Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [natural-language-process]

Natural language processing (NLP) is a field of computer science, artificial intelligence, and linguistics concerned with the interactions between computers and human (natural) languages. As such, NLP is related to the area of human–computer interaction. Many challenges in NLP involve natural ...

1
vote
2answers
22 views

Continous bag of words claimed to be unsupervised, how is it working?

I'm following these two lectures on CBOW and skip-gram word2vec models. The first is lec 12 and the next lec 13 of a deep learning series https://www.youtube.com/watch?v=syWB-YMYZvI https://www....
0
votes
0answers
16 views

How is Universal Sentence Encoder trained using Deep Averaging Network (DAN)?

In the paper of Universal Sentence Encoder (USE), the author mentions it to be trained using transfer learning in an unsupervised manner in two forms: 1. Using Deep Averaging Network (DAN) 2. Using ...
0
votes
0answers
5 views

Hierachical Softmax Example In Deep Learning Book

I was learning neural network using the book "Deep Learning" by Ian Goodfellow, Yoshua Bengio and Aaron Courville. Section 12.4.3.2 has an example to show the computation cost improvement from ...
1
vote
1answer
25 views

Updating Google News Word2vec Word Embedding?

Is it possible to update the Google News Word Embedding with a custom text dataset (text data pertaining to a particular domain) ? Google News Word2Vec - Word Embedding clearly helps us to come with ...
0
votes
0answers
10 views

Sequence tokenization and pretrained embedding layers

Sequence tokenization and pretrained embedding initialization - say you have a unique (but not huge) corpus of texts, and you also load a pretrained embedding vector (for example GloVe-100d). What's ...
0
votes
0answers
10 views

How CNN contributes differently in sentiment classification task than RNN?

I would like to know how fundamentally CNN is different from RNN (Many to one) for sentiment classification task. More specifically, what CNN models can learn from data that the RNN can't learn or ...
1
vote
0answers
18 views

Is there a way to automatically generate a string given an input of another string? [closed]

I am fairly new to data science in general, and I'm wondering if it is possible to use machine learning/natural language processing to generate definitions for various terms. My team has recently ...
1
vote
2answers
39 views

What is a suitable loss function and evaluation metric for a classification model with large number of unbalanced target classes?

I am building a multiclass classifier to predict the "Intent" of a question. There are some 100 classes in the target variable and each target class contains an unequal proportion of observations/...
1
vote
0answers
22 views

How to learn word embedding from a context on the fly?

Consider the fictional word tahiliuk in the sentence “We found a small, fluffy tahiliuk running around our garden.” While hearing a new word used in context, people are remarkably adept at inferring a ...
0
votes
1answer
20 views

Find correct forms of a word

I'm trying to find all grammatical forms for words from a dataset. I'm new to NLP. I'm using a combo: spaCy (to get a base form of a word), ...
0
votes
1answer
22 views

How do you measure performance for word prediction tasks?

Say I have to predict the next word in a sentence, given the initial few words. Suppose the prefix is "I went to _____". This prefix is common enough that it might appear 10 times in the training ...
1
vote
0answers
10 views

TextRank algorithm for Web content

I am looking for an algorithm that would be able to extract meaningful keyphrases from web articles. Each article has more than 2000 words and information is structured using paragraphs, h1, h2 tags ...
0
votes
1answer
18 views

I am getting a Type Error in this Line

Diff = [i - j for i,j in zip(text_features, author_signature)] Diff is a List , text_features = [1, 2, 3] , author_signature = [3, 2, 1]
1
vote
0answers
17 views

Audio signal signal processing for background noise reduction or removal

I am performing simple audio recognition using tensor-flow to spot key word or hot word detection. The graph takes the microphone input directly and performs "Audio spectrometer --> mfcc's --> and ...
0
votes
0answers
13 views

What is the correct way to calculate the entropy of a language model on a data-set of sentences?

