summaryrefslogtreecommitdiff
path: root/klm/lm/ngram_query.hh
diff options
context:
space:
mode:
authorChris Dyer <redpony@gmail.com>2014-10-13 00:42:37 -0400
committerChris Dyer <redpony@gmail.com>2014-10-13 00:42:37 -0400
commitb1ed81ef3216b212295afa76c5d20a56fb647204 (patch)
tree9633cdc1b8a341dfa58b0b7fec0e2cae44d28835 /klm/lm/ngram_query.hh
parent1b17f61d359be6e1c3cea29f8c100db3bcdd73a0 (diff)
new kenlm
Diffstat (limited to 'klm/lm/ngram_query.hh')
-rw-r--r--klm/lm/ngram_query.hh91
1 files changed, 61 insertions, 30 deletions
diff --git a/klm/lm/ngram_query.hh b/klm/lm/ngram_query.hh
index ec2590f4..5f330c5c 100644
--- a/klm/lm/ngram_query.hh
+++ b/klm/lm/ngram_query.hh
@@ -1,8 +1,9 @@
-#ifndef LM_NGRAM_QUERY__
-#define LM_NGRAM_QUERY__
+#ifndef LM_NGRAM_QUERY_H
+#define LM_NGRAM_QUERY_H
#include "lm/enumerate_vocab.hh"
#include "lm/model.hh"
+#include "util/file_piece.hh"
#include "util/usage.hh"
#include <cstdlib>
@@ -16,64 +17,94 @@
namespace lm {
namespace ngram {
-template <class Model> void Query(const Model &model, bool sentence_context, std::istream &in_stream, std::ostream &out_stream) {
+struct BasicPrint {
+ void Word(StringPiece, WordIndex, const FullScoreReturn &) const {}
+ void Line(uint64_t oov, float total) const {
+ std::cout << "Total: " << total << " OOV: " << oov << '\n';
+ }
+ void Summary(double, double, uint64_t, uint64_t) {}
+
+};
+
+struct FullPrint : public BasicPrint {
+ void Word(StringPiece surface, WordIndex vocab, const FullScoreReturn &ret) const {
+ std::cout << surface << '=' << vocab << ' ' << static_cast<unsigned int>(ret.ngram_length) << ' ' << ret.prob << '\t';
+ }
+
+ void Summary(double ppl_including_oov, double ppl_excluding_oov, uint64_t corpus_oov, uint64_t corpus_tokens) {
+ std::cout <<
+ "Perplexity including OOVs:\t" << ppl_including_oov << "\n"
+ "Perplexity excluding OOVs:\t" << ppl_excluding_oov << "\n"
+ "OOVs:\t" << corpus_oov << "\n"
+ "Tokens:\t" << corpus_tokens << '\n'
+ ;
+ }
+};
+
+template <class Model, class Printer> void Query(const Model &model, bool sentence_context) {
+ Printer printer;
typename Model::State state, out;
lm::FullScoreReturn ret;
- std::string word;
+ StringPiece word;
+
+ util::FilePiece in(0);
double corpus_total = 0.0;
+ double corpus_total_oov_only = 0.0;
uint64_t corpus_oov = 0;
uint64_t corpus_tokens = 0;
- while (in_stream) {
+ while (true) {
state = sentence_context ? model.BeginSentenceState() : model.NullContextState();
float total = 0.0;
- bool got = false;
uint64_t oov = 0;
- while (in_stream >> word) {
- got = true;
+
+ while (in.ReadWordSameLine(word)) {
lm::WordIndex vocab = model.GetVocabulary().Index(word);
- if (vocab == 0) ++oov;
ret = model.FullScore(state, vocab, out);
+ if (vocab == model.GetVocabulary().NotFound()) {
+ ++oov;
+ corpus_total_oov_only += ret.prob;
+ }
total += ret.prob;
- out_stream << word << '=' << vocab << ' ' << static_cast<unsigned int>(ret.ngram_length) << ' ' << ret.prob << '\t';
+ printer.Word(word, vocab, ret);
++corpus_tokens;
state = out;
- char c;
- while (true) {
- c = in_stream.get();
- if (!in_stream) break;
- if (c == '\n') break;
- if (!isspace(c)) {
- in_stream.unget();
- break;
- }
- }
- if (c == '\n') break;
}
- if (!got && !in_stream) break;
+ // If people don't have a newline after their last query, this won't add a </s>.
+ // Sue me.
+ try {
+ UTIL_THROW_IF('\n' != in.get(), util::Exception, "FilePiece is confused.");
+ } catch (const util::EndOfFileException &e) { break; }
if (sentence_context) {
ret = model.FullScore(state, model.GetVocabulary().EndSentence(), out);
total += ret.prob;
++corpus_tokens;
- out_stream << "</s>=" << model.GetVocabulary().EndSentence() << ' ' << static_cast<unsigned int>(ret.ngram_length) << ' ' << ret.prob << '\t';
+ printer.Word("</s>", model.GetVocabulary().EndSentence(), ret);
}
- out_stream << "Total: " << total << " OOV: " << oov << '\n';
+ printer.Line(oov, total);
corpus_total += total;
corpus_oov += oov;
}
- out_stream << "Perplexity " << pow(10.0, -(corpus_total / static_cast<double>(corpus_tokens))) << std::endl;
+ printer.Summary(
+ pow(10.0, -(corpus_total / static_cast<double>(corpus_tokens))), // PPL including OOVs
+ pow(10.0, -((corpus_total - corpus_total_oov_only) / static_cast<double>(corpus_tokens - corpus_oov))), // PPL excluding OOVs
+ corpus_oov,
+ corpus_tokens);
}
-template <class M> void Query(const char *file, bool sentence_context, std::istream &in_stream, std::ostream &out_stream) {
- Config config;
- M model(file, config);
- Query(model, sentence_context, in_stream, out_stream);
+template <class Model> void Query(const char *file, const Config &config, bool sentence_context, bool show_words) {
+ Model model(file, config);
+ if (show_words) {
+ Query<Model, FullPrint>(model, sentence_context);
+ } else {
+ Query<Model, BasicPrint>(model, sentence_context);
+ }
}
} // namespace ngram
} // namespace lm
-#endif // LM_NGRAM_QUERY__
+#endif // LM_NGRAM_QUERY_H