# The 16-language multilingual module is the default but feel free
# to pick others from the list and compare the results.
module_url = 'https://tfhub.dev/google/universal-sentence-encoder-multilingual/3'

model = hub.load(module_url)

def embed_text(input):
  return model(input)

# Some texts of different lengths in different languages.
arabic_sentences = ['كلب', 'الجراء لطيفة.', 'أستمتع بالمشي لمسافات طويلة على طول الشاطئ مع كلبي.']
chinese_sentences = ['狗', '小狗很好。', '我喜欢和我的狗一起沿着海滩散步。']
english_sentences = ['dog', 'Puppies are nice.', 'I enjoy taking long walks along the beach with my dog.']
french_sentences = ['chien', 'Les chiots sont gentils.', 'J\'aime faire de longues promenades sur la plage avec mon chien.']
german_sentences = ['Hund', 'Welpen sind nett.', 'Ich genieße lange Spaziergänge am Strand entlang mit meinem Hund.']
italian_sentences = ['cane', 'I cuccioli sono carini.', 'Mi piace fare lunghe passeggiate lungo la spiaggia con il mio cane.']
japanese_sentences = ['犬', '子犬はいいです', '私は犬と一緒にビーチを散歩するのが好きです']
korean_sentences = ['개', '강아지가 좋다.', '나는 나의 개와 해변을 따라 길게 산책하는 것을 즐긴다.']
russian_sentences = ['собака', 'Милые щенки.', 'Мне нравится подолгу гулять по пляжу со своей собакой.']
spanish_sentences = ['perro', 'Los cachorros son agradables.', 'Disfruto de dar largos paseos por la playa con mi perro.']

# Multilingual example
multilingual_example = ["Willkommen zu einfachen, aber", "verrassend krachtige", "multilingüe", "compréhension du langage naturel", "модели.", "大家是什么意思" , "보다 중요한", ".اللغة التي يتحدثونها"]
multilingual_example_in_en =  ["Welcome to simple yet", "surprisingly powerful", "multilingual", "natural language understanding", "models.", "What people mean", "matters more than", "the language they speak."]

# Compute embeddings.
ar_result = embed_text(arabic_sentences)
en_result = embed_text(english_sentences)
es_result = embed_text(spanish_sentences)
de_result = embed_text(german_sentences)
fr_result = embed_text(french_sentences)
it_result = embed_text(italian_sentences)
ja_result = embed_text(japanese_sentences)
ko_result = embed_text(korean_sentences)
ru_result = embed_text(russian_sentences)
zh_result = embed_text(chinese_sentences)

multilingual_result = embed_text(multilingual_example)
multilingual_in_en_result = embed_text(multilingual_example_in_en)

visualize_similarity(multilingual_in_en_result, multilingual_result,
                     multilingual_example_in_en, multilingual_example,  "Multilingual Universal Sentence Encoder for Semantic Retrieval (Yang et al., 2019)")

visualize_similarity(en_result, ar_result, english_sentences, arabic_sentences, 'English-Arabic Similarity')

visualize_similarity(en_result, ru_result, english_sentences, russian_sentences, 'English-Russian Similarity')

visualize_similarity(en_result, es_result, english_sentences, spanish_sentences, 'English-Spanish Similarity')

visualize_similarity(en_result, it_result, english_sentences, italian_sentences, 'English-Italian Similarity')

visualize_similarity(it_result, es_result, italian_sentences, spanish_sentences, 'Italian-Spanish Similarity')

visualize_similarity(en_result, zh_result, english_sentences, chinese_sentences, 'English-Chinese Similarity')

visualize_similarity(en_result, ko_result, english_sentences, korean_sentences, 'English-Korean Similarity')

visualize_similarity(zh_result, ko_result, chinese_sentences, korean_sentences, 'Chinese-Korean Similarity')

corpus_metadata = [
    ('ar', 'ar-en.txt.zip', 'News-Commentary.ar-en.ar', 'Arabic'),
    ('zh', 'en-zh.txt.zip', 'News-Commentary.en-zh.zh', 'Chinese'),
    ('en', 'en-es.txt.zip', 'News-Commentary.en-es.en', 'English'),
    ('ru', 'en-ru.txt.zip', 'News-Commentary.en-ru.ru', 'Russian'),
    ('es', 'en-es.txt.zip', 'News-Commentary.en-es.es', 'Spanish'),
]

language_to_sentences = {}
language_to_news_path = {}
for language_code, zip_file, news_file, language_name in corpus_metadata:
  zip_path = tf.keras.utils.get_file(
      fname=zip_file,
      origin='http://opus.nlpl.eu/download.php?f=News-Commentary/v11/moses/' + zip_file,
      extract=True)
  news_path = os.path.join(os.path.dirname(zip_path), news_file)
  language_to_sentences[language_code] = pd.read_csv(news_path, sep='\t', header=None)[0][:1000]
  language_to_news_path[language_code] = news_path

  print('{:,} {} sentences'.format(len(language_to_sentences[language_code]), language_name))

