei LI

Text attribute transfer is modifying certain linguistic attributes (e.g. sentiment, style, authorship, etc.) of a sentence and transforming them from one type to another. In this paper, we aim to analyze and interpret wh…

AttributeGeneral ClassificationLexical AnalysisSentence+1

Multiple Text Style Transfer by using Word-level Conditional Generative Adversarial Network with Two-Phase Training

2019-11-01 · IJCNLP 2019 11 · Chih-Te Lai, Yi-Te Hong, Hong-You Chen, Chi-Jen Lu 외

The objective of non-parallel text style transfer, or controllable text generation, is to alter specific attributes (e.g. sentiment, mood, tense, politeness, etc) of a given text while preserving its remaining attributes…

AttributeGenerative Adversarial NetworkStyle TransferText Generation+1

Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer

2018-04-17 · NAACL 2018 6 · Juncen Li, Robin Jia, He He, Percy Liang

We consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e.g., sentiment) while preserving its attribute-independent content (e.g., changing "screen is just the right size" …

AttributeImage CaptioningSentenceStyle Transfer+2

CoAPT: Context Attribute words for Prompt Tuning

2024-07-18 · Gun Lee, Subin An, Sungyong Baik, Soochahn Lee

We propose a novel prompt tuning method called CoAPT(Context Attribute words in Prompt Tuning) for few/zero-shot image classification. The core motivation is that attributes are descriptive words with rich information ab…

AttributeDescriptiveDomain Generalizationimage-classification+2

ChatGPT-guided Semantics for Zero-shot Learning

2023-10-18 · Fahimul Hoque Shubho, Townim Faisal Chowdhury, Ali Cheraghian, Morteza Saberi 외

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods…

AttributeLanguage ModellingLarge Language ModelWord Embeddings+1