Neural Generative Question Answering
Open accessAbstract
This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base.More specifically, the model is built on the encoderdecoder framework for sequence-to-sequence learning, while equipped with the ability to enquire the knowledge-base, and is trained on a corpus of question-answer pairs, with their associated triples in the knowledge-base.Empirical study shows the proposed model can effectively deal with the variations of questions and answers, and generate right and natural answers by referring to the facts in the knowledge-base.The experiment on question answering demonstrates that the proposed model can outperform an embedding-based QA model as well as a neural dialogue model trained on the same data.
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?
Early works on GQA mostly tried to improve the faithfulness of the answer by investigating reliable external knowledge sources or incorporating multiple information sources.
“Early works on GQA mostly tried to improve the faithfulness of the answer by investigating reliable external knowledge sources or incorporating multiple information sources.”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [297]
The Introduction (page unavailable) describes GENQA using an external knowledge base of facts to generate correct answers, supporting the external-knowledge part of the claim. It does not establish that early GQA works mostly took this approach or investigated multiple information sources; it says the authors knew of no previous generative-QA work. (LLM, conf=0.84)
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
Large-scale Simple Question Answering with Memory Networks
Bordes, A., Usunier, N., Chopra, S., & Weston, J. (2015) · arXiv · doi:10.48550/arxiv.1506.02075 · Cited by 528 · see citing works
Flagged first, then by citations
Research works printed but not linked: 11
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In ICLR.
- Bordes et al.2014a] Antoine Bordes, Jason Weston, and Sumit Chopra. 2014a. Question answering with sub- graph embeddings. EMNLP.
- Bordes et al.2014b] Antoine Bordes, Jason Weston, and Nicolas Usunier. 2014b. Open question answering with weakly supervised embedding models. In ECML PKDD, pages 165-180.
- Cho et al.2014] Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using rnn encoder-decoder for statistical machine translation. EMNLP.
- Chung et al.2014] Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empir- ical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. · arXiv
- Baotian Hu, Zhengdong Lu, Hang Li, and Qingcai Chen. 2014. Convolutional neural network architectures for matching natural language sentences. In Advances in Neural Information Processing System- s, pages 2042-2050.
- Iulian V Serban, Alessandro Sordoni, Yoshua Bengio, Aaron Courville, and Joelle Pineau. 2015. Building end-to-end dialogue systems using generative hierarchical neural network models. arX- iv preprint arXiv:1507.04808. · arXiv
- Lifeng Shang, Zhengdong Lu, and Hang Li. 2015. Neural responding machine for short- text conversation. In Association for Computational Linguistics (ACL), pages 1577-1586.
- Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, and Grégoire Mesnil. 2014. Learn- ing semantic representations using convolutional neu- ral networks for web search. In Proceedings of the companion publication of the 23rd international con- ference on World wide web companion, pages 373- 374. International World Wide Web Conferences S- teering Committee. [Sutskever et al.2014] Ilya Sutskever, Oriol Vinyals, and Quoc VV Le. 2014. Sequence to sequence learning with neural networks. In NIPS, pages 3104-3112.
- and Le2015] Oriol Vinyals and Quoc Le. 2015. A neural conversational model. arXiv preprint arX- iv:1506.05869.
- Weston et al.2015] Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory networks. In In- ternational Conference on Learning Representations (ICLR).
Cited by
Sorted by citations
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · see citing works
A Survey on Dialogue Systems: Recent Advances and New Frontiers
Chen, H., Liu, X., Yin, D., & Tang, J. (2017) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3166054.3166058 · Cited by 579 · see citing works
A Survey of Knowledge-enhanced Text Generation
Yu, W., Zhu, C., Li, Z., Hu, Z., Wang, Q., Ji, H., & Jiang, M. (2022) · ACM Computing Surveys · doi:10.1145/3512467 · Cited by 257 · see citing works
Is GitHub’s Copilot as bad as humans at introducing vulnerabilities in code?
Asare, O., Nagappan, M., & Asokan, N. (2023) · Empirical Software Engineering · doi:10.1007/s10664-023-10380-1 · Cited by 128 · see citing works
Low latency RNN inference with cellular batching
Gao, P., Yu, L., Wu, Y., & Li, J. (2018) · Proceedings of the Thirteenth EuroSys Conference · doi:10.1145/3190508.3190541 · Cited by 66 · see citing works
Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering
Baek, J., Aji, A., & Saffari, A. (2023) · Proceedings of the First Workshop on Matching From Unstructured and Structured Data (MATCHING 2023) · doi:10.18653/v1/2023.matching-1.7 · Cited by 51 · see citing works
“Generation Following the evaluation protocol of generative KGQA (Yin et al., 2016; Sen et al., 2022; Mavi et al., 2022), we use accuracy, which measures whether the generated tokens from the given prompt include one of the answer entities.”
Question Generation With Doubly Adversarial Nets
Bao, J., Gong, Y., Duan, N., Zhou, M., & Zhao, T. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2018.2859777 · Cited by 14 · see citing works
- Authors
- Yin, J., Jiang, X., Lu, Z., Shang, L., Li, H., & Li, X.
- Affiliations
- Peking University (CN)
- Huawei Technologies (China) (CN)
- Venue
- Proceedings of the Workshop on Human-Computer Question Answering
- Published
- 2016
- Pages
- 36-42
- OpenAlex
- W2963546833
- Cited by
- 186
- References
- 1
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 6 · 2023: 12 · 2022: 18 · 2021: 17 · 2020: 30 · 2019: 34 · 2018: 39 · 2017: 15 · 2016: 7 · 2015: 1
- FWCI
- 17.06
- Type
- conference paper
- Language
- en
- Open access
- gold
- doi.org
- Licence
- 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 › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- question answering, knowledge base, factoid questions, sequence-to-sequence learning, encoder-decoder architecture, knowledge base retrieval, answer generation, question-answer pairs
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