Downloading data from http://opus.nlpl.eu/download.php?f=News-Commentary/v11/moses/ar-en.txt.zip
24715264/24714354 [==============================] - 2s 0us/step
1,000 Arabic sentences
Downloading data from http://opus.nlpl.eu/download.php?f=News-Commentary/v11/moses/en-zh.txt.zip
18104320/18101984 [==============================] - 2s 0us/step
1,000 Chinese sentences
Downloading data from http://opus.nlpl.eu/download.php?f=News-Commentary/v11/moses/en-es.txt.zip
28106752/28106064 [==============================] - 2s 0us/step
1,000 English sentences
Downloading data from http://opus.nlpl.eu/download.php?f=News-Commentary/v11/moses/en-ru.txt.zip
24854528/24849511 [==============================] - 2s 0us/step
1,000 Russian sentences
1,000 Spanish sentences

# Takes about 3 minutes

batch_size = 2048
language_to_embeddings = {}
for language_code, zip_file, news_file, language_name in corpus_metadata:
  print('\nComputing {} embeddings'.format(language_name))
  with tqdm(total=len(language_to_sentences[language_code])) as pbar:
    for batch in pd.read_csv(language_to_news_path[language_code], sep='\t',header=None, chunksize=batch_size):
      language_to_embeddings.setdefault(language_code, []).extend(embed_text(batch[0]))
      pbar.update(len(batch))

0%|          | 0/1000 [00:00<?, ?it/s]
Computing Arabic embeddings
83178it [00:30, 2768.60it/s]
  0%|          | 0/1000 [00:00<?, ?it/s]
Computing Chinese embeddings
69206it [00:18, 3664.60it/s]
  0%|          | 0/1000 [00:00<?, ?it/s]
Computing English embeddings
238853it [00:37, 6319.00it/s]
  0%|          | 0/1000 [00:00<?, ?it/s]
Computing Russian embeddings
190092it [00:34, 5589.16it/s]
  0%|          | 0/1000 [00:00<?, ?it/s]
Computing Spanish embeddings
238819it [00:41, 5754.02it/s]

%%time

# Takes about 8 minutes

num_index_trees = 40
language_name_to_index = {}
embedding_dimensions = len(list(language_to_embeddings.values())[0][0])
for language_code, zip_file, news_file, language_name in corpus_metadata:
  print('\nAdding {} embeddings to index'.format(language_name))
  index = SimpleNeighbors(embedding_dimensions, metric='dot')

  for i in trange(len(language_to_sentences[language_code])):
    index.add_one(language_to_sentences[language_code][i], language_to_embeddings[language_code][i])

  print('Building {} index with {} trees...'.format(language_name, num_index_trees))
  index.build(n=num_index_trees)
  language_name_to_index[language_name] = index

0%|          | 1/1000 [00:00<02:21,  7.04it/s]
Adding Arabic embeddings to index
100%|██████████| 1000/1000 [02:06<00:00,  7.90it/s]
  0%|          | 1/1000 [00:00<01:53,  8.84it/s]
Building Arabic index with 40 trees...

Adding Chinese embeddings to index
100%|██████████| 1000/1000 [02:05<00:00,  7.99it/s]
  0%|          | 1/1000 [00:00<01:59,  8.39it/s]
Building Chinese index with 40 trees...

Adding English embeddings to index
100%|██████████| 1000/1000 [02:07<00:00,  7.86it/s]
  0%|          | 1/1000 [00:00<02:17,  7.26it/s]
Building English index with 40 trees...

Adding Russian embeddings to index
100%|██████████| 1000/1000 [02:06<00:00,  7.91it/s]
  0%|          | 1/1000 [00:00<02:03,  8.06it/s]
Building Russian index with 40 trees...

