文档与Word Mover距离和Bert-Embedding的相似性

Question

我正在尝试使用基于Google's BERT的单词嵌入来计算两个任意文档的文档相似度（最近邻居）。为了从Bert获得单词嵌入，我使用bert-as-a-service。文档相似性应基于使用python wmd-relax包的Word-Mover-Distance。

我以前的尝试是从qazxsw poi github repo的本教程开始的：qazxsw poi

wmd-relax

不幸的是，计算失败，距离计算中的尺寸不匹配：https://github.com/src-d/wmd-relax/blob/master/spacy_example.py

Answer 1

import numpy as np
import spacy
import requests
from wmd import WMD
from collections import Counter
from bert_serving.client import BertClient

# Wikipedia titles
titles = ["Germany", "Spain", "Google", "Apple"]

# Standard model from spacy
nlp = spacy.load("en_vectors_web_lg")

# Fetch wiki articles and prepare as specy document
documents_spacy = {}
print('Create spacy document')
for title in titles:
    print("... fetching", title)
    pages = requests.get(
        "https://en.wikipedia.org/w/api.php?action=query&format=json&titles=%s"
        "&prop=extracts&explaintext" % title).json()["query"]["pages"]
    text = nlp(next(iter(pages.values()))["extract"])
    tokens = [t for t in text if t.is_alpha and not t.is_stop]
    words = Counter(t.text for t in tokens)
    orths = {t.text: t.orth for t in tokens}
    sorted_words = sorted(words)
    documents_spacy[title] = (title, [orths[t] for t in sorted_words],
                              np.array([words[t] for t in sorted_words],
                                       dtype=np.float32))


# This is the original embedding class with the model from spacy
class SpacyEmbeddings(object):
    def __getitem__(self, item):
        return nlp.vocab[item].vector


# Bert Embeddings using bert-as-as-service
class BertEmbeddings:
    def __init__(self, ip='localhost', port=5555, port_out=5556):
        self.server = BertClient(ip=ip, port=port, port_out=port_out)

    def __getitem__(self, item):
        text = nlp.vocab[item].text
        emb = self.server.encode([text])
        return emb


# Get the nearest neighbor of one of the atricles
calc_bert = WMD(BertEmbeddings(), documents_spacy)
calc_bert.nearest_neighbors(titles[0])

输出的形状是（batch_size，sequence_len，embedding_dimension。在你的情况下，sequence_len是1，因为你正在汇集结果。

现在，您可以使用ValueError: shapes (812,1,768) and (768,1,812) not aligned: 768 (dim 2) != 1 (dim 1)的bert-as-service方法转置另一个与此匹配。