I have what I think is a simple question. I am trying to put together a question answering system and I am having trouble converting a natural question to a knowledge graph triple. Here is an example of what I mean:
Assume I have a prebuilt knowledge graph with the relationship:
((Todd) -[:picked_up_by]-> (Jane))
How can I make this conversion:
"Who picked up Todd today?" -> ((Todd) -[:picked_up_by]-> (?))
I am aware that there is a field dedicated to "Relationship Extraction", but I don't think that this fits that problem if I could name it, "question triple extraction" would be the name of what I am trying to do.
Generally speaking, it looks like a relation extraction problem, with your custom relations. Since the question is too generic, this is not an answer, just some links.
Check out reading comprehension: projects on github and lecture by Christopher Manning
Also, look up Semantic Role Labeling.
Related
Is there a way to generate a one-sentence summarization of Q&A pairs?
For example, provided:
Q: What is the color of the car?
A: Red
I want to generate a summary as
The color of the car is red
Or, given
Q: Are you a man?
A: Yes
to
Yes, I am a man.
which accounts for both question and answer.
What would be some of the most reasonable ways to do this?
I had to once work on solving the opposite problem, i.e. generating questions out of sentences from Wikipedia articles.
I used the Stanford Parser to generate parse trees out of all possible sentences in my training dataset.
e.g.
Go to http://nlp.stanford.edu:8080/parser/index.jsp
Enter "The color of the car is red." and click "Parse".
Then look at the Parse section of the response. The first layer of that sentence is NP VP (noun phrase followed by a verb phrase).
The second layer is NP PP VBZ ADJP.
I basically collected these patterns across 1000s of sentences, sorted them how common each patter was, and then used figured out how to best modify this parse tree to convert into each sentence in a different Wh-question (What, Who, When, Where, Why, etc)
You could you easily do something very similar. Study the parse trees of all of your training data, and figure out what patterns you could extract to get your work done. In many cases, just replacing the Wh word from the question with the answer would give you a valid albeit somewhat awkwardly phrases sentence.
e.g. "Red is the color of the car."
In the case of questions like "Are you a man?" (i.e. primary verb is something like 'are', 'can', 'should', etc), swapping the first 2 words usually does the trick - "You are a man?"
I don't know any NLP task that explicitly handles your requirement.
Broadly, there are two kinds of questions. Questions that expect a passage as the answer such as definition or explain sort: What is Ebola Fever. The second type are fill in the blank which are referred to as Factoid Questions in the literature such as What is the height of Mt. Everest?. It is not clear what kind of question you would like to summarize. I am assuming you are interested in factoid questions as your examples refer to only them.
A very similar problem arises in the task of Question Answering. One of the first stages of this task is to generate query. In the paper: An Exploration of the Principles Underlying
Redundancy-Based Factoid Question
Answering; Jimmy Lin 2007, the author claims that better performance can be achieved by reformulating the query (see section 4.1) to the form more likely to appear in free text. Let me copy some of the examples discussed in the paper.
1. What year did Alaska became a state?
2. Alaska became a state ?x
1. Who was the first person to run the miles in less than four minutes?
2. The first person to run the miles in less than four minutes was ?x
In the above examples, the query in 1 is reformulated to 2. As you might have already observed, ?x is the blank that should be filled by the answer. This reformulation is carried out through a dozen hand-written rules and are built into the software tool discussed in the paper: ARANEA. All you have to do is to find the tool and use it, the paper is a good ten years old, I cannot promise you anything though :)
Hope this helps.
I am experimenting with machine learning in general, and Bayesian analysis in particular, by writing a tool to help me identify my collection of e-books. The input data consist of a set of e-book files, whose names and in some cases contents contain hints as to the book they correspond to.
Some are obvious to the human reader, like:
Artificial Intelligence - A Modern Approach 3rd.pdf
Microsoft Press - SharePoint Foundation 2010 Inside Out.pdf
The Complete Guide to PC Repair 5th Ed [2011].pdf
Hamlet.txt
Others are not so obvious:
Vsphere5.prc (Actually 'Mastering VSphere 5' by Scott Lowe)
as.ar.pdf (Actually 'Atlas Shrugged' by Ayn Rand)
Rather than try to code various parsers for different formats of file names, I thought I would build a few dozen simple rules, each with a score.
For example, one rule would look in the first few pages of the file for something resembling an ISBN number, and if found would propose a hypothesis that the file corresponds to the book identified by that ISBN number.
Another rule would look to see if the file name is in 'Author - Title' format and, if so, would propose a hypothesis that the author is 'Author' and the title is 'Title'. Similar rules for other formats.
I thought I could also get a list of book titles and authors from Amazon or an ISBN database, and search the file name and first few pages of the file for any of these; any matches found would result in a hypothesis being suggested by that rule.
In the end I would have a set of tuples like this:
[rulename,hypothesis]
I expect that some rules, such as the ISBN match, will have a high probability of being correct, when they are available. Other rules, like matches based on known book titles and authors, would be more common but not as accurate.
