I have to write 30+ memos related to stream crossings. I have written the first memo, and it occurs to me that I could use it as a template for further memos. All that would require revision in subsequent memos would be a few fields such as Stream Name Crossing ID and Road Name.
I would like to use a table with these field to automate the process of using them to replace placeholder values in multiple word documents.
Which programming languages or software packages could be used to complete this task?
Related
I'm working on an NLP/NER script using transformers/BERT and I'm having an issue extracting the name of a company from a set of texts.
In all the texts the script will be used on, the company's name will be presented like this:
"COMPANY NAME: the company's name is XXX"
or
"NAME: the company's name is XXX"
this is my code:
def get_company_info(text, tokenizer_1, model_1, tokenizer_2, model_2):
company_info = {"name": None}
try:
start_company_index = re.search('name', text, re.I).span()[0]
info = NLP_2(
text[start_company_index:start_company_index+100], tokenizer_2, model_2)
for data in info:
if data['entity_group'] == 'ORG':
company_info['name'] = data['word']
break
except:
pass
However, the BERT script returns the word "company" since it finds it in the text and assumes correctly that it is the subject I'm looking for but I want to extract the name of the company instead.
Is there a simple way to avoid this or do I have to fine-tune the model?
I'm using regex to delimit the field of the search but I cannot simply use re.search("company") to start the search after the word company, because sometimes there will be 2 consecutive mentions of the word.
You cannot avoid that from a model-perspective unfortunately.
You have to:
Either, as suggested in your comments, perform some regex parsing or try to use another type of logic to eliminate paragraph titles (if it suits you).
Retrain on your own dataset, giving many examples of such situations like above, so that the network would eventually learn to distinguish and not detect COMPANY_NAME or other similar examples.
For (1) things can get complicated since what you gave here is just one instance where the network fails, it may very well be the case that as you see more documents, you discover more error-prone situations - the post-processing becomes more and more difficult.
For (2) you can actually start predicting on your new data, clean it, and start creating a cleaned dataset on your own for finetuning purposes.
One other approach would be to search for specific pre-trained BERT/similar models which are pre-trained on specific corpuses. For example, SciBERT is a pre-trained language model on scientific text, and, given that you would presumably work with scientific texts, it would have a better performance than a basic BERT. However, I do not know if you will find a model catered exactly for your needs as in the above example.
I work at a publishing site. I'm interested in developing a model that can predict a user's affinity for a piece or set of content based on the content they have previously engaged with.
Content is classified via categories and tags. Engagement per item could be binary (clicked on) or a 0-1 float value (normalized length of time engaged).
How should I train a model will allow me to personalize effectively per user?
I don't need realtime access to recommendations. Ideally I would retrain the model weekly with new clickstream data, and batch download data describing each user's top categories and tags with an affinity score.
Thanks.
Working backwards from your use case, the user-personalization recipe is where you should start. This recipe is designed to recommend items (content in your case) to users based on their previous interactions with items/content.
The primary input into this recipe (and all Personalize recipes for that matter) is interactions/events. For you this would be the clicks/views of content. If you have historical interactions of these clicks, you can prepare a CSV with this data. The minimum required fields are USER_ID, ITEM_ID, and TIMESTAMP where each row represents a moment in time when a specific user interacted with an item. You can optionally include an EVENT_TYPE column and EVENT_VALUE column. The values for EVENT_TYPE depends on your application and event taxonomy. If you're just tracking clicks right now, you can use click or view as the event type and then add support for more event types in the future (e.g. bookmark, favorite, etc) as needed. For EVENT_VALUE (type float), you could use your normalized length of time engaged. You can use the EVENT_VALUE to filter which events are included in training by specifying an eventType and eventValueThreshold when creating your solution. For example, if you consider any values equal to or greater than, say, 0.4 to indicate positive interest by a user in a piece of content, you can set a eventValueThreshold of 0.4 and Personalize will only include interactions equal to or above that value in training. Personalize will also include the event value as a feature in the model but it won't be used to weight or reward interactions based this value.
