FMAT (version 2025.4)

FMAT_query: Prepare a data.table of queries and variables for the FMAT.

Description

Prepare a data.table of queries and variables for the FMAT.

Usage

FMAT_query(
  query = "Text with [MASK], optionally with {TARGET} and/or {ATTRIB}.",
  MASK = .(),
  TARGET = .(),
  ATTRIB = .()
)

Value

A data.table of queries and variables.

Arguments

query

Query text (should be a character string/vector with at least one [MASK] token). Multiple queries share the same set of MASK, TARGET, and ATTRIB. For multiple queries with different MASK, TARGET, and/or ATTRIB, please use FMAT_query_bind to combine them.

MASK

A named list of [MASK] target words. Must be single words in the vocabulary of a certain masked language model.

For model vocabulary, see, e.g., https://huggingface.co/bert-base-uncased/raw/main/vocab.txt

Infrequent words may be not included in a model's vocabulary, and in this case you may insert the words into the context by specifying either TARGET or ATTRIB.

TARGET, ATTRIB

A named list of Target/Attribute words or phrases. If specified, then query must contain {TARGET} and/or {ATTRIB} (in all uppercase and in braces) to be replaced by the words/phrases.

See Also

FMAT_query_bind

FMAT_run

Examples

FMAT_query("[MASK] is a nurse.", MASK = .(Male="He", Female="She"))

FMAT_query(
  c("[MASK] is {TARGET}.", "[MASK] works as {TARGET}."),
  MASK = .(Male="He", Female="She"),
  TARGET = .(Occupation=c("a doctor", "a nurse", "an artist"))
)

FMAT_query(
  "The [MASK] {ATTRIB}.",
  MASK = .(Male=c("man", "boy"),
           Female=c("woman", "girl")),
  ATTRIB = .(Masc=c("is masculine", "has a masculine personality"),
             Femi=c("is feminine", "has a feminine personality"))
)