paper-with-me

Papers

One Word Is Not Enough: Simple Prompts Improve Word Embeddings

2025-12-07 · Rajeev Ranjan arxiv

Text embedding models are designed for sentence-level applications like retrieval and semantic similarity, and are primarily evaluated on sentence-level benchmarks. Their behavior on isolated words is less understood. We show that simply prepending semantic prompts to words before embedding substantially improves word similarity correlations. Testing 7 text embedding models, including text-embedding-3-large (OpenAI), embed-english-v3.0 (Cohere), voyage-3(Voyage AI), all-mpnet-base-v2, and Qwen3-Embedding-8B, on 3 standard benchmarks (SimLex-999, WordSim-353, MEN-3000), we find that prompts like "meaning: {word}" or "Represent the semantic concept: {word}" improve Spearman correlations by up to +0.29 on SimLex-999. Some models fail completely on bare words (correlation = 0) but recover with prompts (+0.73 improvement). Our best results achieve correlation = 0.692 on SimLex-999 with embed-english-v3.0 (Cohere), correlation = 0.811 on WordSim-353, and correlation = 0.855 on MEN-3000 with text-embedding-3-large (OpenAI). These results outperform classic static embeddings like Word2Vec (correlation = 0.40) and even the best static method LexVec (correlation = 0.48) on SimLex-999, establishing a new state-of-the-art for pure embedding methods. This zero-shot technique requires no training and works with any text embedding model.

📄 PDF Abstract BibTeX arXiv:2512.06744

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SimilarityWord Similarity

Similar Papers 제목 키워드 기반

Data Collection vs. Knowledge Graph Completion: What is Needed to Improve Coverage?

2021-11-01 · EMNLP 2021 11 · Kenneth Church, Yuchen Bian

This survey/position paper discusses ways to improve coverage of resources such as WordNet. Rapp estimated correlations, rho, between corpus statistics and pyscholinguistic norms. rho improves with quantity (corpus size)…

Knowledge Graph CompletionPosition

Spot the Odd Man Out: Exploring the Associative Power of Lexical Resources

2018-10-01 · EMNLP 2018 10 · Gabriel Stanovsky, Mark Hopkins

We propose Odd-Man-Out, a novel task which aims to test different properties of word representations. An Odd-Man-Out puzzle is composed of 5 (or more) words, and requires the system to choose the one which does not belon…

ClusteringNatural Language InferenceQuestion AnsweringWord Embeddings

Keyword-Aware ASR Error Augmentation for Robust Dialogue State Tracking

2024-09-10 · Jihyun Lee, Solee Im, Wonjun Lee, Gary Geunbae Lee

Dialogue State Tracking (DST) is a key part of task-oriented dialogue systems, identifying important information in conversations. However, its accuracy drops significantly in spoken dialogue environments due to named en…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationDialogue State Tracking+3

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

2024-03-04 · CVPR 2024 1 · Lin Li, Haoyan Guan, Jianing Qiu, Michael Spratling

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the no…

Adversarial AttackAdversarial Robustness

Can We Use Word Embeddings for Enhancing Guarani-Spanish Machine Translation?

2022-05-01 · ComputEL (ACL) 2022 5 · Santiago Góngora, Nicolás Giossa, Luis Chiruzzo

Machine translation for low-resource languages, such as Guarani, is a challenging task due to the lack of data. One way of tackling it is using pretrained word embeddings for model initialization. In this work we try to …

Machine TranslationTranslationWord Embeddings