SpanFinder: set default max_length to 25 (#12791)

When the default `max_length` is not set and there are longer training
documents, it can be difficult to train and evaluate the span finder due
to memory limits and the time it takes to evaluate a huge number of
predicted spans.
This commit is contained in:
Adriane Boyd 2023-07-06 09:55:34 +02:00 committed by GitHub
parent eab929361d
commit 830dcca367
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 3 deletions

View File

@ -130,7 +130,7 @@ grad_factor = 1.0
{% if "span_finder" in components -%} {% if "span_finder" in components -%}
[components.span_finder] [components.span_finder]
factory = "span_finder" factory = "span_finder"
max_length = null max_length = 25
min_length = null min_length = null
scorer = {"@scorers":"spacy.span_finder_scorer.v1"} scorer = {"@scorers":"spacy.span_finder_scorer.v1"}
spans_key = "sc" spans_key = "sc"
@ -419,7 +419,7 @@ width = ${components.tok2vec.model.encode.width}
{% if "span_finder" in components %} {% if "span_finder" in components %}
[components.span_finder] [components.span_finder]
factory = "span_finder" factory = "span_finder"
max_length = null max_length = 25
min_length = null min_length = null
scorer = {"@scorers":"spacy.span_finder_scorer.v1"} scorer = {"@scorers":"spacy.span_finder_scorer.v1"}
spans_key = "sc" spans_key = "sc"

View File

@ -48,7 +48,7 @@ DEFAULT_SPAN_FINDER_MODEL = Config().from_str(span_finder_default_config)["model
"threshold": 0.5, "threshold": 0.5,
"model": DEFAULT_SPAN_FINDER_MODEL, "model": DEFAULT_SPAN_FINDER_MODEL,
"spans_key": DEFAULT_SPANS_KEY, "spans_key": DEFAULT_SPANS_KEY,
"max_length": None, "max_length": 25,
"min_length": None, "min_length": None,
"scorer": {"@scorers": "spacy.span_finder_scorer.v1"}, "scorer": {"@scorers": "spacy.span_finder_scorer.v1"},
}, },