CoChat

A Survey of Knowledge-enhanced Text Generation

Open access

The DOI matches its Crossref record; 249 of the 249 references it cites were found in a registry or an index.

Abstract

The goal of text-to-text generation is to make machines express like a human in many applications such as conversation, summarization, and translation. It is one of the most important yet challenging tasks in natural language processing (NLP). Various neural encoder-decoder models have been proposed to achieve the goal by learning to map input text to output text. However, the input text alone often provides limited knowledge to generate the desired output, so the performance of text generation is still far from satisfaction in many real-world scenarios. To address this issue, researchers have considered incorporating (i) internal knowledge embedded in the input text and (ii) external knowledge from outside sources such as knowledge base and knowledge graph into the text generation system. This research topic is known as knowledge-enhanced text generation . In this survey, we present a comprehensive review of the research on this topic over the past five years. The main content includes two parts: (i) general methods and architectures for integrating knowledge into text generation; (ii) specific techniques and applications according to different forms of knowledge data. This survey can have broad audiences, researchers and practitioners, in academia and industry.

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 · 10.1145/3512467

Cites

249 of 249 references verified0 citation errors · 0 not checkable

Statistics

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

Show all 249 references

Research works printed but not linked: 6

  1. 10.18653/v1/D17-1209 · DOI · Paper page
  2. 10.5555/3524938.3525295 · doi:10.5555/3524938.3525295
  3. 10.5555/2145432.2145494 · doi:10.5555/2145432.2145494
  4. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. In Nature. Nature Publishing Group.
  5. Lianhui Qin, Vered Shwartz, Peter West, Chandra Bhagavatula, Jena Hwang, Ronan Le Bras, Antoine Bosselut, and Yejin Choi. 2020. Backpropagation-based decoding for unsupervised counterfactual and abductive reasoning. In Conference on Empirical Methods in Natural Language Processing (EMNLP).
  6. 10.18653/v1/W16-2209 · DOI

Cited by

Items 101–200 of 261

Metadata

Authors
Yu, W., Zhu, C., Li, Z., Hu, Z., Wang, Q., Ji, H., & Jiang, M.
Affiliations
  • University of Notre Dame (US)
  • Microsoft (United States) (US)
  • Chinese University of Hong Kong (HK)
  • University of California San Diego (US)
  • University of Illinois Urbana-Champaign (US)
Venue
ACM Computing Surveys
Published
2022-01-31
Volume
54
Issue
11s
Pages
1-38
ISSN
  • 0360-0300 (ISSN-L)
  • 1557-7341
OpenAlex
W3092288641
Cited by
257
References
241
Citations by year
2026: 27 · 2025: 54 · 2024: 63 · 2023: 67 · 2022: 26
FWCI
17.28
Type
journal article
Language
en
Open access
Locations
  • ACM Computing Surveys (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
  • National Science Foundation (IIS-1849816, CCF-1901059, and IIS-2119531)
  • Agriculture and Food Research Initiative (2020-67021-32799)
  • USDA National Institute of Food and Agriculture, U.S. (HR001120C0123, FA8750-18-2-0014, and FA8750-19-2-1004)
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 › Speech and dialogue systems
Keywords
text-to-text generation, knowledge base integration, knowledge graphs, external knowledge, encoder-decoder architecture, internal knowledge

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.