CoChat

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling

Open access
Liu, Liyuan, Ren, Xiang, Shang, Jingbo, Gu, Xiaotao, Peng, Jian, Han, Jiawei · 2018 · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.

Abstract

Many efforts have been made to facilitate natural language processing tasks with pre-trained language models (LMs), and brought significant improvements to various applications.To fully leverage the nearly unlimited corpora and capture linguistic information of multifarious levels, large-size LMs are required; but for a specific task, only parts of these information are useful.Such large-sized LMs, even in the inference stage, may cause heavy computation workloads, making them too time-consuming for large-scale applications.Here we propose to compress bulky LMs while preserving useful information with regard to a specific task.As different layers of the model keep different information, we develop a layer selection method for model pruning using sparsityinducing regularization.By introducing the dense connectivity, we can detach any layer without affecting others, and stretch shallow and wide LMs to be deep and narrow.In model training, LMs are learned with layerwise dropouts for better robustness.Experiments on two benchmark datasets demonstrate the effectiveness of our method.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/d18-1153

Cites

43 of 43 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Leverage the dense connectivity to compress models via layer selection, and replace wide and shallow RNNs with deep and narrow ones.
Figure 1 Leverage the dense connectivity to compress models via layer selection, and replace wide and shallow RNNs with deep and narrow ones.CC-BY · From the PDF
Figure 2 Penalty values of various R for z with three dimensions. λ 1 has been set to 2 for R 2 and R 3 .
Figure 2 Penalty values of various R for z with three dimensions. λ 1 has been set to 2 for R 2 and R 3 .CC-BY · From the PDF
Figure 3 Layer-wise dropout conducted on a 4-layer densely connected RNN. (a) is the remained RNN. (b) is the original densely connected RNN.
Figure 3 Layer-wise dropout conducted on a 4-layer densely connected RNN. (a) is the remained RNN. (b) is the original densely connected RNN.CC-BY · From the PDF
Image 4
CC-BY · From the PDF
Figure 5 The performance of pruned models in two tasks w.r.t. their efficiency (FLOPs).
Figure 5 The performance of pruned models in two tasks w.r.t. their efficiency (FLOPs).CC-BY · From the PDF
Figure 6 The performance of pruned models in two tasks w.r.t. their efficiency (FLOPs).
Figure 6 The performance of pruned models in two tasks w.r.t. their efficiency (FLOPs).CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 4

  1. Xavier Glorot and Yoshua Bengio. 2010. Understand- ing the difficulty of training deep feedforward neu- ral networks. In Proceedings of the Thirteenth In- ternational Conference on Artificial Intelligence and Statistics.
  2. Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural network. In Advances in neural in- formation processing systems, pages 1135-1143.
  3. Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. 2017. Densely connected con- volutional networks. In CVPR.
  4. Walter Murray and Kien-Ming Ng. 2010. An algo- rithm for nonlinear optimization problems with bi- nary variables. Computational Optimization and Applications, 47(2):257-288.

Cited by

See all 45

Metadata

Authors
Liu, L., Ren, X., Shang, J., Gu, X., Peng, J., & Han, J.
Affiliations
  • University of Illinois Urbana-Champaign (US)
  • University of Southern California (US)
Venue
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Published
2018
Pages
1215-1225
OpenAlex
W2963972328
Cited by
45
References
43
Citations by year
2026: 1 · 2025: 2 · 2024: 1 · 2023: 5 · 2022: 8 · 2021: 3 · 2020: 13 · 2019: 11 · 2018: 1
FWCI
2.86
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
Army Research Laboratory (Cooperative Agreement Number W911NF-09-2-0053 (the, W911NF, W911NF-09-2-0053)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
sequence labeling, layer selection, sparsity-promoting regularization, dense connections, model compression, pre-trained language models, inference efficiency

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.