mlsanityData to 13 Oct 2026

Concatenated Power Mean Word Embeddings as Universal Cross-Lingual Sentence Representations

arXiv 1803.01400 ↗First posted 4 Mar 2018cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Average word embeddings are a common baseline for more sophisticated sentence embedding techniques. However, they typically fall short of the performances of more complex models such as InferSent. Here, we generalize the concept of average word embeddings to power mean word embeddings. We show that the concatenation of different types of power mean word embeddings considerably closes the gap to state-of-the-art methods monolingually and substantially outperforms these more complex techniques cross-lingually. In addition, our proposed method outperforms different recently proposed baselines such as SIF and Sent2Vec by a solid margin, thus constituting a much harder-to-beat monolingual baseline. Our data and code are publicly available.

Key facts. Cited by 20 papers in the map (data through 13 Oct 2026). First posted on arXiv 4 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 5; 2023: 4; 2024: 3; 2025: 1.

20 papers.

Sort:

By area:

  1. 2023Gloss Attention for Gloss-free Sign Language Translationcited by 51
  2. 2021Automatic Text Evaluation through the Lens of Wasserstein Barycenterscited by 38
  3. 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
  4. 2021Survey on reinforcement learning for language processingcited by 31
  5. 2022Just Rank: Rethinking Evaluation with Word and Sentence Similaritiescited by 20
  6. 2023Unsupervised Layer-wise Score Aggregation for Textual OOD Detectioncited by 15
  7. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  8. 2022Reproducibility Issues for BERT-based Evaluation Metricscited by 9
  9. 2022QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevancecited by 9
  10. 2021Learning Zero-Shot Multifaceted Visually Grounded Word Embeddings via Multi-Task Trainingcited by 8
  11. 2024Codenames as a Benchmark for Large Language Modelscited by 8
  12. 2021Unsupervised Sentence-embeddings by Manifold Approximation and Projectioncited by 4
8 more
  1. 2024SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detectioncited by 4
  2. 2022Beyond Mahalanobis-Based Scores for Textual OOD Detectioncited by 3
  3. 2021Discrete Cosine Transform as Universal Sentence Encodercited by 2
  4. 2021A Novel Perspective for Positive-Unlabeled Learning via Noisy Labelscited by 1
  5. 2025LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilitiescited by 1
  6. 2023NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representationcited by 0
  7. 2023Sentiment analysis in Tourism: Fine-tuning BERT or sentence embeddings concatenation?cited by 0
  8. 2024Investigating Consistency in Query-Based Meeting Summarization: A Comparative Study of Different Embedding Methodscited by 0