I want to fit the parameters of my language model by minimizing the entropy/ maximizing likelihood of my language model on my data-set. However, I am uncertain as how I should go about doing this. ...
0
votes
0answers
13 views

Comment Classifier

I have a problem where I'm trying to sort comments on cases by their types People type different comments in response to questions customers ask. Mostly though the comment will either be a comment ...
3
votes
2answers
66 views

Classification of Conversations in Text

I am trying to pick a technique for classifying conversational text. I am concerned about treating the problem at a level of fidelity of each individual message because people often say things like, "...
0
votes
0answers
27 views

Intiative detection problem

I currently try to wrap my head around a problem of detecting an initiative in a company report document. The following are the types of initiatives a company can report: health, no_poverty, ...
2
votes
1answer
26 views

Confidence Intervals for Multi-Categorical Votes

I have an ngram-based language model that produces a long tag list for a given sentence. For example, the just-previous sentence, broken into bigrams, and run through the model might produce something ...
1
vote
1answer
24 views

best activation function for ensemble?

i have created some logistic regression model (different preprocessing) with softmax function. and i mix all model with an ensemble with a hierarchical method. so the output of all model (base) will ...
1
vote
0answers
18 views

Using an ontology to recognize named entities in free text

I'm trying to solve a fairly basic problem in NPL efficiently. What tool or software package would you use to identify the words, or group of words that are part of an given ontology within a free ...
1
vote
0answers
18 views

What approach to use to detect violations of media ethics in news?

I've been trying to come up with a solution to detect violations of media ethics in news articles. For example, I need to detect if an article has mentioned the name of a victim of rape. So far, I've ...
0
votes
0answers
45 views

Recommending top answerers for a Question on Quora/Stackexchange sites

I want to make a tool that will tell me who can potentially answer a question on Quora or StackExchange. The tool will take input the text of a question, and output a sorted list of users who can ...
1
vote
0answers
18 views

Common deep learning practices in NLP for text classification

Are there any articles about best modern techniques in text classification (not only for English texts, but in general)? In particular, I'm interested: what kind of text preprocessing techniques are ...
2
votes
1answer
38 views

word/sentence alignment for English document

I have a English document, which is preprocessed into two versions. I want to align words or sentences from these two versions of document. A simple example is as below: ...
1
vote
0answers
17 views

Check If Answer is Correct by Similarity

I am new to data science and machine learning. Let's say that I have a question, and some correct answers for that question (for example, 10 correct answers). Is there a way to get a new answer as ...
1
vote
1answer
207 views

Difference between IOB and IOB2 format?

I have to tag a dataset for NER. I came across conll2002/esp. What I understand so far, in IOB2 format if I want to tag '...
2
votes
0answers
18 views

How do I perform Sentiment Analysis on Tweets in the following pattern:

I have tweets obtained based on matches (football) before the match begins. I have tweets which specify a team will win 3-1 and so on which are easily analyzed using regular expressions. I am facing ...
0
votes
1answer
30 views

Classifying whether a comment or review is a complaint or appreciation of product and extracting the Topic?

I need to classify whether a given review or comment is a complaint or appreciation. This is planned to be used in multiple places, product review pages of own site as well as facebook and twitter. ...
1
vote
0answers
8 views

Grouping prefix and term queries

Consider the following context: You have a website that is offering a search function, which produces a list of matching articles. The search has prefix functionality: if you are looking for "...
1
vote
1answer
21 views

how to encode labels for relationship extraction

I am trying to extract relationship from text. So, lets take the following text "He went to movie. but, they went to school" So, here the relationship's are "He and Movie", "they and school". How ...
0
votes
0answers
22 views

NLP research: Emotive conjugation

Is there any formal NLP research into emotive conjugation (aka Russel's conjugation)? Here are some examples of emotive conjugation by Bertrand Russell that are shown on the Wikipedia page: I am ...
0
votes
0answers
12 views
1
vote
0answers
80 views