The user-personalization recipe will also consider the items and users datasets, if provided. For your use case, providing an items dataset is where you'd specify the categories and tags for each piece of content (item). You can also include the raw text for each piece of content as a textual field in your items dataset. Personalize will automatically extract features from your textual field to improve the relevance of recommendations.
Once you have your datasets imported into a dataset group, you can create a solution using the user-personalization recipe and then a solution version (which represents the trained model). To get batch recommendations weekly, you would use a batch inference job each week to generate recommendations for each user. The output of the batch inference job can then be processed to determine the category and tag affinities for each user based on the recommended content.
I want to automate a few search in one, here are the steps:
Search in Kibana for this ID:"b2c729b5-6440-4829-8562-abd81991e2a0" which will return me a bunch of logs. Of these logs I need to take the first and the last timestamp:
I now would like to store these two data FROM: September 3rd 2019, 21:28:22.155, TO: September 3rd 2019, 21:28:23.524 in 2 variables
Run a second search in Kibana for the word "fail" in between these two variable of time
How to automate the whole process without need of copy/paste and running a second query?
EDIT:
SHORT STORY LONG: I work in a company that produce a software for autonomous vehicles.
SCENARIO: A booking is rejected and we need to understand why.
WHERE IS THE PROBLE: I need to monitor just a few seconds of logs on 3 different machines. Each log is completely separated, there is no relation between the logs so I cannot write a query in discover, I need to run 3 separated queries.
EXAMPLE:
A booking was rejected, so I open Chrome and I search on "elk-prod.myhost.com" for the BookingID:"b2c729b5-6440-4829-8562-abd81991e2a0" and I have a dozen of logs returned during a range of 2 seconds (FROM: September 3rd 2019, 21:28:22.155, TO: September 3rd 2019, 21:28:23.524).
Now I need to know what was happening on the car so I open a new Chrome tab and I search on "elk-prod.myhost.com" for the CarID: "Tesla-45-OU" on the time range FROM: September 3rd 2019, 21:28:22.155, TO: September 3rd 2019, 21:28:23.524
Now I need to know why the server which calculate the matching rejected the booking so I open a new Chrome tab and I search for the word CalculationMatrix always on the time range FROM: September 3rd 2019, 21:28:22.155, TO: September 3rd 2019, 21:28:23.524
CONCLUSION: I want to stop to keep opening Chrome tabs by hand and automate the whole thing. I have no idea around what time the book was made so I first need to search for the BookingID "b2c729b5-6440-4829-8562-abd81991e2a0", then store the timestamp of first and last log and run a second and third query based on those timestamps.
There is no relation between the 3 logs I search so there is no way to filter from the Discover, I need to automate 3 different query.
Here is how I would do it. First of all, from what I understand, you have three different indexes:
one for "bookings"
one for "cars"
one for "matchings"
First, in Discover, I would create three Saved Searches, one per index pattern. Then in Visualize, I would create a Vertical bar chart on the bookings saved search (Bucket X-Axis by date_histogram on the timestamp field, leave the rest as is). You'll get a nice histogram of all your booking events bucketed by time.
Finally, I would create a dashboard and add the vertical bar chart + those three saved searches inside it.
When done, the way I would search according to the process you've described above is as follows:
Search for the booking ID b2c729b5-6440-4829-8562-abd81991e2a0 in the top filter bar. In the bar chart histogram (bookings), you will see all documents related to the selected booking. On that chart, you can select the exact period from when the very first booking document happened to the very last. This will adapt the main time picker at the top and the start/end time will be "remembered" by Kibana
Remove the booking ID from the top filter (since we now know the time range and Kibana stores it). Search for Tesla-45-OU in the top filter bar. The bar histogram + the booking saved search + the matchings saved search will be empty, but you'll have data inside the second list, the one for cars. Find whatever you need to find in there and go to the next step.
