xinyadu/grit_doc_event_entity

grit_doc_event_entity's Issues

Missing annotations in preprocessed dataset

The original MUC-4 dataset (file key-tst3.v2) contains the following annotations:

0.  MESSAGE: ID                    TST3-MUC4-0002
1.  MESSAGE: TEMPLATE              1
...
9.  PERP: INDIVIDUAL ID            "MILITARY" / "MILITARY SUSPECTS" / "SOME MILITARY" / "ARMED FORCES MEMBERS"
10. PERP: ORGANIZATION ID          "ARMED FORCES"
11. PERP: ORGANIZATION CONFIDENCE  SUSPECTED OR ACCUSED BY AUTHORITIES: "ARMED FORCES"
...
19. HUM TGT: DESCRIPTION           "JESUITS"
                                   "MAIDS"
20. HUM TGT: TYPE                  CIVILIAN: "JESUITS"
                                   CIVILIAN: "MAIDS"
21. HUM TGT: NUMBER                6: "JESUITS"
                                   2: "MAIDS"
22. HUM TGT: FOREIGN NATION        -
23. HUM TGT: EFFECT OF INCIDENT    DEATH: "JESUITS"
                                   DEATH: "MAIDS"
24. HUM TGT: TOTAL NUMBER          -

While the preprocessed file test.json from your repository contains the following annotations for the same document:

    "docid": "TST3-MUC4-0002",
    "doctext": "...",
    "extracts": {
        "PerpInd": [
            [
                [
                    "military",
                    141
                ],
                [
                    "some military",
                    295
                ],
                [
                    "military suspects",
                    1002
                ],
                [
                    "armed forces members",
                    1360
                ]
            ]
        ],
        "PerpOrg": [
            [
                [
                    "armed forces",
                    1360
                ]
            ]
        ],
        "Target": [],
        "Victim": [],
        "Weapon": []
    }
}

Here the Victim is excluded while it should be present according to the original annotations. Why?

IndexError: list index out of range

Traceback (most recent call last):
File "run_pl_s_t.py", line 424, in
model = NERTransformer.load_from_checkpoint(checkpoints[-1])
IndexError: list index out of range
请问这个错误怎么解决呢，