declare-lab / relationprompt Goto Github PK

from wrapper import Dataset

data = Dataset.load(path)
for s in data.sents:
    print(s.tokens)
    for t in s.triplets:
        print(t.head, t.tail, t.label)

from wrapper import Generator

model = Generator(load_dir="gpt2", save_dir="outputs/wrapper/fewrel/unseen_10_seed_0/generator")
model.generate(labels=["location", "religion"], path_out="synthetic.jsonl")

from wrapper import Extractor

model = Extractor(load_dir="facebook/bart-base", save_dir="outputs/wrapper/fewrel/unseen_10_seed_0/extractor_final")
model.predict(path_in=path_test, path_out="pred.jsonl")

from pathlib import Path
from wrapper import Generator, Extractor

generator = Generator(
    load_dir="gpt2",
    save_dir=str(Path(save_dir) / "generator"),
)
extractor = Extractor(
    load_dir="facebook/bart-base",
    save_dir=str(Path(save_dir) / "extractor"),
)
generator.fit(path_train, path_dev)
extractor.fit(path_train, path_dev)

generator.generate(labels_test, path_out=path_synthetic)

extractor_final = Extractor(
    load_dir=str(Path(save_dir) / "extractor" / "model"),
    save_dir=str(Path(save_dir) / "extractor_final"),
)
extractor_final.fit(path_synthetic, path_dev)
extractor_final.predict(path_in=path_test, path_out=path_pred)

python wrapper.py main \
--path_train outputs/data/splits/zero_rte/fewrel/unseen_10_seed_0/train.jsonl \                                       
--path_dev outputs/data/splits/zero_rte/fewrel/unseen_10_seed_0/dev.jsonl \                                           
--path_test outputs/data/splits/zero_rte/fewrel/unseen_10_seed_0/test.jsonl \                                         
--save_dir outputs/wrapper/fewrel/unseen_10_seed_0   

python wrapper.py run_eval \                                                                                               
--path_model outputs/wrapper/fewrel/unseen_10_seed_0/extractor_final \                                                  
--path_test outputs/data/splits/zero_rte/fewrel/unseen_10_seed_0/test.jsonl \
--mode single

python wrapper.py run_eval \                                                                                               
--path_model outputs/wrapper/fewrel/unseen_10_seed_0/extractor_final \                                                  
--path_test outputs/data/splits/zero_rte/fewrel/unseen_10_seed_0/test.jsonl \
--mode multi

@inproceedings{chia-etal-2022-relationprompt,
    title = "{R}elation{P}rompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction",
    author = "Chia, Yew Ken  and
      Bing, Lidong  and
      Poria, Soujanya  and
      Si, Luo",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-acl.5",
    doi = "10.18653/v1/2022.findings-acl.5",
    pages = "45--57",
    abstract = "Despite the importance of relation extraction in building and representing knowledge, less research is focused on generalizing to unseen relations types. We introduce the task setting of Zero-Shot Relation Triplet Extraction (ZeroRTE) to encourage further research in low-resource relation extraction methods. Given an input sentence, each extracted triplet consists of the head entity, relation label, and tail entity where the relation label is not seen at the training stage. To solve ZeroRTE, we propose to synthesize relation examples by prompting language models to generate structured texts. Concretely, we unify language model prompts and structured text approaches to design a structured prompt template for generating synthetic relation samples when conditioning on relation label prompts (RelationPrompt). To overcome the limitation for extracting multiple relation triplets in a sentence, we design a novel Triplet Search Decoding method. Experiments on FewRel and Wiki-ZSL datasets show the efficacy of RelationPrompt for the ZeroRTE task and zero-shot relation classification. Our code and data are available at github.com/declare-lab/RelationPrompt.",
}