d1f6748120abc8b1b0bfccd2e6ccc4142ba127d0,allennlp/modules/conditional_random_field.py,ConditionalRandomField,_joint_likelihood,#ConditionalRandomField#Any#Any#Any#,238

Before Change

            current_tag, next_tag = tags[i], tags[i+1]

            // The scores for transitioning from current_tag to next_tag
            transition_score = (
                    broadcast_transitions
                    // Choose the current_tag-th row for each input
                    .gather(1, current_tag.view(batch_size, 1, 1).expand(batch_size, 1, num_tags))
                    // Squeeze down to (batch_size, num_tags)
                    .squeeze(1)
                    // Then choose the next_tag-th column for each of those
                    .gather(1, next_tag.view(batch_size, 1))
                    // And squeeze down to (batch_size,)
                    .squeeze(1)
            )

            // The score for using current_tag
            emit_score = logits[i].gather(1, current_tag.view(batch_size, 1)).squeeze(1)

After Change

        // Transition from last state to "stop" state. To start with, we need to find the last tag
        // for each instance.
        last_tag_index = mask.sum(0).long() - 1
        last_tags = tags.gather(0, last_tag_index.view(1, batch_size)).squeeze(0)

        // Compute score of transitioning to `stop_tag` from each "last tag".
        if self.include_start_end_transitions:
            last_transition_score = self.end_transitions.index_select(0, last_tags)

Instances