FocusedColumnModule.cpp

#include "FocusedColumnModule.hpp"

FocusedColumnModuleImpl::FocusedColumnModuleImpl(std::string name, const std::string & definition, std::filesystem::path path) : path(path)
{
  setName(name);
  std::regex regex("(?:(?:\\s|\\t)*)Column\\{(.*)\\}(?:(?:\\s|\\t)*)NbElem\\{(.*)\\}(?:(?:\\s|\\t)*)Buffer\\{(.*)\\}(?:(?:\\s|\\t)*)Stack\\{(.*)\\}(?:(?:\\s|\\t)*)(\\S+)\\{(.*)\\}(?:(?:\\s|\\t)*)In\\{(.*)\\}(?:(?:\\s|\\t)*)Out\\{(.*)\\}(?:(?:\\s|\\t)*)w2v\\{(.*)\\}(?:(?:\\s|\\t)*)");
  if (!util::doIfNameMatch(regex, definition, [this,&definition](auto sm)
        {
          try
          {
            func = getFunction(sm.str(1));
            column = util::split(sm.str(1), ':').back();
            maxNbElements = std::stoi(sm.str(2));

            for (auto & index : util::split(sm.str(3), ' '))
              focusedBuffer.emplace_back(std::stoi(index));

            for (auto & index : util::split(sm.str(4), ' '))
              focusedStack.emplace_back(std::stoi(index));

            auto subModuleType = sm.str(5);
            auto subModuleArguments = util::split(sm.str(6), ' ');

            auto options = MyModule::ModuleOptions(true)
              .bidirectional(std::stoi(subModuleArguments[0]))
              .num_layers(std::stoi(subModuleArguments[1]))
              .dropout(std::stof(subModuleArguments[2]))
              .complete(std::stoi(subModuleArguments[3]));

            inSize = std::stoi(sm.str(7));
            int outSize = std::stoi(sm.str(8));

            if (subModuleType == "LSTM")
              myModule = register_module("myModule", LSTM(inSize, outSize, options));
            else if (subModuleType == "GRU")
              myModule = register_module("myModule", GRU(inSize, outSize, options));
            else if (subModuleType == "Concat")
              myModule = register_module("myModule", Concat(inSize));
            else
              util::myThrow(fmt::format("unknown sumodule type '{}'", subModuleType));

            w2vFiles = sm.str(9);

            if (!w2vFiles.empty())
            {
              auto pathes = util::split(w2vFiles.string(), ' ');
              for (auto & p : pathes)
              {
                auto splited = util::split(p, ',');
                if (splited.size() != 2)
                  util::myThrow("expected 'prefix,pretrained.w2v'");
                getDict().loadWord2Vec(this->path / splited[1], splited[0]);
                getDict().setState(Dict::State::Closed);
                dictSetPretrained(true);
              }
            }

          } catch (std::exception & e) {util::myThrow(fmt::format("{} in '{}'",e.what(),definition));}
        }))
    util::myThrow(fmt::format("invalid definition '{}'", definition));
}

torch::Tensor FocusedColumnModuleImpl::forward(torch::Tensor input)
{
  std::vector<torch::Tensor> outputs;
  for (unsigned int i = 0; i < focusedBuffer.size()+focusedStack.size(); i++)
    outputs.emplace_back(myModule->forward(wordEmbeddings(input.narrow(1, firstInputIndex+i*maxNbElements, maxNbElements))).reshape({input.size(0), -1}));

  return torch::cat(outputs, 1);
}

std::size_t FocusedColumnModuleImpl::getOutputSize()
{
  return (focusedBuffer.size()+focusedStack.size())*myModule->getOutputSize(maxNbElements);
}

std::size_t FocusedColumnModuleImpl::getInputSize()
{
  return (focusedBuffer.size()+focusedStack.size()) * maxNbElements;
}

void FocusedColumnModuleImpl::addToContext(std::vector<std::vector<long>> & context, const Config & config)
{
  auto & dict = getDict();
  std::vector<long> focusedIndexes;

  for (int index : focusedBuffer)
    focusedIndexes.emplace_back(config.getRelativeWordIndex(index));

  for (int index : focusedStack)
    if (config.hasStack(index))
      focusedIndexes.emplace_back(config.getStack(index));
    else
      focusedIndexes.emplace_back(-1);

  for (auto & contextElement : context)
  {
    for (auto index : focusedIndexes)
    {
      if (index == -1)
      {
        for (int i = 0; i < maxNbElements; i++)
          contextElement.emplace_back(dict.getIndexOrInsert(Dict::nullValueStr, column));
        continue;
      }

      std::vector<std::string> elements;
      if (column == "FORM")
      {
        auto asUtf8 = util::splitAsUtf8(func(config.getAsFeature(column, index).get()));

        //TODO don't use nullValueStr here
        for (int i = 0; i < maxNbElements; i++)
          if (i < (int)asUtf8.size())
            elements.emplace_back(fmt::format("{}", asUtf8[i]));
          else
            elements.emplace_back(Dict::nullValueStr);
      }
      else if (column == "FEATS")
      {
        auto splited = util::split(func(config.getAsFeature(column, index).get()), '|');

        for (int i = 0; i < maxNbElements; i++)
          if (i < (int)splited.size())
            elements.emplace_back(splited[i]);
          else
            elements.emplace_back(Dict::nullValueStr);
      }
      else if (column == "ID")
      {
        if (config.isTokenPredicted(index))
          elements.emplace_back("TOKEN");
        else if (config.isMultiwordPredicted(index))
          elements.emplace_back("MULTIWORD");
        else if (config.isEmptyNodePredicted(index))
          elements.emplace_back("EMPTYNODE");
      }
      else if (column == "EOS")
      {
        bool isEOS = func(config.getAsFeature(Config::EOSColName, index)) == Config::EOSSymbol1;
        elements.emplace_back(fmt::format("{}", isEOS));
      }
      else
      {
        elements.emplace_back(func(config.getAsFeature(column, index)));
      }

      if ((int)elements.size() != maxNbElements)
        util::myThrow(fmt::format("elements.size ({}) != maxNbElements ({})", elements.size(), maxNbElements));

      for (auto & element : elements)
        contextElement.emplace_back(dict.getIndexOrInsert(element, column));
    }
  }
}

void FocusedColumnModuleImpl::registerEmbeddings()
{
  wordEmbeddings = register_module("embeddings", WordEmbeddings(getDict().size(), inSize));
  auto pathes = util::split(w2vFiles.string(), ' ');
  for (auto & p : pathes)
  {
    auto splited = util::split(p, ',');
    loadPretrainedW2vEmbeddings(wordEmbeddings->get(), path / splited[1], splited[0]);
  }
}