// Setup and run just the initial segsearch on an established matrix,
// without doing any additional chopping or joining.
// (Internal factored version that can be used as part of the main SegSearch.)
void Wordrec::InitialSegSearch(WERD_RES* word_res, LMPainPoints* pain_points,
GenericVector<SegSearchPending>* pending,
BestChoiceBundle* best_choice_bundle,
BlamerBundle* blamer_bundle) {
if (segsearch_debug_level > 0) {
tprintf("Starting SegSearch on ratings matrix%s:\n",
wordrec_enable_assoc ? " (with assoc)" : "");
word_res->ratings->print(getDict().getUnicharset());
}
pain_points->GenerateInitial(word_res);
// Compute scaling factor that will help us recover blob outline length
// from classifier rating and certainty for the blob.
float rating_cert_scale = -1.0 * getDict().certainty_scale / rating_scale;
language_model_->InitForWord(prev_word_best_choice_,
assume_fixed_pitch_char_segment,
segsearch_max_char_wh_ratio, rating_cert_scale);
// Initialize blamer-related information: map character boxes recorded in
// blamer_bundle->norm_truth_word to the corresponding i,j indices in the
// ratings matrix. We expect this step to succeed, since when running the
// chopper we checked that the correct chops are present.
if (blamer_bundle != NULL) {
blamer_bundle->SetupCorrectSegmentation(word_res->chopped_word,
wordrec_debug_blamer);
}
// pending[col] tells whether there is update work to do to combine
// best_choice_bundle->beam[col - 1] with some BLOB_CHOICEs in matrix[col, *].
// As the language model state is updated, pending entries are modified to
// minimize duplication of work. It is important that during the update the
// children are considered in the non-decreasing order of their column, since
// this guarantees that all the parents would be up to date before an update
// of a child is done.
pending->init_to_size(word_res->ratings->dimension(), SegSearchPending());
// Search the ratings matrix for the initial best path.
(*pending)[0].SetColumnClassified();
UpdateSegSearchNodes(rating_cert_scale, 0, pending, word_res,
pain_points, best_choice_bundle, blamer_bundle);
}
/**
* @name improve_by_chopping
*
* Repeatedly chops the worst blob, classifying the new blobs fixing up all
* the data, and incrementally runs the segmentation search until a good word
* is found, or no more chops can be found.
*/
void Wordrec::improve_by_chopping(float rating_cert_scale,
WERD_RES* word,
BestChoiceBundle* best_choice_bundle,
BlamerBundle* blamer_bundle,
LMPainPoints* pain_points,
GenericVector<SegSearchPending>* pending) {
int blob_number;
do { // improvement loop.
// Make a simple vector of BLOB_CHOICEs to make it easy to pick which
// one to chop.
GenericVector<BLOB_CHOICE*> blob_choices;
int num_blobs = word->ratings->dimension();
for (int i = 0; i < num_blobs; ++i) {
BLOB_CHOICE_LIST* choices = word->ratings->get(i, i);
if (choices == NULL || choices->empty()) {
blob_choices.push_back(NULL);
} else {
BLOB_CHOICE_IT bc_it(choices);
blob_choices.push_back(bc_it.data());
}
}
SEAM* seam = improve_one_blob(blob_choices, &best_choice_bundle->fixpt,
false, false, word, &blob_number);
if (seam == NULL) break;
// A chop has been made. We have to correct all the data structures to
// take into account the extra bottom-level blob.
// Put the seam into the seam_array and correct everything else on the
// word: ratings matrix (including matrix location in the BLOB_CHOICES),
// states in WERD_CHOICEs, and blob widths.
word->InsertSeam(blob_number, seam);
// Insert a new entry in the beam array.
best_choice_bundle->beam.insert(new LanguageModelState, blob_number);
// Fixpts are outdated, but will get recalculated.
best_choice_bundle->fixpt.clear();
// Remap existing pain points.
pain_points->RemapForSplit(blob_number);
// Insert a new pending at the chop point.
pending->insert(SegSearchPending(), blob_number);
// Classify the two newly created blobs using ProcessSegSearchPainPoint,
// as that updates the pending correctly and adds new pain points.
MATRIX_COORD pain_point(blob_number, blob_number);
ProcessSegSearchPainPoint(0.0f, pain_point, "Chop1", pending, word,
pain_points, blamer_bundle);
pain_point.col = blob_number + 1;
pain_point.row = blob_number + 1;
ProcessSegSearchPainPoint(0.0f, pain_point, "Chop2", pending, word,
pain_points, blamer_bundle);
if (language_model_->language_model_ngram_on) {
// N-gram evaluation depends on the number of blobs in a chunk, so we
// have to re-evaluate everything in the word.
ResetNGramSearch(word, best_choice_bundle, pending);
blob_number = 0;
}
// Run language model incrementally. (Except with the n-gram model on.)
UpdateSegSearchNodes(rating_cert_scale, blob_number, pending,
word, pain_points, best_choice_bundle, blamer_bundle);
} while (!language_model_->AcceptableChoiceFound() &&
word->ratings->dimension() < kMaxNumChunks);
// If after running only the chopper best_choice is incorrect and no blame
// has been yet set, blame the classifier if best_choice is classifier's
// top choice and is a dictionary word (i.e. language model could not have
// helped). Otherwise blame the tradeoff between the classifier and
// the old language model (permuters).
if (word->blamer_bundle != NULL &&
word->blamer_bundle->incorrect_result_reason() == IRR_CORRECT &&
!word->blamer_bundle->ChoiceIsCorrect(word->best_choice)) {
bool valid_permuter = word->best_choice != NULL &&
Dict::valid_word_permuter(word->best_choice->permuter(), false);
word->blamer_bundle->BlameClassifierOrLangModel(word,
getDict().getUnicharset(),
valid_permuter,
wordrec_debug_blamer);
}
}
