The ideal goal is to correct the output from a speech2text model according to a reference corpus (the actual text). I don't mind using any off the selves tool either in NLP space or ElasticSearch
I have a reference corpus like the following:
It is a reliance that has led to a cycle of addiction that has
destroyed lives it is a cycle that makes you sick when you try to stop
and potentially takes your life when you don't and beyond its physical
effects this cycle of addiction also includes constant contact with
the criminal justice system and not just a cycle of arrests release
and violation.
In fact its much longer ...
On the other hand, I have a set of sentences that are recognized from a speech-2-text model in a CSV files
1, is a cycle that makes you dick when
2, try two stops and essentially hates your
3, posses activated
4, lives when who don't and beyond
As you can see there because the speech2text model is not perfect there are errors, for example
1) With references to the corpus these subsentences are misspelled (e.g. dick instead of sick in number the sentence number 1
2) there are sentences that do not match to the corpus at all - e.g. number 3
3) putting the sentences together does not cover the whole paragraph.
So basically I wonder what is this task called in the NLP topic, then I can do a better googling, and I appreciate if you name specific functions or examples that I can leverage, e.g. in Space or NLTK or any other tool.
edit : * I already have experience with nlp (coursera certificate) - therefore, looking for a concrete answer and/or example rather a scientific paper. This is not a general error correction task or the next work recommendation based on sequential models.
The most suited NLP technique for this is probably language models.
They predict the likelihood of a word given the previous words (or surrounding words).
They can be used for error correction .
You may find following useful:
article
page
Why do you think this is "not a general error correction task"? I think it is. You cool look into 'grammar correction' or 'sentence validity'.
Sentence validity is discussed at How to check whether a sentence is correct (simple grammar check in Python)?. The listed tools also provide suggestions, and could therefore be useful for you.
Related
We have Google Natural AI integrated into our product for Sentiment Analysis (https://cloud.google.com/natural-language). One of the customers complained that when they write "BAD" then it shows a positive sentiment.
On further investigation, we found that when google Sentiment Analysis Natural Language API is called with input as BAD or Bad (pls see its in all caps or first letter caps ), it identifies text as an entity (a location or consumer good) & sends back the result as Positive while when we write "bad" in all small case, it sends negative.
Has anyone faced a similar problem? How did you solve it?
One obvious way looks like converting text into a small case but that may break some other use cases (maybe where entities do not get analyzed due to a small case text). Another way which we are building is to use our own dictionary of words with sentiments before calling google APIs but that doesn't answer the said problem, which may occur with any other text.
Inputs will help us. Thank you!
The NLP API uses an underlying model that is neural in nature. The knowledge comes from training on real world text. It is normal to get different results for different capitalizations as they can relate to different uses of the same trigram, e.g. Mike (person), mike (microphone, slang), MIKE (military alphabet entry).
The second key aspect is that the model is tuned and meant to be used on larger pieces of text and not on single words, hence good results can not be expected in this case.
I have been having this problem in a variety of different cases.
I'll share an example of one.
I have a few FAQ intents.
One answers "What is Named Entity Recognition"
These are it's utterances :
Tell me about Named Entity Recognition
Tell me about NER
What is NER
What do you mean by Named Entity Recognition
What is Named Entity Recognition
and the other answers "What is Optical Character Recognition?"
These are it's utterances :
OCR
What do you mean by OCR
Can you tell me what OCR is
Tell about OCR
What is optical character recognition
What is OCR
When I enter, "What is ocr?" it works as expected and shows the answer for OCR.
But when I instead enter OCR in all caps, with the same exact question (What is OCR?). It switches to the NER intent and shows me the answer for "What is NER?"
Can any one answer why it is doing so? and more important than that, What do I do to make it work as expected.
Do keep in mind that this is just one example. I have encountered this in many other similar scenarios too.
There was also a case where the intent utterances didn't seem to match even remotely. But it still switched to the wrong intent.
As per the Lex and Alexa documentation, acronyms in custom slot types should be written as either a single word in all caps (OCR) or lowercase letters separated by periods and spaces (o. c. r.).
