When using the pipeline annotator, relation, I get back appropriate RelationMention objects for each sentence. These are binary type objects with two entity mentions and a corresponding relation type.
However, in the code, I also see EventMention objects which can be obtained from the sentence in much the same way. In the class MachineReadingProperties, I see that extraction of relations and extraction of events both default to true. However, I am only seeing generated relations and not generated events.
I can find no mention of events in the Stanford documentation, nor does the page describing the relation annotator or how to train a custom relation model describe it. There are no links to research papers on the event portion, just the link to the Roth and Yih paper on relations.
So do events work with the relation annotator and if so are there any more documents describing them?
From tracing the code, I see that EventMention is only used in conjunction with the ACE2005 code. It does not appear to be connected with any of the pipeline annotators and cannot be directly created in that manner.
Related
In the v3 api for building LUIS apps I notice an emphasis on Machined learned entities. When working with them I notice something that concerns me and I was hoping to get more insight into the matter.
The idea is that when using a machined learned entity you can bind it to descriptors of phrase lists or other entities or list entities as a constraint on that machined learned entity. Why not just aim to extract the list entity by itself? What is the purpose of wrapping it in a machined learnt object?
I ask this because I have always had great success with lists. It very controllable albeit you need to watch for spelling mistakes and variations to assure accuracy. However, when I use machined learnt entities I notice you have to be more careful with word order. If there is a variation it could not pick up that machined learnt entity.
Now training would fix this but in reality if I know I have the intent I want and I just need entities from that what really does the machine learnt entity provide?
It seems you need to be more careful with it.
Now I say this with this suspicion. Would the answer lie in the fact that a machine learnt entity would increase intent detection where a list entity would only serve to increase entity detection. If that is the answer that most fits I think I can see the solution to what it is I am looking for.
EDITED:
I haven't been keeping up with LUIS ever since I went on maternity leave, and lo and behold, it's moving from V2 to V3!
The following shows an email conversation from a writer of the LUIS team's documentation.
LUIS is moving away from different types of entities toward a single ML entity to encapsulate a concept. The ML entity can have children which are ML entities themselves. An ML entity can have a feature directly connected to it, instead of acting as a global feature.
This feature can be a phrase list, or it can be another model such as a prebuilt entity, reg ex entity, or list entity.
So a year ago a customer might have built a composite entity and thrown features into the app. Now they should create an ML entity with children, and these children should have features.
Now (before //MS Build Conference) any non-phrase-list feature can be a constraint (required) so a child entity with a constrained regex entity won’t fire until the regex matches.
At/after //Build, this concept has been reworked in the UI to be a required feature – same idea but different terminology.
...
This is about understanding a whole concept that has parts, so an address is a typical example. An address has street number, street name, street type (street/court/blvd), city, state/province, country, postal code.
Each of the subparts is a feature (strong indicator) that an address is in the utterance.
If you used a list entity but not as a required feature to the address, yes it would trigger, but that wouldn’t help the address entity which is what you are really trying to get.
If however, you really just want to match a list, go head. But when the customer says the app isn’t predicting as well as they thought, the team will come back to this concept of the ML entity parent and its parts and suggest changes to the entities.
This question is very similar to my question, however due to the way SO works, I think it is better to ask a new question rather than just continue a thread.
CoreNLP has the Simple API which allows for quicker access to various components of the NLP pipeline. The way to get named entities appears to be:
Form a document annotation from the text
Get the sentences from the document object
Use nerTags() from the sentences object to get the token-by-token ner labeling.
Via other mechanisms, as talked about in the question link above, one can retrieve full multi-token entity mentions such as George Washington, which is an entity mention composed of 2 tokens. Is there a way using the simple api to get these multi-token entity mentions?
Yes, though it gives you less information than the full API, returning only the String spans of the mention. See Sentence#mentions(String) and Sentence#mentions().
If you want to get more information about a mention, you'll have to either use the regular API, or re-implement the logic in these functions. You can also try mucking around in the raw Proto, which will certainly have all the information you could possibly want, but in a less-than-pleasant proto interface. The proto definition is here.
I'm using IBM Rational Rose, but I'm not sure if I'm able to model/design the methods/procedures which are known as "operations" within a class onto "UML User Class Diagram". Is there any way to model the algorithm or the code of 'operations' (i.e something like flowchart) via the software? If so, is there any possibility to get the methods design auto-implementation integrated via code generation in order to define them within a java source file?
Another way to model behavior is to use StateMachine, Constraints, Sequence and Timing diagrams. Of course, you can simply write Notes describing behavior in plain words.
You can use activity diagram, activity diagrams are near a flow chart.
See rsa activity diagram
On your activity diagram, you create a partition and you can link your partition to you operation. Then you create callOperation action which can be linked to method call.
I create a class diagram with 4 class Class1, Class2, Class3, Class4, each one containing a method operationx.
And here is a simple example modeling operation1. The important point is that the partition named Operation1 is linked in the UML model to Class1:operation1 and the 3 actions are linked to method operations. This is not a "typo" tips.
You can look also to sequences diargam but it does not look like a flow chart.
I have developed a system where various classes have attributes consisting of a custom formula. The formula can contain special tokens which refer to different types of object. For example an object of class FruitSalad may have the following attribute;
$contents = "[A12] + [B76]";
In somewhat abstract terms, this means "add apple 12 to banana 76". It can also get significantly more complex than that with as many as 15 or 20 references to other objects involved in one formula.
I have a trait which passes formulae such as this and each time it finds a reference to a model (i.e. "[A12]") it gets it from the database with A::find(12) and adds it to an array of component objects which can be used for other processes later on in the request.
So, in essence, it's a relationship. But instead of a pivot table to describe the relationship, there is a formula on the parent model which can include references to child models.
This is all working. Yay! But it's really inefficient because there are so many tiny queries to get single models as formulae are parsed. One request may quite easily result in hundreds of queries. Oops.
I see two potential options;
1. Get all my apples and bananas from the database at the start of the request and get them from an in-memory store instead of from the database when parsing a formula (is this the repository pattern??).
2. Create a custom relation type (something like hasManyFromFormula) which makes eager loading work so that the parsing becomes much simpler because the relevant apples and bananas would already be loaded into the parent model.
Is there a precedent for this? As for why I am doing it like this, it would a bit tough to explain in brief but suffice to say it is to support a highly configurable data retrieval system which supports as-yet unknown input data configurations.
Help!
Thanks,
Geoff
Am not completely sure if it is the best solution, but in the end I created a new directory class for basic components and then set it up in the app service provider as a singleton. The constructor for the directory class loaded all models of several relevant classes and made them available as collections throughout the app.
I made a sentiment analysis model using Standford CoreNLP's library. So I have a bunch of ser.gz files that look like the following:
I was wondering what model to use in my java code, but based on a previous question,
I just used the model with the highest F1 score, which in this case is model-0014-93.73.ser.gz. And in my java code, I pointed to the model I want to use by using the following line:
props.put("sentiment.model", "/path/to/model-0014-93.73.ser.gz.");
However, by referring to just that model, am I excluding the sentiment analysis from the other models that were made? Should I be referring to all the model files to make sure I "covered" all the bases or does the highest scoring model trump everything else?
You should point to only the single highest scoring model. The code has no way to make use of multiple models at the same time.