/** * @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beam.insert(new LanguageModelState, blob_number); // Fixpts are outdated, but will get recalculated.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); } }
void Wordrec::SegSearch(WERD_RES* word_res, BestChoiceBundle* best_choice_bundle, BlamerBundle* blamer_bundle) { LMPainPoints pain_points(segsearch_max_pain_points, segsearch_max_char_wh_ratio, assume_fixed_pitch_char_segment, &getDict(), segsearch_debug_level); // 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; GenericVector<SegSearchPending> pending; InitialSegSearch(word_res, &pain_points, &pending, best_choice_bundle, blamer_bundle); if (!SegSearchDone(0)) { // find a better choice if (chop_enable && word_res->chopped_word != NULL) { improve_by_chopping(rating_cert_scale, word_res, best_choice_bundle, blamer_bundle, &pain_points, &pending); } if (chop_debug) SEAM::PrintSeams("Final seam list:", word_res->seam_array); if (blamer_bundle != NULL && !blamer_bundle->ChoiceIsCorrect(word_res->best_choice)) { blamer_bundle->SetChopperBlame(word_res, wordrec_debug_blamer); } } // Keep trying to find a better path by fixing the "pain points". MATRIX_COORD pain_point; float pain_point_priority; int num_futile_classifications = 0; STRING blamer_debug; while (wordrec_enable_assoc && (!SegSearchDone(num_futile_classifications) || (blamer_bundle != NULL && blamer_bundle->GuidedSegsearchStillGoing()))) { // Get the next valid "pain point". bool found_nothing = true; LMPainPointsType pp_type; while ((pp_type = pain_points.Deque(&pain_point, &pain_point_priority)) != LM_PPTYPE_NUM) { if (!pain_point.Valid(*word_res->ratings)) { word_res->ratings->IncreaseBandSize( pain_point.row - pain_point.col + 1); } if (pain_point.Valid(*word_res->ratings) && !word_res->ratings->Classified(pain_point.col, pain_point.row, getDict().WildcardID())) { found_nothing = false; break; } } if (found_nothing) { if (segsearch_debug_level > 0) tprintf("Pain points queue is empty\n"); break; } ProcessSegSearchPainPoint(pain_point_priority, pain_point, LMPainPoints::PainPointDescription(pp_type), &pending, word_res, &pain_points, blamer_bundle); UpdateSegSearchNodes(rating_cert_scale, pain_point.col, &pending, word_res, &pain_points, best_choice_bundle, blamer_bundle); if (!best_choice_bundle->updated) ++num_futile_classifications; if (segsearch_debug_level > 0) { tprintf("num_futile_classifications %d\n", num_futile_classifications); } best_choice_bundle->updated = false; // reset updated // See if it's time to terminate SegSearch or time for starting a guided // search for the true path to find the blame for the incorrect best_choice. if (SegSearchDone(num_futile_classifications) && blamer_bundle != NULL && blamer_bundle->GuidedSegsearchNeeded(word_res->best_choice)) { InitBlamerForSegSearch(word_res, &pain_points, blamer_bundle, &blamer_debug); } } // end while loop exploring alternative paths if (blamer_bundle != NULL) { blamer_bundle->FinishSegSearch(word_res->best_choice, wordrec_debug_blamer, &blamer_debug); } if (segsearch_debug_level > 0) { tprintf("Done with SegSearch (AcceptableChoiceFound: %d)\n", language_model_->AcceptableChoiceFound()); } }