Along the bottom of the table, you can see the examples for Fire HD7, Fire h. d., Fire HD, and Fire HD 7 that demonstrate this -- both of the valid options will resolve to the same Slot Value Output.
Assuming utterances are set up in accordance with best practice, if you're providing vocal input, it's important to note that utterances are sensitive to things such as inflection in your voice, pacing/space between words, accents, and more.
As for immediate steps to improve accuracy, you can always try breaking up your intents further, where instead of having two intents, you have one for each permutation of custom slot value (NER, Named Entity Recognition, OCR, and Optical Character Recognition). It's easy for humans to understand that the first letter of a phrase maps to the letters in an acronym, but when it comes to teaching a chatbot to understand that these phrases are synonymous, that's a bit harder.
In the end I didn't find a proper solution but used some really inelegant workarounds, but hey as long as it works :D
The workaround I used was to make a "what" intent, a "how" intent etc. Keeping the sentence structure intact:
For example :
IntentName => "Bot_HowTo"
Utterances =>
"What is {slotName}"
"What are {slotName}"
"Meaning of {slotName}"
Slots =>
name : "slotName"
values (using synonyms) :
{OCR => "ocr", Optical Character recognition"}
{NER=> "ner", Named Entity Recognition"}
This makes the amount of intents needed much less and also eliminates a lot of the ambiguity. All questions that have "what" or similar formats go straight to that intent.
And then in my codehook I see which synonym was matched and provide the answer accordingly.
I want to read the bold words as the column names in the dataframe and the string following the bold letters as the value for that particular row.
<posts>
<**row Id**="5" PostTypeId="1" **CreationDate**="2014-05-13T23:58:30.457" **Score**="7" ViewCount="315" **Body**="<p>I've always been interested in machine learning, but I can't figure out one thing about starting out with a simple "Hello World" example - how can I avoid hard-coding behavior?</p><p>For example, if I wanted to "teach" a bot how to avoid randomly placed obstacles, I couldn't just use relative motion, because the obstacles move around, but I don't want to hard code, say, distance, because that ruins the whole point of machine learning.</p><p>Obviously, randomly generating code would be impractical, so how could I do this?</p>" **OwnerUserId**="5" LastActivityDate="2014-05-14T00:36:31.077" Title="How can I do simple machine learning without hard-coding behavior?" Tags="<machine-learning>" AnswerCount="1" CommentCount="1" FavoriteCount="1" ClosedDate="2014-05-14T14:40:25.950"/>
<**row Id**="7" **PostTypeId**="1" **AcceptedAnswerId**="10" CreationDate="2014-05-14T00:11:06.457" Score="2" ViewCount="297" Body="<p>As a researcher and instructor, I'm looking for open-source books (or similar materials) that provide a relatively thorough overview of data science from an applied perspective. To be clear, I'm especially interested in a thorough overview that provides material suitable for a college-level course, not particular pieces or papers.</p>" OwnerUserId="36" LastEditorUserId="97" LastEditDate="2014-05-16T13:45:00.237"LastActivityDate="2014-05-16T13:45:00.237" Title="What open-source books (or other materials) provide a relatively thorough overview of data science?" Tags="<education><open-source>" AnswerCount="3" CommentCount="4" FavoriteCount="1" **ClosedDate**="2014-05-14T08:40:54.950"/>
</posts>
I am looking to recognize simple phrases like the ones what happens in google calendar
but rather than parsing Calendar Entries I have to parse Sentence related to finance, accounting and to do lists. So For example I have to parse sentences like
I spent 50 dollars on food yesterday
I need to mark an separate the info as Reason : 'food' , Cost : 50 and Time: <Yesterday's Date>
My question is do I go in for a full fledged Natural Language Processing like
given in these Questions and use Something like GATE
Machine Learning and Natural Language Processing
Natural Language Processing in Ruby
Ideas for Natural Language Processing project?
https://stackoverflow.com/a/3058063/492561
Or is it better to Write simple grammars using Something like AntLR and try to recognize it .
