https://github.com/metaphors/TSAttack
공식 코드TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Semantic textual similarity deals with determining how similar two pieces of texts are. This can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.
Image source: Learning Semantic Textual Similarity from Conversations
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
Bridging the Gap between Structural and Semantic Similarity in Diverse Planning
SeFNet: Bridging Tabular Datasets with Semantic Feature Nets
Weakly-supervised Audio Separation via Bi-modal Semantic Similarity
A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations
Soft Alignment Objectives for Robust Adaptation of Language Generation
Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation
Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation
Guiding and Diversifying LLM-Based Story Generation via Answer Set Programming
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter
An Efficient Self-Supervised Cross-View Training For Sentence Embedding
JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its Applications
Novel Categories Discovery Via Constraints on Empirical Prediction Statistics
Determining Semantic Textual Similarity using Natural Deduction Proofs
Multi-Task Deep Neural Networks for Natural Language Understanding
Boosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with Momentum
Better Summarization Evaluation with Word Embeddings for ROUGE
User-in-the-loop Adaptive Intent Detection for Instructable Digital Assistant
KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Search
EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics
An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.