CoChat
Sign Up
Cited by 436Topic ModelingNatural Language Processing TechniquesSentiment Analysis and Opinion Mining

The DOI matches its Crossref record; 54 of the 57 references it cites were found in a registry or an index.

Dissecting Contextual Word Embeddings: Architecture and Representation

Open access
Peters, Matthew, Neumann, Mark, Zettlemoyer, Luke, Yih, Wen-tau·2018·Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
DOI 10.18653/v1/d18-1179
Open this paper in CoChat — free accountOpen PDF

Abstract

Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks.However, many questions remain as to how and why these models are so effective.In this paper, we present a detailed empirical study of how the choice of neural architecture (e.g.LSTM, CNN, or self attention) influences both end task accuracy and qualitative properties of the representations that are learned.We show there is a tradeoff between speed and accuracy, but all architectures learn high quality contextual representations that outperform word embeddings for four challenging NLP tasks.Additionally, all architectures learn representations that vary with network depth, from exclusively morphological based at the word embedding layer through local syntax based in the lower contextual layers to longer range semantics such coreference at the upper layers.Together, these results suggest that unsupervised biLMs, independent of architecture, are learning much more about the structure of language than previously appreciated.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.18653/v1/d18-1179

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Visualization of contextual similarity between all word pairs in a single sentence using the 4-layer LSTM. The left panel uses context vectors from the bottom LSTM layer while the right panel uses the top LSTM layer. Lighter yellow-colored areas have higher contextual similarity.
Figure 1 Visualization of contextual similarity between all word pairs in a single sentence using the 4-layer LSTM. The left panel uses context vectors from the bottom LSTM layer while the right panel uses the top LSTM layer. Lighter yellow-colored areas have higher contextual similarity.CC-BY · From the PDF
Figure 2 t-SNE visualization of 3K random chunks and 500 unlabeled spans ('NULL') from the CoNLL 2000 chunking dataset.
Figure 2 t-SNE visualization of 3K random chunks and 500 unlabeled spans ('NULL') from the CoNLL 2000 chunking dataset.CC-BY · From the PDF
Image 3
CC-BY · From the PDF
Image 4
CC-BY · From the PDF
Image 5
CC-BY · From the PDF
Figure 4 Normalized layer weights s for the tasks in Sec. 4. The vertical axis indexes the layer in the biLM, with layer 0 the word embedding x k .
Figure 4 Normalized layer weights s for the tasks in Sec. 4. The vertical axis indexes the layer in the biLM, with layer 0 the word embedding x k .CC-BY · From the PDF

Verification

Claims the paper makes

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Show all 57 references

Research works printed but not linked: 4

  1. Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Has- san Sajjad, and James R. Glass. 2017. What do neu- ral machine translation models learn about morphol- ogy? In ACL.
  2. Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander M. Rush. 2017. Open- NMT: Open-source toolkit for neural machine trans- lation. In ACL.
  3. Liyuan Liu, Xiang Ren, Jingbo Shang, Jian Peng, and Jiawei Han. 2018. Efficient contextualized represen- tation: Language model pruning for sequence label- ing. In EMNLP.
  4. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word rep- resentations. In NAACL.

Cited by

Sorted by citations

Items 301–400 of 436

Related

See all

Metadata

Authors
Peters, M., Neumann, M., Zettlemoyer, L., & Yih, W.-T.
Affiliations
  • Allen Institute for Artificial Intelligence (US)
  • University of Washington (US)
ORCID
Venue
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Publisher
Association for Computational Linguistics
Published
2018
Pages
1499-1509
DOI
10.18653/v1/d18-1179
OpenAlex
W2888329843
Cited by
434
References
57
Citations by year
2026: 23 · 2025: 27 · 2024: 37 · 2023: 53 · 2022: 55 · 2021: 75 · 2020: 83 · 2019: 77 · 2018: 4
FWCI
24.08
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
Keywords
contextual word embeddings, bidirectional language models, LSTM, convolutional neural networks, self-attention, representation learning, network depth, morphological representation, syntactic representation, coreference, word embeddings, speed-accuracy trade-off

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