Or should I go really low and just Define a syntax and use Regular expressions .
Time is a Constraint , I have about 45 - 50 Days , And I don't know how to use AntLR or NLP libraries like GATE.
Preferred languages : Python , Java , Ruby (Not in any particular order)
PS : This is not home-work , So please Don't tag it as so.
PPS : Please try to give an answer with Facts on why using a particular method is better.
even if a particular method may not fit inside the time constraint please feel free to share it because It might benefit someone else .
You could look at named entity recognition indeed. From your question I understand your domain is pretty well defined, so you can identify the (few?) entities (dates, currencies, money amount, time expressions, etc.) that are relevant for you. If the phrases are very simple, you could go with a rule-based approach, otherwise it's likely to get too complex too soon.
Just to get yourself up and running in a few sec, http://timmcnamara.co.nz/post/2650550090/extracting-names-with-6-lines-of-python-code is an extremely nice example of what you could do. Of course I would not expect an high accuracy from just 6 lines of python, but it should give you an idea of how it works:
1>>> import nltk
2>>> def extract_entities(text):
3... for sent in nltk.sent_tokenize(text):
4... for chunk in nltk.ne_chunk(nltk.pos_tag(nltk.word_tokenize(sent))):
5... if hasattr(chunk, 'node'):
6... print chunk.node, ' '.join(c[0] for c in chunk.leaves())
The core idea is on line 3 and 4: on line 3 it split text in sentences and iterates them.
On line 4, it splits the sentence in tokens, it runs "part of speech" tagging on the sentence, and then it feeds the pos-tagged sentence to the named entity recognition algorithm. That's the very basic pipeline.
In general, nltk is an extremely beautiful piece of software, and very well documented: I would look at it. Other answers contain very useful links.
Your task is a type of Information Extraction task, specifically relation/fact extraction, preceded by Named Entity Recognition.
Take a look at the following frameworks for Java/Python:
GExp
GATE
NLTK. Python. Book chapter on Information Extraction.
UIMA. (used for IBM's Watson.)
I'm going to be running through live twitter data and attempting to pull out tweets that mention, for example, movie titles. Assuming I have a list of ~7000 hard-coded movie titles I'd like to look against, what's the best way to select the relevant tweets? This project is in it's infancy so I'm open to any looking into any solution (i.e. language agnostic.) Any help would be greatly appreciated.
Update: I'd be curious if anyone had any insight to how the Yahoo! Placemaker API, solves this problem. It can take a text string and return a geocoded JSON result of all the locations mentioned in it.
You could try Wu and Manber's A Fast Algorithm For Multi-Pattern Searching.
The multi-pattern matching problem lies at the heart of virus scanning, so you might look to scanner implementations for inspiration. ClamAV, for example, is open source and some papers have been published describing its algorithms:
Lin, Lin and Lai: A Hybrid Algorithm of Backward Hashing and Automaton Tracking for Virus Scanning (a variant of Wu-Manber; the paper is behind the IEEE paywall).
Cha, Moraru, et al: SplitScreen: Enabling Efficient, Distributed Malware Detection
If you use compiled regular expressions, it should be pretty fast. Maybe especially if you put lots of titles in one expression.
Efficiently searching for many terms in a long character sequence would require a specialized algorithm to avoid testing for every term at every position.
But since it sounds like you have short strings with a known pattern, you should be able to use something fairly simple. Store the set of titles you care about in a hash table or tree. Parse out "string1" and "string2" from each tweet using a regex, and test whether they are contained in the set.
Working off what erickson suggested, the most feasible search is for the ("is better than" in your example), then checking for one of the 7,000 terms. You could instead narrow the set by creating 7,000 searches for "[movie] is better than" and then filtering manually on the second movie, but you'll probably hit the search rate limit pretty quickly.
You could speed up the searching by using a dedicated search service like Solr instead of using text parsing. You might be able to pull out titles quickly using some natural language processing service (OpenCalais?), but that would be better suited to batch processing.
For simultaneously searching for a large number of possible targets, the Rabin-Karp algorithm can often be useful.