My questions are:
Is this a good approach for solving this problem?
If so, is Bayesian analysis a good candidate for combining all of these rules' hypotheses into compound score to help determine which hypothesis is the strongest, or most likely?
Is there a better way to solve this problem, or some research paper or book which you can suggest I turn to for more information?
It depends on the size of your collection and the time you want to spend training the classifier. It will be difficult to get good generalization that will save you time. For any type of classifier you will have to create a large training set, and also find a lot of rules before you get good accuracy. It will probably be more efficient (less false positives) to create the rules and use them only to suggest title alternatives for you to choose from, and not to implement the classifier. But, if the purpose is learning, then go ahead.
I've studied some simple semantic network implementations and basic techniques for parsing natural language. However, I haven't seen many projects that try and bridge the gap between the two.
For example, consider the dialog:
"the man has a hat"
"he has a coat"
"what does he have?" => "a hat and coat"
A simple semantic network, based on the grammar tree parsing of the above sentences, might look like:
the_man = Entity('the man')
has = Entity('has')
a_hat = Entity('a hat')
a_coat = Entity('a coat')
Relation(the_man, has, a_hat)
Relation(the_man, has, a_coat)
print the_man.relations(has) => ['a hat', 'a coat']
However, this implementation assumes the prior knowledge that the text segments "the man" and "he" refer to the same network entity.
How would you design a system that "learns" these relationships between segments of a semantic network? I'm used to thinking about ML/NL problems based on creating a simple training set of attribute/value pairs, and feeding it to a classification or regression algorithm, but I'm having trouble formulating this problem that way.
Ultimately, it seems I would need to overlay probabilities on top of the semantic network, but that would drastically complicate an implementation. Is there any prior art along these lines? I've looked at a few libaries, like NLTK and OpenNLP, and while they have decent tools to handle symbolic logic and parse natural language, neither seems to have any kind of proabablilstic framework for converting one to the other.
There is quite a lot of history behind this kind of task. Your best start is probably by looking at Question Answering.
The general advice I always give is that if you have some highly restricted domain where you know about all the things that might be mentioned and all the ways they interact then you can probably be quite successful. If this is more of an 'open-world' problem then it will be extremely difficult to come up with something that works acceptably.
The task of extracting relationship from natural language is called 'relationship extraction' (funnily enough) and sometimes fact extraction. This is a pretty large field of research, this guy did a PhD thesis on it, as have many others. There are a large number of challenges here, as you've noticed, like entity detection, anaphora resolution, etc. This means that there will probably be a lot of 'noise' in the entities and relationships you extract.
As for representing facts that have been extracted in a knowledge base, most people tend not to use a probabilistic framework. At the simplest level, entities and relationships are stored as triples in a flat table. Another approach is to use an ontology to add structure and allow reasoning over the facts. This makes the knowledge base vastly more useful, but adds a lot of scalability issues. As for adding probabilities, I know of the Prowl project that is aimed at creating a probabilistic ontology, but it doesn't look very mature to me.
There is some research into probabilistic relational modelling, mostly into Markov Logic Networks at the University of Washington and Probabilstic Relational Models at Stanford and other places. I'm a little out of touch with the field, but this is is a difficult problem and it's all early-stage research as far as I know. There are a lot of issues, mostly around efficient and scalable inference.
All in all, it's a good idea and a very sensible thing to want to do. However, it's also very difficult to achieve. If you want to look at a slick example of the state of the art, (i.e. what is possible with a bunch of people and money) maybe check out PowerSet.
Interesting question, I've been doing some work on a strongly-typed NLP engine in C#: http://blog.abodit.com/2010/02/a-strongly-typed-natural-language-engine-c-nlp/ and have recently begun to connect it to an ontology store.
To me it looks like the issue here is really: How do you parse the natural language input to figure out that 'He' is the same thing as "the man"? By the time it's in the Semantic Network it's too late: you've lost the fact that statement 2 followed statement 1 and the ambiguity in statement 2 can be resolved using statement 1. Adding a third relation after the fact to say that "He" and "the man" are the same is another option but you still need to understand the sequence of those assertions.
Most NLP parsers seem to focus on parsing single sentences or large blocks of text but less frequently on handling conversations. In my own NLP engine there's a conversation history which allows one sentence to be understood in the context of all the sentences that came before it (and also the parsed, strongly-typed objects that they referred to). So the way I would handle this is to realize that "He" is ambiguous in the current sentence and then look back to try to figure out who the last male person was that was mentioned.
In the case of my home for example, it might tell you that you missed a call from a number that's not in its database. You can type "It was John Smith" and it can figure out that "It" means the call that was just mentioned to you. But if you typed "Tag it as Party Music" right after the call it would still resolve to the song that's currently playing because the house is looking back for something that is ITaggable.
I'm not exactly sure if this is what you want, but take a look at natural language generation wikipedia, the "reverse" of parsing, constructing derivations that conform to the given semantical constraints.
