AllenNLP 2.0:在MultiTaskDatasetReader中使用‘AllenNLP谓词’会导致RuntimeError

Question

我使用allennlp2.0训练了一个多任务模型，现在我想使用allennlp predict命令来预测新的例子。

Problem/Error:我正在使用以下命令：allennlp predict results/model.tar.gz new_instances.jsonl --include-package mtl_sd --predictor mtlsd_predictor --use-dataset-reader --dataset-reader-choice validation

这给了我以下错误：

Traceback (most recent call last):
File ".../mtl_sd_venv/bin/allennlp", line 10, in <module>
sys.exit(run())
File ".../mtl_sd_venv/lib/python3.7/site-packages/allennlp/__main__.py", line 34, in run
main(prog="allennlp")
File ".../mtl_sd_venv/lib/python3.7/site-packages/allennlp/commands/__init__.py", line 119, in main
args.func(args)
File ".../mtl_sd_venv/lib/python3.7/site-packages/allennlp/commands/predict.py", line 220, in _predict
manager.run()
File ".../mtl_sd_venv/lib/python3.7/site-packages/allennlp/commands/predict.py", line 186, in run
for batch in lazy_groups_of(self._get_instance_data(), self._batch_size):
File ".../mtl_sd_venv/lib/python3.7/site-packages/allennlp/common/util.py", line 139, in lazy_groups_of
s = list(islice(iterator, group_size))
File ".../mtl_sd_venv/lib/python3.7/site-packages/allennlp/commands/predict.py", line 180, in _get_instance_data
yield from self._dataset_reader.read(self._input_file)
File ".../mtl_sd_venv/lib/python3.7/site-packages/allennlp/data/dataset_readers/multitask.py", line 31, in read
raise RuntimeError("This class is not designed to be called like this")
RuntimeError: This class is not designed to be called like this

据我所知，就是这么回事：

这个RuntimeError是由MultiTaskDatasetReader引发的，因为read()-method的MultiTaskDatasetReader不应该被称为自己。read()-method只应在MultiTaskDatasetReader.readers中调用特定的DatasetReaders。

调用MultiTaskDatasetReader的read()MultiTaskDatasetReader是因为在jsonnet-config中，我将DatasetsReaders指定如下：

"dataset_reader": {
    "type": "multitask",
    "readers": {
        "SemEval2016": {
            "type": "SemEval2016",
            "max_sequence_length": 509,
            "token_indexers": {
                "bert": {
                    "type": "pretrained_transformer",
                    "model_name": "bert-base-cased"
                }
            },
            "tokenizer": {
                "type": "pretrained_transformer",
                "model_name": "bert-base-cased"
            }
        }, ...
    }
}

通常，type of dataset_reader表示要实例化以进行预测的dataset-reader类。但是在本例中，type只是点MultiTaskDatasetReader，它没有实现read()-method，包含多个DatasetReaders。

据我所知，在使用allennlp predict时，我需要以某种方式指定应该使用的多个DatasetReaders中的哪个。

问题是：

如何指定在执行DatasetReader时应该使用哪个特定的DatasetReaders (MultiTaskDatasetReader.readers中的多个DatasetReaders)？或者更广泛地说:如何让allennlp predict与MultiTaskDatasetReader一起运行？

为了完整性起见，附加代码：是预测器：

@Predictor.register('mtlsd_predictor')
class MTLSDPredictor(Predictor):

    def predict(self, sentence: str) -> JsonDict:
        return self.predict_json({'sentence': sentence})

    @overrides
    def _json_to_instance(self, json_dict: JsonDict) -> Instance:
        target = json_dict['text1']
        claim = json_dict['text2']
        return self._dataset_reader.text_to_instance(target, claim)

Answer 1

这里有两个问题。一个是AllenNLP中的一个bug，它在2.1.0版本中得到了修复。另一个是@sinaj在他的模型头上缺少了default_predictor。