# Lookup table not giving desired result **URL:** \ **Category:** Rasa Open Source\ **Created:** [May 30, 2019, 3:49pm UTC](https://forum.rasa.com/t/lookup-table-not-giving-desired-result/10669 "2019-05-30T15:49:05Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![abhi\_bh\_nlp](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/abhi_bh_nlp/32/5905_2.png) [@abhi\_bh\_nlp](https://forum.rasa.com/u/abhi_bh_nlp)\ **Post date:** [May 30, 2019, 3:49pm UTC](https://forum.rasa.com/t/lookup-table-not-giving-desired-result/10669/1 "2019-05-30T15:49:05Z")
Hi, i have gone through the blog [Improving Entity Extraction with Lookup Tables](https://blog.rasa.com/improving-entity-extraction/?_ga=2.258433229.630265857.1559062226-1054761945.1556541568). I am facing challenges in getting the desired result, if anyone can help me understand how exactly this lookup functionality works. Below are my files: nlu\_entity\_md=“”" ## intent:Access -Can I get access to ABCD [Animal & Bird Cat Data] (application) -May I get access to CODE Control and Operational Dept Evaluation -how do i get entry into ABCD? -Access to ROSE -How can I get access to FIFA -How do I acees into Controls Room -I want login to ABA? -access to code? -rose access -Animal & Bird Cat Data access -FIFA access -FIFA access -access to fifa -access to aba -Can I get access for [Animal & Bird Cat Data] (application:ABCD) -May I get access for Control and Operational Dept Evaluation -May I get access to control and operational dept evaluation -how do i get access for fifa # lookup:application - ABCD - CODE - ROSE - ABA - FIFA - Controls Room - abcd - code - rose - aba - fifa - controls room - apple - rat - mat - value and prepositions “”" %store nlu\_entity\_md \> nlu\_entity.md ##### config file config = “”" language: “en” pipeline: - name: “SpacyNLP” # loads the spacy language model model: “en\_core\_web\_md” case\_sensitive: true - name: “SpacyTokenizer” # splits the sentence into tokens - name: “RegexFeaturizer” - name: “CRFEntityExtractor” features: [[“low”, “titlmate”, “upper”],[“bias”, “low”, “prefix5”, “prefix2”, “suffix5”, “suffix3”,“suffix2”, “upper”, “title”, “digit”, “pattern”],[“low”, “title”, “upper”]] “”" %store config \> config.yml indent preformatted text by 4 spaces ########## test data sent=[‘access to aba’, ‘how do i get access to ROSE’, ‘can i get access to fifa’, ’ how do i get access to RANDOM’, ‘access to MAT’, ‘access to mat’, ‘access to value and prepositions’, ‘access to JIRA’] ![image](https://europe1.discourse-cdn.com/flex013/uploads/rasa/original/2X/f/f494bfb11cbbb6bb94a04771543b8a045278f22c.png) ## queries that i have. 1. Why it is unable to pick up the entity mat and ’ value and prepositions" even tough its there in look up table? 2. RANDOM is not there in lookup table but i believe CRF is able to understand the structure of sentence and predict the entity, thus in this case even if i remove the MAT from the lookup it would work, then how exactly LOOKUP table is useful for us. 3. How do i handle entities that are of more than one word, do i need to train for all such values. 4. How exactly lookup tables are used for entity extraction? ---
**Author:** ![OmarGr](https://avatars.discourse-cdn.com/v4/letter/o/258eb7/32.png) [@OmarGr](https://forum.rasa.com/u/OmarGr)\ **Post date:** [May 30, 2019, 8:28pm UTC](https://forum.rasa.com/t/lookup-table-not-giving-desired-result/10669/3 "2019-05-30T20:28:32Z")
Hi @abhi_bh_nlp, try to include all your lookup words in the training set. It should work then. ---
**Author:** ![abhi\_bh\_nlp](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/abhi_bh_nlp/32/5905_2.png) [@abhi\_bh\_nlp](https://forum.rasa.com/u/abhi_bh_nlp)\ **Post date:** [May 31, 2019, 12:24pm UTC](https://forum.rasa.com/t/lookup-table-not-giving-desired-result/10669/4 "2019-05-31T12:24:50Z")
That’s what i am failing to understand, if i have to give all the words in the training sets how is lookup table helpful. Is it just that it creates additional feature for CRF , so that probability of getting recognized of entity increases? ---
**Author:** ![OmarGr](https://avatars.discourse-cdn.com/v4/letter/o/258eb7/32.png) [@OmarGr](https://forum.rasa.com/u/OmarGr)\ **Post date:** [May 31, 2019, 1:45pm UTC](https://forum.rasa.com/t/lookup-table-not-giving-desired-result/10669/5 "2019-05-31T13:45:17Z")
Yes! The lookup transforms to features for CRF. ---
**Author:** ![juven](https://avatars.discourse-cdn.com/v4/letter/j/b487fb/32.png) [@juven](https://forum.rasa.com/u/juven)\ **Post date:** [June 29, 2019, 9:25am UTC](https://forum.rasa.com/t/lookup-table-not-giving-desired-result/10669/6 "2019-06-29T09:25:34Z")
I have similiar question: Whether do I need include all data in lookup table into nlu training data? If yes, why do I need to use lookup tables? and the volumn of nlu training data will be too much, it will cost a long time to train. Waiting someone for giving the answer. Thanks.