🔑 关键短语提取模型：KBIR-inspec

from transformers import (
    TokenClassificationPipeline,
    AutoModelForTokenClassification,
    AutoTokenizer,
)
from transformers.pipelines import AggregationStrategy
import numpy as np
import torch
import torch_npu

# Define keyphrase extraction pipeline
class KeyphraseExtractionPipeline(TokenClassificationPipeline):
    def __init__(self, model, *args, **kwargs):
        super().__init__(
            model=AutoModelForTokenClassification.from_pretrained(model),
            tokenizer=AutoTokenizer.from_pretrained(model),
            *args,
            **kwargs
        )

    def postprocess(self, all_outputs):
        results = super().postprocess(
            all_outputs=all_outputs,
            aggregation_strategy=AggregationStrategy.SIMPLE,
        )
        return np.unique([result.get("word").strip() for result in results])

# Load pipeline
device = torch.device('npu:0')
model_name = "ml6team/keyphrase-extraction-kbir-inspec"
extractor = KeyphraseExtractionPipeline(model=model_name)to(device)

# Inference
text = """
Keyphrase extraction is a technique in text analysis where you extract the
important keyphrases from a document. Thanks to these keyphrases humans can
understand the content of a text very quickly and easily without reading it
completely. Keyphrase extraction was first done primarily by human annotators,
who read the text in detail and then wrote down the most important keyphrases.
The disadvantage is that if you work with a lot of documents, this process
can take a lot of time. 

Here is where Artificial Intelligence comes in. Currently, classical machine
learning methods, that use statistical and linguistic features, are widely used
for the extraction process. Now with deep learning, it is possible to capture
the semantic meaning of a text even better than these classical methods.
Classical methods look at the frequency, occurrence and order of words
in the text, whereas these neural approaches can capture long-term
semantic dependencies and context of words in a text.
""".replace("\n", " ")

keyphrases = extractor(text)

print(keyphrases)

# Output
['Artificial Intelligence' 'Keyphrase extraction' 'deep learning'
 'linguistic features' 'machine learning' 'semantic meaning'
 'text analysis']

from datasets import load_dataset
from transformers import AutoTokenizer

# Labels
label_list = ["B", "I", "O"]
lbl2idx = {"B": 0, "I": 1, "O": 2}
idx2label = {0: "B", 1: "I", 2: "O"}

# Tokenizer
tokenizer = AutoTokenizer.from_pretrained("bloomberg/KBIR", add_prefix_space=True)
max_length = 512

# Dataset parameters
dataset_full_name = "midas/inspec"
dataset_subset = "raw"
dataset_document_column = "document"
dataset_biotags_column = "doc_bio_tags"

def preprocess_fuction(all_samples_per_split):
    tokenized_samples = tokenizer.batch_encode_plus(
        all_samples_per_split[dataset_document_column],
        padding="max_length",
        truncation=True,
        is_split_into_words=True,
        max_length=max_length,
    )
    total_adjusted_labels = []
    for k in range(0, len(tokenized_samples["input_ids"])):
        prev_wid = -1
        word_ids_list = tokenized_samples.word_ids(batch_index=k)
        existing_label_ids = all_samples_per_split[dataset_biotags_column][k]
        i = -1
        adjusted_label_ids = []

        for wid in word_ids_list:
            if wid is None:
                adjusted_label_ids.append(lbl2idx["O"])
            elif wid != prev_wid:
                i = i + 1
                adjusted_label_ids.append(lbl2idx[existing_label_ids[i]])
                prev_wid = wid
            else:
                adjusted_label_ids.append(
                    lbl2idx[
                        f"{'I' if existing_label_ids[i] == 'B' else existing_label_ids[i]}"
                    ]
                )

        total_adjusted_labels.append(adjusted_label_ids)
    tokenized_samples["labels"] = total_adjusted_labels
    return tokenized_samples

# Load dataset
dataset = load_dataset(dataset_full_name, dataset_subset)

# Preprocess dataset
tokenized_dataset = dataset.map(preprocess_fuction, batched=True)
    

# Define post_process functions
def concat_tokens_by_tag(keyphrases):
    keyphrase_tokens = []
    for id, label in keyphrases:
        if label == "B":
            keyphrase_tokens.append([id])
        elif label == "I":
            if len(keyphrase_tokens) > 0:
                keyphrase_tokens[len(keyphrase_tokens) - 1].append(id)
    return keyphrase_tokens


def extract_keyphrases(example, predictions, tokenizer, index=0):
    keyphrases_list = [
        (id, idx2label[label])
        for id, label in zip(
            np.array(example["input_ids"]).squeeze().tolist(), predictions[index]
        )
        if idx2label[label] in ["B", "I"]
    ]

    processed_keyphrases = concat_tokens_by_tag(keyphrases_list)
    extracted_kps = tokenizer.batch_decode(
        processed_keyphrases,
        skip_special_tokens=True,
        clean_up_tokenization_spaces=True,
    )
    return np.unique([kp.strip() for kp in extracted_kps])