Example #1
0
def init_query_encoder(encoder, tokenizer_name, topics_name, encoded_queries,
                       device, prefix):
    encoded_queries_map = {
        'msmarco-passage-dev-subset': 'tct_colbert-msmarco-passage-dev-subset',
        'dpr-nq-dev': 'dpr_multi-nq-dev',
        'dpr-nq-test': 'dpr_multi-nq-test',
        'dpr-trivia-dev': 'dpr_multi-trivia-dev',
        'dpr-trivia-test': 'dpr_multi-trivia-test',
        'dpr-wq-test': 'dpr_multi-wq-test',
        'dpr-squad-test': 'dpr_multi-squad-test',
        'dpr-curated-test': 'dpr_multi-curated-test'
    }
    if encoder:
        if 'dkrr' in encoder:
            return DkrrDprQueryEncoder(encoder_dir=encoder,
                                       device=device,
                                       prefix=prefix)
        elif 'dpr' in encoder:
            return DprQueryEncoder(encoder_dir=encoder,
                                   tokenizer_name=tokenizer_name,
                                   device=device)
        elif 'bpr' in encoder:
            return BprQueryEncoder(encoder_dir=encoder,
                                   tokenizer_name=tokenizer_name,
                                   device=device)
        elif 'tct_colbert' in encoder:
            return TctColBertQueryEncoder(encoder_dir=encoder,
                                          tokenizer_name=tokenizer_name,
                                          device=device)
        elif 'ance' in encoder:
            return AnceQueryEncoder(encoder_dir=encoder,
                                    tokenizer_name=tokenizer_name,
                                    device=device)
        elif 'sentence' in encoder:
            return AutoQueryEncoder(encoder_dir=encoder,
                                    tokenizer_name=tokenizer_name,
                                    device=device,
                                    pooling='mean',
                                    l2_norm=True)
        else:
            return AutoQueryEncoder(encoder_dir=encoder,
                                    tokenizer_name=tokenizer_name,
                                    device=device)

    if encoded_queries:
        if os.path.exists(encoded_queries):
            if 'bpr' in encoded_queries:
                return BprQueryEncoder(encoded_query_dir=encoded_queries)
            else:
                return QueryEncoder(encoded_queries)
        else:
            if 'bpr' in encoded_queries:
                return BprQueryEncoder.load_encoded_queries(encoded_queries)
            else:
                return QueryEncoder.load_encoded_queries(encoded_queries)

    if topics_name in encoded_queries_map:
        return QueryEncoder.load_encoded_queries(
            encoded_queries_map[topics_name])
    raise ValueError(f'No encoded queries for topic {topics_name}')
Example #2
0
 def test_msmarco_passage_ance_encoded_queries(self):
     encoder = QueryEncoder.load_encoded_queries(
         'ance-msmarco-passage-dev-subset')
     topics = get_topics('msmarco-passage-dev-subset')
     for t in topics:
         self.assertTrue(topics[t]['title'] in encoder.embedding)
Example #3
0
 def test_trivia_test_ance_encoded_queries(self):
     encoder = QueryEncoder.load_encoded_queries('dpr_multi-trivia-test')
     topics = get_topics('dpr-trivia-test')
     for t in topics:
         self.assertTrue(topics[t]['title'] in encoder.embedding)
Example #4
0
 def test_msmarco_doc_ance_bf_encoded_queries(self):
     encoder = QueryEncoder.load_encoded_queries(
         'ance_maxp-msmarco-doc-dev')
     topics = get_topics('msmarco-doc-dev')
     for t in topics:
         self.assertTrue(topics[t]['title'] in encoder.embedding)
Example #5
0
 def test_dpr_squad_test_encoded_queries(self):
     encoder = QueryEncoder.load_encoded_queries('dpr_multi-squad-test')
     topics = get_topics('dpr-squad-test')
     for t in topics:
         self.assertTrue(topics[t]['title'] in encoder.embedding)
 def test_msmarco_passage_tct_colbert_v2_hnp_encoded_queries(self):
     encoder = QueryEncoder.load_encoded_queries(
         'tct_colbert-v2-hnp-msmarco-passage-dev-subset')
     topics = get_topics('msmarco-passage-dev-subset')
     for t in topics:
         self.assertTrue(topics[t]['title'] in encoder.embedding)