Remove the car ID from the top filter and search for ComputationMatrix. Now the third saved search is going to show you whatever documents you need to see within that time range.
I'm lacking realistic data to try this out, but I definitely think this is possible as I've laid out above, probably with some adaptations.
Kibana does work like this (any order is ok):
Select time filter: https://www.elastic.co/guide/en/kibana/current/set-time-filter.html
Add additional criteria for search like for example field s is b2c729b5-6440-4829-8562-abd81991e2a0.
Add aditional criteria for search like for example field x is Fail.
Additionaly you can view surrounding documents https://www.elastic.co/guide/en/kibana/current/document-context.html#document-context
This is how Kibana works.
You can prepare some filters beforehands, save them and then use them if you want to automate the process of discovering somehow.
You can do that in Discover tab in Kibana using New/Save/Open options.
Edit:
I do not think you can achieve what you need in Kibana. As I mentioned earlier one option is to change the data that is comming to Elasticsearch so you can search for it via discover in Kibana. Another option could be builiding for example Java application, that is using Elasticsearch - then you can write algorithm that returns the data that you want. But i think it's a big overhead and I recommend checking the data first.
Edit: To clarify - you can create external Java let's say SpringBoot application that uses Elasticsearch - all the data that you need is inside it.
But in this option you will not use Kibana at all.
You can export the result to csv or what you want in the code.
SpringBoot application can ask ElasticSearch for whatever it needs, then it would be easy to store these time variables inside of Java code.
EDIT: After OP edited question to change it dramatically:
#FrancescoMantovani Well the edited version is very different from where you first posted here How to automate the whole process without need of copy/paste and running a second query? and search for word fail in a single shot. In accepted answer you are still using a three filters one at a time so it is not one search, but three.
What's more if you would use one index, and send data from multiple hosts via filebeat you don't even to have to create this dashboard to do that. Then you can you can select the exact period from when the very first document happened to the very last regarding filter and then remove it and add another filter that you need - it's simple as that. Before you were writing about one query,
How to automate the whole process without need of copy/paste and
running a second query?
not three. And you don't need to open new tab in Chrome each time you want to change filter just organize the data by for example using filebeat as mentioned before.
There is no relation between the 3 logs
From what you wrote the realation exist and it is time.
If the data is in for example three diferent indicies (cause documents don't have much similiar data) you can do it like that:
You change them easily in dicover see:
You can go to discover select index 1 search, select time range that you need, when you change index the time range is still the one you selected, you only need to change filter - you will get what you need.
I'm using Elasticsearch to build search for ecommerece site.
One index will have products stored in it, in products index I'll store categories in it's other attributes along with. Categories can be multiple but the attribute will have single field value. (E.g. color)
Let's say user types in Black(color) Nike(brand) shoes(Categories)
I want to process this query so that I can extract entities (brand, attribute, etc...) and I can write Request body search.
I have tought of following option,
Applying regex on query first to extract those entities (But with this approach not sure how Fuzzyness would work, user may have typo in any of the entity)
Using OpenNLP extension (But this one only works on indexation time, in above scenario we want it on query side)
Using NER of any good NLP framework. (This is not time & cost effective because I'll have millions of products in engine also they get updated/added on frequent basis)
What's the best way to solve above issue ?
Edit:
Found couple of libraries which would allow fuzzy text matching in regex. But the entities to find will be many, so what's the best solution to optimise that ?
Still not sure about OpenNLP
NER won't work in this case because there are fixed number of entities so prediction is not right when there are no entity available in the query.
If you cannot achieve desired results with tuning of built-in ElasticSearch scoring/boosting most likely you'll need some kind of 'natural language query' processing:
Tokenize free-form query. Regex can be used for splitting lexems, however very often it is better to write custom tokenizer for that.
Perform named-entity recognition to determine possible field(s) for each keyword. At this step you will get associations like (Black -> color), (Black -> product name) etc. In fact you don't need OpenNLP for that as this should be just an index (keyword -> field(s)), and you can try to use ElasticSearch 'suggest' API for this purpose.
