Situating Sentence Embedders with Nearest Neighbor Overlap
As distributed approaches to natural language semantics have developed and diversified, embedders for linguistic units larger than words have come to play an increasingly important role. To date, such embedders have been evaluated using benchmark tasks (e.g., GLUE) and linguistic probes. We propose a comparative approach, nearest neighbor overlap (N2O), that quantifies similarity between embedders in a task-agnostic manner. N2O requires only a collection of examples and is simple to understand: two embedders are more similar if, for the same set of inputs, there is greater overlap between the inputs' nearest neighbors. Though applicable to embedders of texts of any size, we focus on sentence embedders and use N2O to show the effects of different design choices and architectures.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSimilar Papers 제목 키워드 기반
Tell me what you see: A zero-shot action recognition method based on natural language descriptions
This paper presents a novel approach to Zero-Shot Action Recognition. Recent works have explored the detection and classification of objects to obtain semantic information from videos with remarkable performance. Inspire…
Action RecognitionDescriptiveDomain AdaptationVideo Captioning+1Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs
Hidden states change substantially across the layers of modern language models, but most layer-wise analyses focus on one aspect of that change. We propose Layer-wise Representation Dynamics (LRD), a framework with three…
Debiasing Sentence Embedders through Contrastive Word Pairs
Over the last years, various sentence embedders have been an integral part in the success of current machine learning approaches to Natural Language Processing (NLP). Unfortunately, multiple sources have shown that the b…
SentenceSentence EmbeddingsWord EmbeddingsCA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification
Person re-identification (re-ID) is a challenging task that aims to learn discriminative features for person retrieval. In person re-ID, Jaccard distance is a widely used distance metric, especially in re-ranking and clu…
Person Re-IdentificationPerson RetrievalRe-RankingUnsupervised Person Re-Identification+2Nonparametric Nearest Neighbor Random Process Clustering
We consider the problem of clustering noisy finite-length observations of stationary ergodic random processes according to their nonparametric generative models without prior knowledge of the model statistics and the num…
Clustering