code/run_mrqa.py [191:261]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            tok_start_position = orig_to_tok_index[example.start_position]
            if example.end_position < len(example.doc_tokens) - 1:
                tok_end_position = orig_to_tok_index[example.end_position + 1] - 1
            else:
                tok_end_position = len(all_doc_tokens) - 1
            (tok_start_position, tok_end_position) = _improve_answer_span(
                all_doc_tokens, tok_start_position, tok_end_position, tokenizer,
                example.orig_answer_text)

        # The -3 accounts for [CLS], [SEP] and [SEP]
        max_tokens_for_doc = max_seq_length - len(query_tokens) - 3

        # We can have documents that are longer than the maximum sequence length.
        # To deal with this we do a sliding window approach, where we take chunks
        # of the up to our max length with a stride of `doc_stride`.
        _DocSpan = collections.namedtuple(  # pylint: disable=invalid-name
            "DocSpan", ["start", "length"])
        doc_spans = []
        start_offset = 0
        while start_offset < len(all_doc_tokens):
            length = len(all_doc_tokens) - start_offset
            if length > max_tokens_for_doc:
                length = max_tokens_for_doc
            doc_spans.append(_DocSpan(start=start_offset, length=length))
            if start_offset + length == len(all_doc_tokens):
                break
            start_offset += min(length, doc_stride)

        for (doc_span_index, doc_span) in enumerate(doc_spans):
            tokens = []
            token_to_orig_map = {}
            token_is_max_context = {}
            segment_ids = []
            tokens.append("[CLS]")
            segment_ids.append(0)
            for token in query_tokens:
                tokens.append(token)
                segment_ids.append(0)
            tokens.append("[SEP]")
            segment_ids.append(0)

            for i in range(doc_span.length):
                split_token_index = doc_span.start + i
                token_to_orig_map[len(tokens)] = tok_to_orig_index[split_token_index]

                is_max_context = _check_is_max_context(doc_spans, doc_span_index,
                                                       split_token_index)
                token_is_max_context[len(tokens)] = is_max_context
                tokens.append(all_doc_tokens[split_token_index])
                segment_ids.append(1)
            tokens.append("[SEP]")
            segment_ids.append(1)

            input_ids = tokenizer.convert_tokens_to_ids(tokens)

            # The mask has 1 for real tokens and 0 for padding tokens. Only real
            # tokens are attended to.
            input_mask = [1] * len(input_ids)

            # Zero-pad up to the sequence length.
            while len(input_ids) < max_seq_length:
                input_ids.append(0)
                input_mask.append(0)
                segment_ids.append(0)

            assert len(input_ids) == max_seq_length
            assert len(input_mask) == max_seq_length
            assert len(segment_ids) == max_seq_length

            start_position = None
            end_position = None
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



code/run_squad.py [206:269]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            tok_start_position = orig_to_tok_index[example.start_position]
            if example.end_position < len(example.doc_tokens) - 1:
                tok_end_position = orig_to_tok_index[example.end_position + 1] - 1
            else:
                tok_end_position = len(all_doc_tokens) - 1
            (tok_start_position, tok_end_position) = _improve_answer_span(
                all_doc_tokens, tok_start_position, tok_end_position, tokenizer,
                example.orig_answer_text)

        # The -3 accounts for [CLS], [SEP] and [SEP]
        max_tokens_for_doc = max_seq_length - len(query_tokens) - 3

        _DocSpan = collections.namedtuple(
            "DocSpan", ["start", "length"])
        doc_spans = []
        start_offset = 0
        while start_offset < len(all_doc_tokens):
            length = len(all_doc_tokens) - start_offset
            if length > max_tokens_for_doc:
                length = max_tokens_for_doc
            doc_spans.append(_DocSpan(start=start_offset, length=length))
            if start_offset + length == len(all_doc_tokens):
                break
            start_offset += min(length, doc_stride)

        for (doc_span_index, doc_span) in enumerate(doc_spans):
            tokens = []
            token_to_orig_map = {}
            token_is_max_context = {}
            segment_ids = []
            tokens.append("[CLS]")
            segment_ids.append(0)
            for token in query_tokens:
                tokens.append(token)
                segment_ids.append(0)
            tokens.append("[SEP]")
            segment_ids.append(0)

            for i in range(doc_span.length):
                split_token_index = doc_span.start + i
                token_to_orig_map[len(tokens)] = tok_to_orig_index[split_token_index]

                is_max_context = _check_is_max_context(doc_spans, doc_span_index,
                                                       split_token_index)
                token_is_max_context[len(tokens)] = is_max_context
                tokens.append(all_doc_tokens[split_token_index])
                segment_ids.append(1)
            tokens.append("[SEP]")
            segment_ids.append(1)

            input_ids = tokenizer.convert_tokens_to_ids(tokens)
            input_mask = [1] * len(input_ids)

            while len(input_ids) < max_seq_length:
                input_ids.append(0)
                input_mask.append(0)
                segment_ids.append(0)

            assert len(input_ids) == max_seq_length
            assert len(input_mask) == max_seq_length
            assert len(segment_ids) == max_seq_length

            start_position = None
            end_position = None
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -