code/run_mrqa.py [314:357]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            unique_id += 1

    return features


def _improve_answer_span(doc_tokens, input_start, input_end, tokenizer,
                         orig_answer_text):
    """Returns tokenized answer spans that better match the annotated answer."""
    tok_answer_text = " ".join(tokenizer.tokenize(orig_answer_text))

    for new_start in range(input_start, input_end + 1):
        for new_end in range(input_end, new_start - 1, -1):
            text_span = " ".join(doc_tokens[new_start:(new_end + 1)])
            if text_span == tok_answer_text:
                return (new_start, new_end)

    return (input_start, input_end)


def _check_is_max_context(doc_spans, cur_span_index, position):
    """Check if this is the 'max context' doc span for the token."""
    best_score = None
    best_span_index = None
    for (span_index, doc_span) in enumerate(doc_spans):
        end = doc_span.start + doc_span.length - 1
        if position < doc_span.start:
            continue
        if position > end:
            continue
        num_left_context = position - doc_span.start
        num_right_context = end - position
        score = min(num_left_context, num_right_context) + 0.01 * doc_span.length
        if best_score is None or score > best_score:
            best_score = score
            best_span_index = span_index

    return cur_span_index == best_span_index


RawResult = collections.namedtuple("RawResult",
                                   ["unique_id", "start_logits", "end_logits"])


def make_predictions(all_examples, all_features, all_results, n_best_size,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



code/run_squad.py [326:369]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            unique_id += 1

    return features


def _improve_answer_span(doc_tokens, input_start, input_end, tokenizer,
                         orig_answer_text):
    """Returns tokenized answer spans that better match the annotated answer."""
    tok_answer_text = " ".join(tokenizer.tokenize(orig_answer_text))

    for new_start in range(input_start, input_end + 1):
        for new_end in range(input_end, new_start - 1, -1):
            text_span = " ".join(doc_tokens[new_start:(new_end + 1)])
            if text_span == tok_answer_text:
                return (new_start, new_end)

    return (input_start, input_end)


def _check_is_max_context(doc_spans, cur_span_index, position):
    """Check if this is the 'max context' doc span for the token."""
    best_score = None
    best_span_index = None
    for (span_index, doc_span) in enumerate(doc_spans):
        end = doc_span.start + doc_span.length - 1
        if position < doc_span.start:
            continue
        if position > end:
            continue
        num_left_context = position - doc_span.start
        num_right_context = end - position
        score = min(num_left_context, num_right_context) + 0.01 * doc_span.length
        if best_score is None or score > best_score:
            best_score = score
            best_span_index = span_index

    return cur_span_index == best_span_index


RawResult = collections.namedtuple("RawResult",
                                   ["unique_id", "start_logits", "end_logits"])


def make_predictions(all_examples, all_features, all_results, n_best_size,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -