void Run::parse(const std::string &sInputFile, const std::string &sOutputFile,
const std::string &sFeatureFile) const {
Sentence sentence;
DependencyTree tree;
std::cout << "Parsing started" << std::endl;
auto time_begin = time(NULL);
std::unique_ptr<DepParser> parser(new DepParser(sFeatureFile, sFeatureFile, ParserState::PARSE));
std::ifstream input(sInputFile);
std::ofstream output(sOutputFile);
if (input) {
while (input >> sentence) {
if (sentence.size() < MAX_SENTENCE_SIZE) {
parser->parse(sentence, &tree);
output << tree;
tree.clear();
}
}
}
input.close();
output.close();
auto time_end = time(NULL);
auto seconds = difftime(time_end, time_begin);
std::cout << "Parsing has finished successfully. Total time taken is: " << difftime(time_end, time_begin) <<
"s" << std::endl;
}
void StateItem::generateTree(const DependencyTree & sent, DependencyTree & tree) const {
int i = 0;
tree.clear();
for (const auto & token : sent) {
tree.push_back(DependencyTreeNode(TREENODE_POSTAGGEDWORD(token), m_lHeads[i], TDepLabel::key(m_lLabels[i])));
++i;
}
}
const string NonProjNivre::get_oracle(
Configuration& c,
DependencyTree& tree)
{
int w1 = c.get_stack(1);
int w2 = c.get_stack(0);
int k = c.buffer.empty() ? -1 : c.buffer.back();
if (w1 > 0
&& tree.get_head(w1) == w2
&& !c.has_other_child(w1, tree))
return "L(" + tree.get_label(w1) + ")";
else if (w1 >= 0
&& tree.get_head(w2) == w1
&& !c.has_other_child(w2, tree))
return "R(" + tree.get_label(w2) + ")";
else if (w1 < w2 && tree.proj_order[w1] > tree.proj_order[w2] &&
(k == -1 || tree.mpc[w2] != tree.mpc[k]))
// else if (w1 < w2 && tree.proj_order[w1] > tree.proj_order[w2])
return "E";
else
return "S";
}
void Run::parse(const std::string &sInputFile, const std::string &sOutputFile,
const std::string &sFeatureFile) const {
Sentence sentence;
DependencyTree tree;
std::cout << "Parsing started" << std::endl;
std::unique_ptr<DepParser> parser(new DepParser(sFeatureFile, sFeatureFile, ParserState::PARSE));
std::ifstream input(sInputFile);
std::ofstream output(sOutputFile);
if (input) {
while (input >> sentence) {
if (sentence.size() < MAX_SENTENCE_SIZE) {
parser->parse(sentence, &tree);
output << tree;
tree.clear();
}
}
}
input.close();
output.close();
}
bool StateItem::standardMove(const DependencyTree & tree) {
int top;
if (m_nNextWord == tree.size()) {
if (m_nStackBack > 0) {
reduce();
return true;
}
else {
popRoot();
return false;
}
}
if (m_nStackBack >= 0) {
top = m_lStack[m_nStackBack];
while (!(m_lHeads[top] == -1)) {
top = m_lHeads[top];
}
if (TREENODE_HEAD(tree[top]) == m_nNextWord) {
if (top == m_lStack[m_nStackBack]) {
arcLeft(TDepLabel::code(TREENODE_LABEL(tree[top])));
return true;
}
else {
reduce();
return true;
}
}
}
if (TREENODE_HEAD(tree[m_nNextWord]) == -1 || TREENODE_HEAD(tree[m_nNextWord]) > m_nNextWord) {
shift();
return true;
}
else {
top = m_lStack[m_nStackBack];
if (TREENODE_HEAD(tree[m_nNextWord]) == top) {
arcRight(TDepLabel::code(TREENODE_LABEL(tree[m_nNextWord])));
return true;
}
else {
reduce();
return true;
}
}
}