Name
Abstract | ||
|---|---|---|
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 encoder-decoder 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. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.18653/v1/W16-0106 | international joint conference on artificial intelligence |
Field | DocType | Volume |
Embedding,Question answering,Computer science,Artificial intelligence,Natural language processing,Generative grammar,Artificial neural network,Factoid,Machine learning,Empirical research | Journal | abs/1512.01337 |
Citations | PageRank | References |
12 | 0.51 | 3 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jun Yin | 1 | 121 | 12.32 |
| Xin Jiang | 2 | 150 | 32.43 |
| Zhengdong Lu | 3 | 1755 | 66.51 |
| Lifeng Shang | 4 | 485 | 30.96 |
| Hang Li | 5 | 6294 | 317.05 |
| Xiaoming Li | 6 | 517 | 60.22 |