Inventor · disambiguated record
Linfeng Song
Also filed as: SONG LINFENG
22 granted patents·9 pending applications·9 citations·filing 2016–2025
90Inventor score
Top patents by PatentIndex Score
31 records- 0189US11550997B2Structural information preserving for graph-to-text generationTencent America LLC·Filed 2020·Granted Jan 10, 2023·3 cites·15 claims
- 0288US11868344B1System, method, and computer program for cross-lingual text-to-SQL semantic parsing with representation mixupTencent America LLC·Filed 2022·Granted Jan 9, 2024·2 cites·19 claims
- 0385US12229505B2Structural information preserving for graph-to-text generationTencent America LLC·Filed 2022·Granted Feb 18, 2025·1 cites·17 claims
- 0485US12222936B2System, method, and computer program for augmenting multi-turn text-to-SQL datasets with self-playTencent America LLC·Filed 2022·Granted Feb 11, 2025·1 cites·17 claims
- 0582US11455467B2Relation extraction using full dependency forestsTencent America LLC·Filed 2020·Granted Sep 27, 2022·2 cites·20 claims
- 0679US2025390684A1Variational graph autoencoding as cheap supervision for amr coreference resolutionTencent America LLC·Filed 2025·Application pending·0 cites
- 0778US12443846B2Dialogue training with rich reference-free discriminatorsTencent America LLC·Filed 2024·Granted Oct 14, 2025·0 cites·15 claims
- 0872US2024256790A1Structure self-aware model for discourse parsing on multi-party dialoguesTencent America LLC·Filed 2024·Application pending·0 cites
- 0971US12468889B2Multi-task self-training for character gender identificationTencent America LLC·Filed 2023·Granted Nov 11, 2025·0 cites·20 claims
- 1069US11663412B2Relation extraction exploiting full dependency forestsTencent America LLC·Filed 2022·Granted May 30, 2023·0 cites·20 claims
- 1167US11822884B2Unified model for zero pronoun recovery and resolutionTencent America LLC·Filed 2022·Granted Nov 21, 2023·0 cites·20 claims
- 1266US11735174B2Video-aided unsupervised grammar inductionTencent America LLC·Filed 2022·Granted Aug 22, 2023·0 cites·20 claims
- 1365US12423527B2Variational graph autoencoding for abstract meaning representation coreference resolutionTencent America LLC·Filed 2022·Granted Sep 23, 2025·0 cites·16 claims
- 1465US11995542B2Dialogue model training based on reference-free discriminatorsTencent America LLC·Filed 2021·Granted May 28, 2024·0 cites·17 claims
- 1562US12032916B2Structure self-aware model for discourse parsing on multi-party dialoguesTencent America LLC·Filed 2021·Granted Jul 9, 2024·0 cites·20 claims
- 1661US12462171B2Hierarchical context tagging for utterance rewritingTencent America LLC·Filed 2021·Granted Nov 4, 2025·0 cites·20 claims
- 1761US11954136B2Method and apparatus for multi-view conversational query productionTencent America LLC·Filed 2022·Granted Apr 9, 2024·0 cites·17 claims
- 1860US11521605B2Video-aided unsupervised grammar inductionTencent America LLC·Filed 2021·Granted Dec 6, 2022·0 cites·20 claims
- 1959US11481548B2Zero pronoun recovery and resolutionTencent America LLC·Filed 2019·Granted Oct 25, 2022·0 cites·18 claims
- 2057US12229523B2Search-engine-augmented dialogue response generation with cheaply supervised query productionTencent America LLC·Filed 2022·Granted Feb 18, 2025·0 cites·18 claims
- 2157US12190880B2Method and apparatus for multi-party dialogue discourse parsing as a sequence generationTencent America LLC·Filed 2022·Granted Jan 7, 2025·0 cites·20 claims
- 2254US2025348665A1Method and apparatus for self-consistency boosts calibration for math reasoningTencent America LLC·Filed 2024·Application pending·0 cites
- 2354US2025335482A1Response enhanced semi-supervised dialogue query generationTencent America LLC·Filed 2024·Application pending·0 cites
- 2452US2023196087A1Instance adaptive training with noise robust losses against noisy labelsTencent America LLC·Filed 2021·Application pending·0 cites
- 2552US2025315610A1Method and apparatus for fine-grained self-endorsement improves factuality and reasoningTencent America LLC·Filed 2024·Application pending·0 cites
- 2651US12223283B2Conversational aspect sentiment analysis for dialogue understandingTencent America LLC·Filed 2021·Granted Feb 11, 2025·0 cites·17 claims
- 2750US2025131203A1Advantage modeling for rlhfTencent America LLC·Filed 2023·Application pending·0 cites
- 2849US12182519B2Systems and methods for semantic-based pre-training for dialogue understandingTencent America LLC·Filed 2022·Granted Dec 31, 2024·0 cites·15 claims
- 2947US10423685B2System and method for automatic question generation from knowledge baseBOSCH GMBH ROBERT·Filed 2016·Granted Sep 24, 2019·0 cites·18 claims
- 3046US2025350337A1Skywave massive mimo-ofdm triple beam-based channel modeling and channel information acquisitionUNIV SOUTHEAST·Filed 2023·Application pending·0 cites
- 3141US2022284193A1Robust dialogue utterance rewriting as sequence taggingTencent America LLC·Filed 2021·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when Linfeng Song files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →