| Presentation | 2023-03-18 Estimating Named Entity Label Representation for Generative Low-Resource NER Yuya Sawada, Hiroki Teranishi, Hiroki Ouchi, Yuji Matsumoto, Taro Watanabe, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Named entity recognition (NER) system needs to identify the entities of novel entity types with fewer examples. Few-shot NER systems can capture useful knowledge from external resources, but identifying the nested and discontinuous span is still challenging because their methods are based on sequence labeling and span-based method. We aim for a low-resource generative NER model corresponding to the complex span and propose utilizing methods that use label representation by the novel type's descriptions. Experiments show that the proposed methods achieve competitive performances in few-shot scenarios, and can extract complex spans with limited samples. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Named Entity Recognition / Fine-tuning / Few-shot learning / Description / Nested / Discontinuous |
| Paper # | NLC2022-22 |
| Date of Issue | 2023-03-11 (NLC) |
| Conference Information | |
| Committee | NLC / IPSJ-NL |
|---|---|
| Conference Date | 2023/3/18(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | OIST |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Applications of natural language processing, and etc. |
| Chair | Mitsuo Yoshida(Univ. of Tsukuba) / 須藤 克仁(奈良先端科学技術大学院大学) |
| Vice Chair | Hiroki Sakaji(Univ. of Tokyo) / Takeshi Kobayakawa(NHK) |
| Secretary | Hiroki Sakaji(NTT) / Takeshi Kobayakawa(Hiroshima Univ. of Economics) / (LINE株式会社) |
| Assistant | Kanjin Takahashi(Sansan) / Yasuhiro Ogawa(Nagoya Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Estimating Named Entity Label Representation for Generative Low-Resource NER |
| Sub Title (in English) | |
| Keyword(1) | Named Entity Recognition |
| Keyword(2) | Fine-tuning |
| Keyword(3) | Few-shot learning |
| Keyword(4) | Description |
| Keyword(5) | Nested |
| Keyword(6) | Discontinuous |
| 1st Author's Name | Yuya Sawada |
| 1st Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 2nd Author's Name | Hiroki Teranishi |
| 2nd Author's Affiliation | RIKEN Center for Advanced Intelligence Project(RIKEN AIP) |
| 3rd Author's Name | Hiroki Ouchi |
| 3rd Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| 4th Author's Name | Yuji Matsumoto |
| 4th Author's Affiliation | RIKEN Center for Advanced Intelligence Project(RIKEN AIP) |
| 5th Author's Name | Taro Watanabe |
| 5th Author's Affiliation | Nara Institute of Science and Technology(NAIST) |
| Date | 2023-03-18 |
| Paper # | NLC2022-22 |
| Volume (vol) | vol.122 |
| Number (no) | NLC-449 |
| Page | pp.pp.16-21(NLC), |
| #Pages | 6 |
| Date of Issue | 2023-03-11 (NLC) |