Adding Spanish embeddings to index
100%|██████████| 1000/1000 [02:07<00:00,  7.84it/s]
Building Spanish index with 40 trees...
CPU times: user 11min 21s, sys: 2min 14s, total: 13min 35s
Wall time: 10min 33s

%%time

# Takes about 13 minutes

num_index_trees = 60
print('Computing mixed-language index')
combined_index = SimpleNeighbors(embedding_dimensions, metric='dot')
for language_code, zip_file, news_file, language_name in corpus_metadata:
  print('Adding {} embeddings to mixed-language index'.format(language_name))
  for i in trange(len(language_to_sentences[language_code])):
    annotated_sentence = '({}) {}'.format(language_name, language_to_sentences[language_code][i])
    combined_index.add_one(annotated_sentence, language_to_embeddings[language_code][i])

print('Building mixed-language index with {} trees...'.format(num_index_trees))
combined_index.build(n=num_index_trees)

0%|          | 1/1000 [00:00<02:00,  8.29it/s]
Computing mixed-language index
Adding Arabic embeddings to mixed-language index
100%|██████████| 1000/1000 [02:06<00:00,  7.92it/s]
  0%|          | 1/1000 [00:00<02:24,  6.89it/s]
Adding Chinese embeddings to mixed-language index
100%|██████████| 1000/1000 [02:05<00:00,  7.95it/s]
  0%|          | 1/1000 [00:00<02:05,  7.98it/s]
Adding English embeddings to mixed-language index
100%|██████████| 1000/1000 [02:06<00:00,  7.88it/s]
  0%|          | 1/1000 [00:00<02:18,  7.20it/s]
Adding Russian embeddings to mixed-language index
100%|██████████| 1000/1000 [02:04<00:00,  8.03it/s]
  0%|          | 1/1000 [00:00<02:17,  7.28it/s]
Adding Spanish embeddings to mixed-language index
100%|██████████| 1000/1000 [02:06<00:00,  7.90it/s]
Building mixed-language index with 60 trees...
CPU times: user 11min 18s, sys: 2min 13s, total: 13min 32s
Wall time: 10min 30s

English sentences similar to: "The stock market fell four points."
['Nobel laureate Amartya Sen attributed the European crisis to four failures – political, economic, social, and intellectual.',
 'Just last December, fellow economists Martin Feldstein and Nouriel Roubini each penned op-eds bravely questioning bullish market sentiment, sensibly pointing out gold’s risks.',
 'His ratings have dipped below 50% for the first time.',
 'As a result, markets were deregulated, making it easier to trade assets that were perceived to be safe, but were in fact not.',
 'Consider the advanced economies.',
 'But the agreement has three major flaws.',
 'This “predetermined equilibrium” thinking – reflected in the view that markets always self-correct – led to policy paralysis until the Great Depression, when John Maynard Keynes’s argument for government intervention to address unemployment and output gaps gained traction.',
 'Officials underestimated tail risks.',
 'Consider a couple of notorious examples.',
 'Stalin was content to settle for an empire in Eastern Europe.']

English sentences similar to: "The stock market fell four points."
['Nobel laureate Amartya Sen attributed the European crisis to four failures – political, economic, social, and intellectual.',
 'It was part of the 1945 consensus.',
 'The end of the East-West ideological divide and the end of absolute faith in markets are historical turning points.',
 'Just last December, fellow economists Martin Feldstein and Nouriel Roubini each penned op-eds bravely questioning bullish market sentiment, sensibly pointing out gold’s risks.',
 'His ratings have dipped below 50% for the first time.',
 'As a result, markets were deregulated, making it easier to trade assets that were perceived to be safe, but were in fact not.',
 'Consider the advanced economies.',
 'Since their articles appeared, the price of gold has moved up still further.',
 'But the agreement has three major flaws.',
 'Gold prices even hit a record-high $1,300 recently.',
 'This “predetermined equilibrium” thinking – reflected in the view that markets always self-correct – led to policy paralysis until the Great Depression, when John Maynard Keynes’s argument for government intervention to address unemployment and output gaps gained traction.',
 'What Failed in 2008?',
 'Officials underestimated tail risks.',
 'Consider a couple of notorious examples.',
 'One of these species, orange roughy, has been caught commercially for only around a quarter-century, but already is being fished to the point of collapse.',
 'Meanwhile, policymakers were lulled into complacency by the widespread acceptance of economic theories such as the “efficient-market hypothesis,” which assumes that investors act rationally and use all available information when making their decisions.',
 'Stalin was content to settle for an empire in Eastern Europe.',
 'Intelligence assets have been redirected.',
 'A new wave of what the economist Joseph Schumpeter famously called “creative destruction” is under way: even as central banks struggle to maintain stability by flooding markets with liquidity, credit to business and households is shrinking.',
 'It all came about in a number of ways.',
 'The UN, like the dream of European unity, was also part of the 1945 consensus.',
 'The End of 1945',
 'The Global Economy’s New Path',
 'But this scenario failed to materialize.',
 'Gold prices are extremely sensitive to global interest-rate movements.',
 'Fukushima has presented the world with a far-reaching, fundamental choice.',
 'It was Japan, the high-tech country par excellence (not the latter-day Soviet Union) that proved unable to take adequate precautions to avert disaster in four reactor blocks.',
 'Some European academics tried to argue that there was no need for US-like fiscal transfers, because any desired degree of risk sharing can, in theory, be achieved through financial markets.',
 '$10,000 Gold?',
 'One answer, of course, is a complete collapse of the US dollar.',
 '1929 or 1989?',
 'The goods we made were what economists call “rival" and “excludible" commodities.',
 'This dream quickly faded when the Cold War divided the world into two hostile blocs. But in some ways the 1945 consensus, in the West, was strengthened by Cold War politics.',
 'The first flaw is that the spending reductions are badly timed: coming as they do when the US economy is weak, they risk triggering another recession.',
 'One successful gold investor recently explained to me that stock prices languished for a more than a decade before the Dow Jones index crossed the 1,000 mark in the early 1980’s.',
 'Eichengreen traces our tepid response to the crisis to the triumph of monetarist economists, the disciples of Milton Friedman, over their Keynesian and Minskyite peers – at least when it comes to interpretations of the causes and consequences of the Great Depression.',
 "However, America's unilateral options are limited.",
 'Once it was dark, a screen was set up and Mark showed home videos from space.',
 'These aspirations were often voiced in the United Nations, founded in 1945.',
 'Then I got distracted for about 40 years.']

