[Next] [Previous] [Top] [Back to MUC-6 main page]

Coreference Task Definition


1.1 - Sgml Tagging
1.2 - The "TYPE" Attribute
1.3 - The "ID" and "REF" Attributes
1.4 - The "MIN" Attribute
1.5 - The "STAT" Attribute

1.1 SGML Tagging

The annotation for coreference is SGML tagging within the text stream. Referring expressions and their antecedents are tagged as follows:

<COREF ID="100">Lawson Mardon Group Ltd.</COREF> said <COREF ID="101" TYPE="IDENT" REF="100">it</COREF> ...

The basic annotation contains the information to establish some type of link between an explicitly marked pair of noun phrases. In the above example, the pronoun "it" is tagged as referring to the same entity as the phrase, "Lawson Mardon Group Ltd."

There is one markup per string. Other links can be inferred from the explicit links. We assume that the coreference relation is symmetric and transitive, so if phrase A is marked as coreferential with B (indicated by a REF pointer from A to B), we can infer that B is coreferential with A; if A is coreferential with B, and B is coreferential with C, we can infer that A is coreferential with C.

1.2 The "TYPE" Attribute

The purpose of the TYPE attribute is to indicate the relationship between the anaphor and the antecedent. At present only one such relationship, "IDENT" (for identity), is being annotated.

1.3 The "ID" and "REF" Attributes

The ID and REF attributes are used to indicate that there is a coreference link between two strings. The ID is arbitrarily but uniquely assigned to the string during markup. The REF uses that ID to indicate the coreference link.

1.4 The "MIN" Attribute

The MIN attribute is used in the answer key ("key") to indicate the minimum string that the system under evaluation must include in the COREF tag in order to receive full credit for its output ("response"). So, in the next example, if the system response had omitted "of Surrey, England" from the COREF tag, the response would nonetheless receive full credit because it identified the minimum string.

<COREF ID="100" MIN="Haden MacLellan PLC">Haden MacLellan PLC of Surrey, England</COREF>

... <COREF ID="101" TYPE="IDENT" REF="100">Haden MacLellan</COREF>

| Any response which includes the MIN string and does not include any tokens beyond those enclosed in the <COREF>...</COREF> tags is valid. The MIN string will in general be the HEAD of the phrase; see section 4 for a full discussion of this issue.

1.5 The "STAT" Attribute

The STAT ("status") attribute is used in the answer key when the markup is optional. The only value for this attribute is OPT ("optional"). The evaluation software will not score a string that is marked OPT in the key unless the response has markup on that string. A potential example is given below. (It is marked OPT because a reader may not be certain that "Livingston Street" refers to the Board of Education.) Note that the optionality is marked only for the anaphor.

<COREF ID="102" MIN="Board of Education">Our Board of Education</COREF> budget is just too high, the Mayor said. <COREF ID="103" STAT="OPT" TYPE="IDENT" REF="102">Livingston Street</COREF> has lost control.

Coreference Task Definition - 31 MAY 95
[Next] [Previous] [Top] [Back to MUC-6 main page]

Generated with CERN WebMaker