paper-with-me

홈 › Papers

Reconstructing Word Embeddings via Scattered $k$-Sub-Embedding

2021-09-29 · Soonyong Hwang, Byung-Ro Moon

The performance of modern neural language models relies heavily on the diversity of the vocabularies. Unfortunately, the language models tend to cover more vocabularies, the embedding parameters in the language models such as multilingual models used to occupy more than a half of their entire learning parameters. To solve this problem, we aim to devise a novel embedding structure to lighten the network without considerably performance degradation. To reconstruct $N$ embedding vectors, we initialize $k$ bundles of $M (\ll N)$ $k$-sub-embeddings to apply Cartesian product. Furthermore, we assign $k$-sub-embedding using the contextual relationship between tokens from pretrained language models. We adjust our $k$-sub-embedding structure to masked language models to evaluate proposed structure on downstream tasks. Our experimental results show that over 99.9$\%+$ compressed sub-embeddings for the language models performed comparably with the original embedding structure on GLUE and XNLI benchmarks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityWord Embeddings

Similar Papers 제목 키워드 기반

Subword-based Compact Reconstruction of Word Embeddings

2019-06-01 · NAACL 2019 6 · Shota Sasaki, Jun Suzuki, Kentaro Inui

The idea of subword-based word embeddings has been proposed in the literature, mainly for solving the out-of-vocabulary (OOV) word problem observed in standard word-based word embeddings. In this paper, we propose a meth…

Word Embeddings

Tiny Word Embeddings Using Globally Informed Reconstruction

2020-12-01 · COLING 2020 8 · Sora Ohashi, Mao Isogawa, Tomoyuki Kajiwara, Yuki Arase

We reduce the model size of pre-trained word embeddings by a factor of 200 while preserving its quality. Previous studies in this direction created a smaller word embedding model by reconstructing pre-trained word repres…

Word EmbeddingsWord Similarity

Deconstructing and reconstructing word embedding algorithms

2019-11-29 · Edward Newell, Kian Kenyon-Dean, Jackie Chi Kit Cheung

Uncontextualized word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applications. Given the historical success of word embeddings in NLP, we propose a retros…

Word Embeddings

Comparing Euclidean and Hyperbolic Embeddings on the WordNet Nouns Hypernymy Graph

2021-09-15 · EMNLP (insights) 2021 11 · Sameer Bansal, Adrian Benton

Nickel and Kiela (2017) present a new method for embedding tree nodes in the Poincare ball, and suggest that these hyperbolic embeddings are far more effective than Euclidean embeddings at embedding nodes in large, hiera…

MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding

2019-08-01 · WS 2019 8 · Nils Rethmeier, Barbara Plank

Word embeddings have undoubtedly revolutionized NLP. However, pretrained embeddings do not always work for a specific task (or set of tasks), particularly in limited resource setups. We introduce a simple yet effective, …

Word Embeddings