Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning
Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this intriguing result using a word analogy prediction formulation and hand-selected relations, but the generality of the finding over a broader range of lexical relation types and different learning settings has not been evaluated. In this paper, we carry out such an evaluation in two learning settings: (1) spectral clustering to induce word relations, and (2) supervised learning to classify vector differences into relation types. We find that word embeddings capture a surprising amount of information, and that, under suitable supervised training, vector subtraction generalises well to a broad range of relations, including over unseen lexical items.
Code (1)
Tasks
ClusteringRelationWord EmbeddingsSimilar Papers 제목 키워드 기반
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Reinforcement Learning with Verifiable Rewards (RLVR) has become a cornerstone for unlocking complex reasoning in Large Language Models (LLMs). Yet, scaling up RL is bottlenecked by limited existing verifiable data, wher…
Reinforcement LearningLearning to Route Among Specialized Experts for Zero-Shot Generalization
Recently, there has been a widespread proliferation of "expert" language models that are specialized to a specific task or domain through parameter-efficient fine-tuning. How can we recycle large collections of expert la…
parameter-efficient fine-tuningZero-shot GeneralizationFirst African Digital Humanism Summer School 2025
Artificial intelligence (AI) has become a transformative force across global societies, reshaping the ways we communicate, collaborate, and make decisions. Yet, as AI systems increasingly mediate interactions between hum…
GOOSE-M2F: Adapting Mask2Former for High-Fidelity, Long-Tailed Fine-Grained Semantic Segmentation in Unstructured Outdoor Terrain
We present GOOSE-M2F, a task-specific adaptation of Mask2Former for the GOOSE 2D Fine-Grained Semantic Segmentation (FGSS) Challenge at ICRA 2026. The GOOSE benchmark spans 64 fine-grained classes across unstructured out…
Semantic SegmentationGoose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tree: deeper trees accept more tokens per s…