English sentences similar to: "The stock market fell four points."
['(Chinese) 新兴市场的号角',
 '(English) It was part of the 1945 consensus.',
 '(Russian) Брюссель. Цунами, пронёсшееся по финансовым рынкам, является глобальной катастрофой.',
 '(Arabic) هناك أربعة شروط مسبقة لتحقيق النجاح الأوروبي في أفغانستان:',
 '(Spanish) Su índice de popularidad ha caído por primera vez por debajo del 50 por ciento.',
 '(English) His ratings have dipped below 50% for the first time.',
 '(Russian) Впервые его рейтинг опустился ниже 50%.',
 '(English) As a result, markets were deregulated, making it easier to trade assets that were perceived to be safe, but were in fact not.',
 '(Arabic) وكانت التطورات التي شهدتها سوق العمل أكثر تشجيعا، فهي على النقيض من أسواق الأصول تعكس النتائج وليس التوقعات. وهنا أيضاً كانت الأخبار طيبة. فقد أصبحت سوق العمل أكثر إحكاما، حيث ظلت البطالة عند مستوى 3.5% وكانت نسبة الوظائف إلى الطلبات المقدمة فوق مستوى التعادل.',
 '(Russian) Это было частью консенсуса 1945 года.',
 '(English) Consider the advanced economies.',
 '(English) Since their articles appeared, the price of gold has moved up still further.',
 '(Russian) Тогда они не только смогут накормить свои семьи, но и начать получать рыночную прибыль и откладывать деньги на будущее.',
 '(English) Gold prices even hit a record-high $1,300 recently.',
 '(Chinese) 另一种金融危机',
 '(Russian) Европейская мечта находится в кризисе.',
 '(English) What Failed in 2008?',
 '(Spanish) Pero el acuerdo alcanzado tiene tres grandes defectos.',
 '(English) Officials underestimated tail risks.',
 '(English) Consider a couple of notorious examples.',
 '(Spanish) Los mercados financieros pueden ser frágiles y ofrecen muy poca capacidad de compartir los riesgos relacionados con el ingreso de los trabajadores, que constituye la mayor parte de la renta de cualquier economía avanzada.',
 '(Chinese) 2008年败在何处？',
 '(Spanish) Consideremos las economías avanzadas.',
 '(Spanish) Los bienes producidos se caracterizaron por ser, como señalaron algunos economistas, mercancías “rivales” y “excluyentes”.',
 '(Arabic) إغلاق الفجوة الاستراتيجية في أوروبا',
 '(English) Stalin was content to settle for an empire in Eastern Europe.',
 '(English) Intelligence assets have been redirected.',
 '(Spanish) Hoy, envalentonados por la apreciación continua, algunos están sugiriendo que el oro podría llegar incluso a superar esa cifra.',
 '(Russian) Цены на золото чрезвычайно чувствительны к мировым движениям процентных ставок.',
 '(Russian) Однако у достигнутой договоренности есть три основных недостатка.']