Am thinking about a project which might use similar functionality to how "Quick Add" handles parsing natural language into something that can be understood with some level of semantics. I'm interested in understanding this better and wondered what your thoughts were on how this might be implemented.
If you're unfamiliar with what "Quick Add" is, check out Google's KB about it.
6/4/10 Update
Additional research on "Natural Language Parsing" (NLP) yields results which are MUCH broader than what I feel is actually implemented in something like "Quick Add". Given that this feature expects specific types of input rather than the true free-form text, I'm thinking this is a much more narrow implementation of NLP. If anyone could suggest more narrow topic matter that I could research rather than the entire breadth of NLP, it would be greatly appreciated.
That said, I've found a nice collection of resources about NLP including this great FAQ.
I would start by deciding on a standard way to represent all the information I'm interested in: event name, start/end time (and date), guest list, location. For example, I might use an XML notation like this:
<event>
<name>meet Sam</name>
<starttime>16:30 07/06/2010</starttime>
<endtime>17:30 07/06/2010</endtime>
</event>
I'd then aim to build up a corpus of diary entries about dates, annotated with their XML forms. How would I collect the data? Well, if I was Google, I'd probably have all sorts of ways. Since I'm me, I'd probably start by writing down all the ways I could think of to express this sort of stuff, then annotating it by hand. If I could add to this by going through friends' e-mails and whatnot, so much the better.
Now I've got a corpus, it can serve as a set of unit tests. I need to code a parser to fit the tests. The parser should translate a string of natural language into the logical form of my annotation. First, it should split the string into its constituent words. This is is called tokenising, and there is off-the-shelf software available to do it. (For example, see NLTK.) To interpret the words, I would look for patterns in the data: for example, text following 'at' or 'in' should be tagged as a location; 'for X minutes' means I need to add that number of minutes to the start time to get the end time. Statistical methods would probably be overkill here - it's best to create a series of hand-coded rules that express your own knowledge of how to interpret the words, phrases and constructions in this domain.
It would seem that there's really no narrow approach to this problem. I wanted to avoid having to pull along the entirety of NLP to figure out a solution, but I haven't found any alternative. I'll update this if I find a really great solution later.
I need to parse recipe ingredients into amount, measurement, item, and description as applicable to the line, such as 1 cup flour, the peel of 2 lemons and 1 cup packed brown sugar etc. What would be the best way of doing this? I am interested in using python for the project so I am assuming using the nltk is the best bet but I am open to other languages.
I actually do this for my website, which is now part of an open source project for others to use.
I wrote a blog post on my techniques, enjoy!
http://blog.kitchenpc.com/2011/07/06/chef-watson/
The New York Times faced this problem when they were parsing their recipe archive. They used an NLP technique called linear-chain condition random field (CRF). This blog post provides a good overview:
"Extracting Structured Data From Recipes Using Conditional Random Fields"
They open-sourced their code, but quickly abandoned it. I maintain the most up-to-date version of it and I wrote a bit about how I modernized it.
If you're looking for a ready-made solution, several companies offer ingredient parsing as a service:
Zestful (full disclosure: I'm the author)
Spoonacular
Edamam
I guess this is a few years out, but I was thinking of doing something similar myself and came across this, so thought I might have a stab at it in case it is useful to anyone else in f
Even though you say you want to parse free test, most recipes have a pretty standard format for their recipe lists: each ingredient is on a separate line, exact sentence structure is rarely all that important. The range of vocab is relatively small as well.
One way might be to check each line for words which might be nouns and words/symbols which express quantities. I think WordNet may help with seeing if a word is likely to be a noun or not, but I've not used it before myself. Alternatively, you could use http://en.wikibooks.org/wiki/Cookbook:Ingredients as a word list, though again, I wouldn't know exactly how comprehensive it is.
The other part is to recognise quantities. These come in a few different forms, but few enough that you could probably create a list of keywords. In particular, make sure you have good error reporting. If the program can't fully parse a line, get it to report back to you what that line is, along with what it has/hasn't recognised so you can adjust your keyword lists accordingly.
Aaanyway, I'm not guaranteeing any of this will work (and it's almost certain not to be 100% reliable) but that's how I'd start to approach the problem
This is an incomplete answer, but you're looking at writing up a free-text parser, which as you know, is non-trivial :)
Some ways to cheat, using knowledge specific to cooking:
Construct lists of words for the "adjectives" and "verbs", and filter against them
measurement units form a closed set, using words and abbreviations like {L., c, cup, t, dash}
instructions -- cut, dice, cook, peel. Things that come after this are almost certain to be ingredients
Remember that you're mostly looking for nouns, and you can take a labeled list of non-nouns (from WordNet, for example) and filter against them.
If you're more ambitious, you can look in the NLTK Book at the chapter on parsers.
Good luck! This sounds like a mostly doable project!
Can you be more specific what your input is? If you just have input like this:
1 cup flour
2 lemon peels
1 cup packed brown sugar
It won't be too hard to parse it without using any NLP at all.