snli.py 文件源码

def read(self, file_path: str):
        # if `file_path` is a URL, redirect to the cache
        file_path = cached_path(file_path)

        instances = []
        with open(file_path, 'r') as snli_file:
            logger.info("Reading SNLI instances from jsonl dataset at: %s", file_path)
            for line in tqdm.tqdm(snli_file):
                example = json.loads(line)

                label = example["gold_label"]
                if label == '-':
                    # These were cases where the annotators disagreed; we'll just skip them.  It's
                    # like 800 out of 500k examples in the training data.
                    continue

                premise = example["sentence1"]
                hypothesis = example["sentence2"]
                instances.append(self.text_to_instance(premise, hypothesis, label))
        if not instances:
            raise ConfigurationError("No instances were read from the given filepath {}. "
                                     "Is the path correct?".format(file_path))
        return Dataset(instances)