Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval
Open accessAbstract
Xiaodong Liu, Jianfeng Gao, Xiaodong He, Li Deng, Kevin Duh, Ye-yi Wang. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.
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.
Integrity signals
Registry
Cites
Statistics
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.
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?
MT-DNN achieved state-of-the-art performance on GLUE and other benchmarks when it was introduced.
“This is the method used by the 'MT-DNN' (Liu et al., 2015, 2019b), which achieved state-of-the-art performance on GLUE and other benchmarks when it was introduced.”
From Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019) · cites this paper as Liu et al., 2015
The available passages are bibliographic metadata for the 2015 paper (pp. 912–921), not its results. Searches for GLUE, MT-DNN, and state-of-the-art benchmark performance returned no passage addressing the claim, so our copy cannot verify it. (LLM, conf=0.75)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Neural Networks: Tricks of the Trade: Second Edition
(2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8 · Cited by 2,116 · cited 2× · see citing works
“Additional training details : (1) Model parameters are initialized with uniform distribution in the range ( 6 / ( fan in + fan out ) , 6 / ( fan in + fan out )) (Montavon et al., 2012).”
Background
Flagged first, then by citations
Cited by
Sorted by citations
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · see citing works
Domain-specific language model pretraining for biomedical natural language processing
Gu, Y., Tinn, R., Cheng, H., Lucas, M., Usuyama, N., Liu, X., Naumann, T., Gao, J., & Poon, H. (2022) · ACM Transactions on Computing for Healthcare · doi:10.1145/3458754 · Cited by 2,170 · see citing works
Self-citationHow to Fine-Tune BERT for Text Classification?
Sun, C., Qiu, X., Xu, Y., & Huang, X. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-32381-3_16 · Cited by 1,534 · see citing works
From Eliza to XiaoIce: Challenges and opportunities with social chatbots
Shum, H.-Y., He, X.-D., & Li, D. (2018) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1700826 · Cited by 749 · see citing works
“First, the user’s input is sent to a user understanding component, where semantic encoding and intent understanding is performed (Tur and Deng 2011; Liu et al., 2015; Vinyals and Le, 2015).”
BackgroundSelf-citationMultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
Teichmann, M., Weber, M., Zollner, M., Cipolla, R., & Urtasun, R. (2018) · 2018 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2018.8500504 · Cited by 681 · see citing works
Multimodal intelligence: Representation learning, information fusion, and applications
Zhang, C., Yang, Z., He, X., & Deng, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2987728 · Cited by 511 · see citing works
Self-citationA neural network multi-task learning approach to biomedical named entity recognition
Crichton, G., Pyysalo, S., Chiu, B., & Korhonen, A. (2017) · BMC Bioinformatics · doi:10.1186/s12859-017-1776-8 · Cited by 229 · see citing works
Georgiev, P., Bhattacharya, S., Lane, N. D., & Mascolo, C. (2017) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3131895 · Cited by 67 · see citing works
SciRepEval: A Multi-Format Benchmark for Scientific Document Representations
Singh, A., D'Arcy, M., Cohan, A., Downey, D., & Feldman, S. (2022) · arXiv · doi:10.48550/arxiv.2211.13308 · Cited by 76
“Multi-Task Learning Across Formats Multi-task learning (Caruana, 1993) with deep neural networks has shown improvements upon single-task training for related objectives (Liu et al., 2015, 2019b).”
- Authors
- Liu, X., Gao, J., He, X., Deng, L., Duh, K., & Wang, Y.-Y.
- Affiliations
- Nara Institute of Science and Technology (JP)
- Microsoft (United States) (US)
- Venue
- Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Published
- 2015
- Pages
- 912-921
- OpenAlex
- W2295072214
- Cited by
- 395
- References
- 1
- Citations by year
- 2026: 1 · 2025: 7 · 2024: 12 · 2023: 35 · 2022: 34 · 2021: 58 · 2020: 80 · 2019: 58 · 2018: 52 · 2017: 34 · 2016: 17 · 2015: 7
- FWCI
- 20.66
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
- Funders
- Microsoft Research
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- representation learning, multi-task learning, deep neural network, semantic classification, information retrieval
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
