Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2004.13821 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916686581465088 |
|---|---|
| author | Xiong, Guanming |
| author_facet | Xiong, Guanming |
| contents | In this paper, we present a two stage model for multi-hop question answering. The first stage is a hierarchical graph network, which is used to reason over multi-hop question and is capable to capture different levels of granularity using the nature structure(i.e., paragraphs, questions, sentences and entities) of documents. The reasoning process is convert to node classify task(i.e., paragraph nodes and sentences nodes). The second stage is a language model fine-tuning task. In a word, stage one use graph neural network to select and concatenate support sentences as one paragraph, and stage two find the answer span in language model fine-tuning paradigm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2004_13821 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network Xiong, Guanming Computation and Language Artificial Intelligence Machine Learning In this paper, we present a two stage model for multi-hop question answering. The first stage is a hierarchical graph network, which is used to reason over multi-hop question and is capable to capture different levels of granularity using the nature structure(i.e., paragraphs, questions, sentences and entities) of documents. The reasoning process is convert to node classify task(i.e., paragraph nodes and sentences nodes). The second stage is a language model fine-tuning task. In a word, stage one use graph neural network to select and concatenate support sentences as one paragraph, and stage two find the answer span in language model fine-tuning paradigm. |
| title | Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2004.13821 |