Apparatus for automatically generating a knowledge graph
By using multilingual models and gradient inversion training, the problem of monolingual models being unable to recognize cross-lingual tense expressions was solved, thus improving the accuracy of cross-lingual tense expression recognition and knowledge graph filling.
CN113535971BActive Publication Date: 2026-07-03ROBERT BOSCH GMBH
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202110405331.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2020-04-16
- Filing Date
- 2021-04-15
- Publication Date
- 2026-07-03
- Estimated Expiration
- 2041-04-15
AI Technical Summary
Technical Problem
Existing monolingual models cannot effectively identify and transfer cross-lingual temporal representations, leading to errors when populating knowledge graphs with multilingual text.
Method used
Using a multilingual model and gradient inversion training method, a multilingual word embedding space is generated through adversarial training. This space is used to identify and label tense expressions in multilingual texts and apply them to fill knowledge graphs.
Benefits of technology
It enables cross-linguistic tense expression recognition and transfer, improving the accuracy of knowledge graph filling and the effectiveness of multilingual text analysis.
✦ Generated by Eureka AI based on patent content.
Abstract
Device (100) for automatically analyzing a multilingual text, comprising an embedder (25) and a tense marker (30), the embedder being set up to assign a numerical representation (12a, 12b) to a text component (10a, 10b) in the multilingual text (10) respectively, the tense marker being set up to identify and mark tense expressions in the multilingual text (10) on the basis of the assigned numerical representations (12a, 12b), wherein the embedder (25) is set up to assign the numerical representations (12a, 12b) of the tense expressions as far as possible such that it is not possible to determine on the basis of the numerical representations (12a, 12b) in which language the respective text component (10a, 10b) was written.
Need to check novelty before this filing date? Find Prior Art