# Entity Extractor alternatives **URL:** \ **Category:** Rasa Open Source\ **Created:** [December 6, 2019, 6:37am UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140 "2019-12-06T06:37:04Z")\ **Posts on this page:** 11\ **Page:** 1
**Author:** ![MohitSinghCS](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mohitsinghcs/32/5120_2.png) [@MohitSinghCS](https://forum.rasa.com/u/MohitSinghCS)\ **Post date:** [December 6, 2019, 6:37am UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/1 "2019-12-06T06:37:04Z")
CRFEntityExtractor Component is increasing the memory and training time of system as training size of nlu increases. Is there any alternative to this extractor that works efficiently for entity extraction and consumes less time and memory as well. Main concern is memory here as it blocks the whole system… ---
**Author:** ![Ghostvv](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/ghostvv/32/211_2.png) [@Ghostvv](https://forum.rasa.com/u/Ghostvv)\ **Post date:** [December 6, 2019, 8:53am UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/2 "2019-12-06T08:53:13Z")
we’re working on a new architecture. But it is a general rule, the more data you have, the more memory you need ---
**Author:** ![MohitSinghCS](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mohitsinghcs/32/5120_2.png) [@MohitSinghCS](https://forum.rasa.com/u/MohitSinghCS)\ **Post date:** [December 6, 2019, 10:32am UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/3 "2019-12-06T10:32:41Z")
what would be different in this new architecture. would it solve the problem of excessive memory and time consumption ---
**Author:** ![Ghostvv](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/ghostvv/32/211_2.png) [@Ghostvv](https://forum.rasa.com/u/Ghostvv)\ **Post date:** [December 6, 2019, 11:17am UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/4 "2019-12-06T11:17:17Z")
what do you mean “excessive”? how much memory it is using already for how much data? ---
**Author:** ![MohitSinghCS](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mohitsinghcs/32/5120_2.png) [@MohitSinghCS](https://forum.rasa.com/u/MohitSinghCS)\ **Post date:** [December 6, 2019, 11:23am UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/5 "2019-12-06T11:23:09Z")
for nlu size of 15-20 MB , it took above 8GB of server’s memory (server’s ram is 8gb) @Ghostvv ---
**Author:** ![Ghostvv](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/ghostvv/32/211_2.png) [@Ghostvv](https://forum.rasa.com/u/Ghostvv)\ **Post date:** [December 6, 2019, 12:08pm UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/6 "2019-12-06T12:08:38Z")
what is your pipeline? ---
**Author:** ![Ghostvv](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/ghostvv/32/211_2.png) [@Ghostvv](https://forum.rasa.com/u/Ghostvv)\ **Post date:** [December 6, 2019, 12:09pm UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/7 "2019-12-06T12:09:05Z")
it is hard to understand in mb, how many examples do you have? ---
**Author:** ![MohitSinghCS](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mohitsinghcs/32/5120_2.png) [@MohitSinghCS](https://forum.rasa.com/u/MohitSinghCS)\ **Post date:** [December 9, 2019, 4:28am UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/8 "2019-12-09T04:28:44Z")
> [@Ghostvv](#): > > what is your pipeline pipeline: - name: “SpacyNLP” - name: “WhitespaceTokenizer” - name: “SpacyFeaturizer” - name: “RegexFeaturizer” - name: “EntitySynonymMapper” - name: “SklearnIntentClassifier” - name: “CRFEntityExtractor” - name: “DucklingHTTPExtractor” url: “[http://localhost:8000](http://localhost:8000)” dimensions: [“time”,“number”,“distance”,“email” , “amount-of-money”] locale: “en\_GB” timezone: “Europe/London” policies: - name: MemoizationPolicy - name: KerasPolicy - name: MappingPolicy - name: “FallbackPolicy” nlu\_threshold: 0.3 fallback\_action\_name: “utter\_default\_fallback” This is the pipeline we are using.@Ghostvv ---
**Author:** ![Ghostvv](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/ghostvv/32/211_2.png) [@Ghostvv](https://forum.rasa.com/u/Ghostvv)\ **Post date:** [December 10, 2019, 10:05am UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/9 "2019-12-10T10:05:33Z")
How many intent examples do you have? ---
**Author:** ![MohitSinghCS](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/mohitsinghcs/32/5120_2.png) [@MohitSinghCS](https://forum.rasa.com/u/MohitSinghCS)\ **Post date:** [December 12, 2019, 12:01pm UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/10 "2019-12-12T12:01:38Z")
@Ghostvvwe have intent examples approx 50-60 thousands. actually our examples are formed dynamically following the permutations and combinations of entities and their synonyms values(dynamic) ---
**Author:** ![Ghostvv](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/ghostvv/32/211_2.png) [@Ghostvv](https://forum.rasa.com/u/Ghostvv)\ **Post date:** [December 13, 2019, 12:06pm UTC](https://forum.rasa.com/t/entity-extractor-alternatives/22140/11 "2019-12-13T12:06:27Z")
that’s a lot. You can implement an online loader, in order to reduce memory consumption