Edit model card

REDFM: a Filtered and Multilingual Relation Extraction Dataset

This is a multilingual version of REBEL. It can be used as a standalone multulingual Relation Extraction system, or as a pretrained system to be tuned on multilingual Relation Extraction datasets.

mREBEL is introduced in the ACL 2023 paper RED^{FM}: a Filtered and Multilingual Relation Extraction Dataset. We present a new multilingual Relation Extraction dataset and train a multilingual version of REBEL which reframed Relation Extraction as a seq2seq task. The paper can be found here. If you use the code or model, please reference this work in your paper:

@inproceedings{huguet-cabot-et-al-2023-redfm-dataset,
    title = "RED$^{\rm FM}$: a Filtered and Multilingual Relation Extraction Dataset",
    author = "Huguet Cabot, Pere-Llu{\'\i}s  and Tedeschi, Simone and Ngonga Ngomo, Axel-Cyrille and
      Navigli, Roberto",
    booktitle = "Proc. of the 61st Annual Meeting of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2306.09802",
}

The original repository for the paper can be found here

Be aware that the inference widget at the right does not output special tokens, which are necessary to distinguish the subject, object and relation types. For a demo of mREBEL and its pre-training dataset check the Spaces demo.

Pipeline usage

from transformers import pipeline

triplet_extractor = pipeline('translation_xx_to_yy', model='Babelscape/mrebel-base', tokenizer='Babelscape/mrebel-base')
# We need to use the tokenizer manually since we need special tokens.
extracted_text = triplet_extractor.tokenizer.batch_decode([triplet_extractor("The Red Hot Chili Peppers were formed in Los Angeles by Kiedis, Flea, guitarist Hillel Slovak and drummer Jack Irons.", src_lang="en", return_tensors=True, return_text=False)[0]["translation_token_ids"]]) # change __en__ for the language of the source.
print(extracted_text[0])
# Function to parse the generated text and extract the triplets
def extract_triplets_typed(text):
    triplets = []
    relation = ''
    text = text.strip()
    current = 'x'
    subject, relation, object_, object_type, subject_type = '','','','',''

    for token in text.replace("<s>", "").replace("<pad>", "").replace("</s>", "").replace("tp_XX", "").replace("__en__", "").split():
        if token == "<triplet>" or token == "<relation>":
            current = 't'
            if relation != '':
                triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
                relation = ''
            subject = ''
        elif token.startswith("<") and token.endswith(">"):
            if current == 't' or current == 'o':
                current = 's'
                if relation != '':
                    triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
                object_ = ''
                subject_type = token[1:-1]
            else:
                current = 'o'
                object_type = token[1:-1]
                relation = ''
        else:
            if current == 't':
                subject += ' ' + token
            elif current == 's':
                object_ += ' ' + token
            elif current == 'o':
                relation += ' ' + token
    if subject != '' and relation != '' and object_ != '' and object_type != '' and subject_type != '':
        triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
    return triplets
extracted_triplets = extract_triplets_typed(extracted_text[0])
print(extracted_triplets)

Model and Tokenizer using transformers

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

def extract_triplets_typed(text):
    triplets = []
    relation = ''
    text = text.strip()
    current = 'x'
    subject, relation, object_, object_type, subject_type = '','','','',''

    for token in text.replace("<s>", "").replace("<pad>", "").replace("</s>", "").replace("tp_XX", "").replace("__en__", "").split():
        if token == "<triplet>" or token == "<relation>":
            current = 't'
            if relation != '':
                triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
                relation = ''
            subject = ''
        elif token.startswith("<") and token.endswith(">"):
            if current == 't' or current == 'o':
                current = 's'
                if relation != '':
                    triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
                object_ = ''
                subject_type = token[1:-1]
            else:
                current = 'o'
                object_type = token[1:-1]
                relation = ''
        else:
            if current == 't':
                subject += ' ' + token
            elif current == 's':
                object_ += ' ' + token
            elif current == 'o':
                relation += ' ' + token
    if subject != '' and relation != '' and object_ != '' and object_type != '' and subject_type != '':
        triplets.append({'head': subject.strip(), 'head_type': subject_type, 'type': relation.strip(),'tail': object_.strip(), 'tail_type': object_type})
    return triplets

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Babelscape/mrebel-base", src_lang="en", tgt_lang="en") 
# Here we set English ("en") as source language. To change the source language swap the first token of the input for your desired language or change to supported language. 
model = AutoModelForSeq2SeqLM.from_pretrained("Babelscape/mrebel-base")
gen_kwargs = {
    "max_length": 256,
    "length_penalty": 0,
    "num_beams": 3,
    "num_return_sequences": 3,
    "forced_bos_token_id": None,
}

# Text to extract triplets from
text = 'The Red Hot Chili Peppers were formed in Los Angeles by Kiedis, Flea, guitarist Hillel Slovak and drummer Jack Irons.'

# Tokenizer text
model_inputs = tokenizer(text, max_length=256, padding=True, truncation=True, return_tensors = 'pt')

# Generate
generated_tokens = model.generate(
    model_inputs["input_ids"].to(model.device),
    attention_mask=model_inputs["attention_mask"].to(model.device),
    **gen_kwargs,
)

# Extract text
decoded_preds = tokenizer.batch_decode(generated_tokens, skip_special_tokens=False)

# Extract triplets
for idx, sentence in enumerate(decoded_preds):
    print(f'Prediction triplets sentence {idx}')
    print(extract_triplets_typed(sentence))

License

This model is licensed under the CC BY-SA 4.0 license. The text of the license can be found here.

Downloads last month
137
Safetensors
Model size
484M params
Tensor type
F32
·