Loss function for Hierarchical Multi-label classification

I am looking to try different loss functions for a hierarchical multi-label classification problem. So far, I have been training different models or submodels (e.g., a simple MLP branch inside a ...
0
votes
0answers
21 views

Unsupervised answering for a predefined set of questions

I am working on a project to read up a text segment and find answers to a specific set of questions, in order to do some information extraction. I have a set of text corpus (each of about 3000 words),...
0
votes
0answers
14 views

How to extract event from news article and merge similar event together

TL;DR Is there a way to extract events from news and cluster similar news event together? I am following the ACE methodology currently, is that a viable way? Longer version: I am currently working ...
2
votes
0answers
18 views

Joint embedding of word and image

I often see some papers, in which the authors do the point-wise multiplication of word embedding and the image embedding. As the image shows below, my question is how come the implementation works?? I ...
3
votes
0answers
50 views

multiple intents for modifying an intent of a sentence?

Say I have a sentence like 'I refuse to fly' or 'I'd like to fly'. I also have a sentence like 'I don't want to sit'. When training custom intents in one of the available NLU engines (rasa/wit/luis), ...
1
vote
0answers
11 views

How are natural language generation algorithms given a target

I've started learning about NLP and NLG and I'm fascinated! I've been blown away by the things I've seen from NLP; but I have a few questions about NLG. All my questions boil down to this: Given a ...
0
votes
0answers
19 views

Extract/detect IDs (like flight booking ids) from text

I'm looking to extract ids from the body of an email. The ids are similar to flight booking IDs. For example, in an email, I would like to obtain the booking reference (something like MNFF3RGC or MNF-...
0
votes
0answers
12 views

Expanding entity extraction to certain types of named-noun phrases (Bi-grams or tri-grams)

I have a corpus of articles from business publications. I'm interesting in extraction information relating to specific types of technologies and processes, as well as just interesting phrases. ...
1
vote
1answer
48 views

Question classification

I have 10 classes and 10-15 questions in each class . Given a new question, I want to find the class to which the question is most similar?
1
vote
1answer
18 views

How to find impactful words affecting classification?

So I know there are many methods to classify sentences into types. Like in sentiment analysis (positive, negative, neutral), spam emails (spam, not spam), etc. The thing I want to ask is how would I ...
0
votes
1answer
27 views

Tools and Techniques for Analyzing German Automotive Discussion Forum Posts [closed]

I work for a German online disussion forum around all things automotive, a bit like a “StackOverflow for cars”, if you will. We would like to train a model using TensorFlow with our high quality ...
1
vote
0answers
60 views

Data scraping & NLP?

I'm scraping data from Bing search results for (non-commercial purposes, of course) on Python using BeautifulSoup. I've entered an Indian dessert name, called 'rasmalai' as the word that I am focusing ...
1
vote
0answers
26 views

Predicting a new document [closed]

I have a document, (purchase agreement) of approx. 100 pages. This document is sent from buyer to seller several times, and each time there is a negotiation. Negotiation could be anything. For eg. ...
0
votes
0answers
97 views

Case-Sensitive Word Embeddings for French

Are there any pre-trained case-sensitive word embeddings for French? The only word embeddings for French I have found is FastText and it is not case sensitive. I am currently working on problems ...
5
votes
1answer
136 views

Is it valid to include your validation data in your vocabulary for NLP?

At the moment, I am following best practices and creating a "bag of words" vector with a vocabulary from the training data. My cross validation (and test) datasets are transformed using this model, ...
1
vote
0answers
132 views

transfer learning with sentiment analysis?

The question is how good and what are some things to keep in mind when sentiment analysis models are tested on different datasets than they are trained on. Say the task is to perform sentiment ...
1
vote
2answers
34 views

How should I format input and output for text generation with LSTMs

I'm attempting to generate a response to an input line of text using an LSTM. I've considered various forms of input, including one-hot encoding each character in the line and passing each input line ...