(optional) Recognize special phrases or combinations like "released yesterday", "price below $20"
Generate possible combinations of matches, and with help of special scoring function determine 'best' recognition result. Scoring function may be hardcoded (reflect 'common sense' heuristics) or it this may be a result of machine learning algorithm.
By recognition result (matches metadata) produce formal query to produce search results - this may be ElasticSearch query with field hints, or even SQL query.
In general, efficient NLQ processing needs significant development efforts - I don't recommend to implement it from scratch until you have enough resources & time for this feature. As alternative, you can try to find existing NLQ solution and integrate it, but most likely this will be commercial product (I don't know any good free/open-source NLQ components that really ready for production use).
I would approach this problem as NER tagging considering you already have corpus of tags. My approach for this problem will be as below:
Create a annotated dataset of queries with each word tagged to one of the tags say {color, brand, Categories}
Train a NER model (CRF/LSTMS).
This is not time & cost effective because I'll have millions of
products in engine also they get updated/added on frequent basis
To handle this situation I suggest dont use words in the query as features but rather use the attributes of the words as features. For example create an indicator function f(x',y) for word x with context x' (i.e the word along with the surrounding words and their attributes) and tag y which will return a 1 or 0. A sample indicator function will be as below
f('blue', 'y') = if 'blue' in `color attribute` column of DB and words previous to 'blue' is in `product attribute` column of DB and 'y' is `colors` then return 1 else 0.
Create lot of these indicator functions also know as features maps.
These indicator functions are then used to train a models using CRFS or LSTMS. Finially we use viterbi algorithm to find the best tagging sequence for your query. For CRFs you can use packages like CRFSuite or CRF++. Using these packages all you have go do is create indicator functions and the package will train a model for you. Once trained you can use this model to predict the best sequence for your queries. CRFs are very fast.
This way of training without using vector representation of words will generalise your model without the need of retraining. [Look at NER using CRFs].
I'm having an issue with querying an index where a common search term also happens to be part of a company name interspersed throughout most of the documents. How do I exclude the business name in results without effecting the ranking on a search that includes part of the business name?
example: Bobs Automotive Supply is the business name.
How can I include relevant results when someone searches automotive or supply without returning every document in the index?
I tried "-'Bobs Automotive Supply' +'search term'" but this seems to exclude any document with Bobs Automotive Supply and isn't very effective on searching 'supply' or 'automotive'
Thanks in advance.
Second answer here, based on additional clarification from first answer.
A few options.
Add the business name as StopWords in the StopWordFilter. This will stop Solr from Indexing them at all. Searches that use them will only really search for those words that aren't in the business name.
Rely on the inherent scoring that Solr will apply due to Term frequency. It sounds like these terms will be in the index frequently. Queries for them will still return the documents, but if the user queries for other, less common terms, those will get a higher score.
Apply a low query boost (not quite negative, but less than other documents) to documents that contain the business name. This is covered in the Solr Relevancy FAQ http://wiki.apache.org/solr/SolrRelevancyFAQ#How_do_I_give_a_negative_.28or_very_low.29_boost_to_documents_that_match_a_query.3F
Do you know that the article is tied to the business name or derive this? If so, you could create another field and then just exclude entities that match on the business name using a filter query. Something like
q=search_term&fq=business_name:(NOT search_term)
It may be helpful to use subqueries for this or to just boost down rather than filter out results.
EDIT: Update to question make this irrelavent. Leaving it hear for posterity. :)
This is why Solr Documents have different fields.
In this case, it sounds like there is a "Footer" field that is separate from your "Body" field in your documents. When searches are performed, they would only done against the Body, which won't include data from the Footer. You could even have a third field which is the "OriginalContent" field, which contains the original copy for display purposes. You wouldn't search that, just store it for later.
The important part is to create the two separate fields in your schema and make sure that you index those field that you want to be able to search.