Questions tagged [nlp]

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 language understanding, that is, enabling computers to derive meaning from human or natural language input, and others involve natural language generation.

415 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
7
votes
0answers
321 views

ngram and RNN prediction rate wrt word index

I tried to plot the rate of correct predictions (for the top 1 shortlist) with relation to the word's position in sentence : I was expecting to see a plateau sooner on the ngram setup since it ...
5
votes
1answer
157 views

How to compute document similarities in case of source codes?

I try to detect the probability of common authorship (person, company) of different kind of source code texts (webpages, program codes). My first idea is to apply the usual NLP tools like any token ...
4
votes
1answer
395 views

Autocomplete with deep learning

I got interested in autocompletion using deep learning and tutorials that I found where conditioned always on specific number of characters (given 40 characters predict the next character or the whole ...
4
votes
1answer
72 views

How to train neural word embeddings?

So I am new to Deep Learning and NLP. I have read several blog posts on medium, towardsdatascience and papers where they talk about pre-training the word embeddings in an unsupervised fashion and then ...
4
votes
1answer
313 views

Find matching text from a text column

This is my first time to use Data Analytics tool to figure out a solution to a problem. I have a table with following columns ...
4
votes
1answer
1k views

Convolutional Network for Text Classification

I am trying to train a convolutional neural network with Keras at recognizing tags for Stack Exchange questions about cooking. The i-th question element of my data-set is like this: ...
4
votes
2answers
228 views

How to change default values of ANNIE resources in GATE from java code?

In GATE default values for ANNIE are set during initialization, but sometimes based on requirements they have to be changed. My Requirement : I want to extract English sentences without considering ...
3
votes
1answer
387 views

How to add a CNN layer on top of BERT?

I am just playing with bert (Bidirectional Encoder Representation from Transformer) Research Paper Suppose I want to add any other model or layers like Convolutional Neural Network layers (CNN), Non ...
3
votes
0answers
89 views

Why categorical cross entropy loss is not correlated with NLP scores?

I'm training a deep network for image captioning which is consist of one CNN and three GRUs. During training epoch by epoch model loss (categorical cross entropy) decreases but when I'm measuring <...
3
votes
2answers
176 views

meaning of fine-tuning in nlp task

There are two types of transfer learning model. One is feature extraction, where the weights of the pre-trained model are not changed while training on the actual task and other is the weights of the ...
3
votes
0answers
3k views

How is WordPiece tokenization helpful to effectively deal with rare words problem in NLP?

I have seen that NLP models such as BERT utilize WordPiece for tokenization. In WordPiece, we split the tokens like playing to play and ##ing. It is mentioned that it covers a wider spectrum of Out-Of-...
3
votes
2answers
519 views

Training NLP with multiple text input features

Question: How can I train a NLP model with discrete labels that is based on multiple text input features? Background: I'm trying to predict the difficulty of a 4-option multiple choice exam ...
3
votes
0answers
91 views

How to implement hierarchical labeling classification?

I am currently working on task of eCommerce product name classification, so I have categories and subcategories in product data. I noticed that using subcategories as labels delivers worse results (84%...
3
votes
0answers
169 views

What are the rules when extracting SVO triples from preprocessed text?

If you have some already preprocessed text that is tagged, what are the rules to extract SVO triplets if you want a triple like (word, word, word). Can you give the sentence as example and extract all ...
3
votes
0answers
90 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), ...
3
votes
1answer
76 views

Is it a red flag that increasing the number of parameters makes the model less able to overfit small amounts of data?

I'm training a deep network (CNN-LSTM-CRF) for Named Entity Recognition. Is there a reason that increasing the number of parameters would make the network less able to overfit a small training set (~...
3
votes
0answers
55 views

Determine the most important documents for supervised learning

I have somewhat of a general/high level question. Assume I'm doing supervised machine learning on some text data (tweets for example) and categorizing the documents to a certain taxonomy (multi-class ...
3
votes
3answers
1k views

Are there any good NLP APIs for comparing strings in terms of semantic similarity?

I want to create a chatbot which informs the user about traffic at the streets but not in real-time for the moment. I have created a small database with MySQL which has some data stored regarding ...
3
votes
0answers
135 views

How to do give input to CNN when doing a text processing?

As a signal processing engineering and being new to NLP, I am confused with giving input to CNN network. With my knowledge of CNN, I am trying to build a classifier for ethnicity with inputs as text ...
3
votes
0answers
160 views

How does Api.ai Google dialogueflow classifies “intent” and extracts data from slots

I am trying to build a very naive version of Api.ai, now Google DailogueFlow. I wanted to know two things. How DF classifies sentences with entities in it that can be user created and/or things like ...
3
votes
2answers
243 views

How to create domain rules from raw unstructured text using NLP and deep learning?

How to create domain rules from raw unstructured text using NLP and deep learning techniques ? For example for the below text on symptoms of Dengue, all three look pretty similar but if you want to ...
3
votes
0answers
291 views

sLDA vs. LDA+Classifier

For simplicity, suppose we're looking at Yelp reviews of restaurants, and are trying to classify the restaurant by cuisine type (e.g. "Italian, Japanese," etc.). Lets also assume our data already a ...
3
votes
0answers
421 views

Complete a Hungarian stem to a real word

I'm quite new to the NLTK package of Python and to NLP too (I usually work in R but for NLP purposes and scraping maybe Python is more able). I scrap articles from Hungarian newsportals and want to ...
2
votes
0answers
13 views

R train(method=“naive_bayes”) and naiveBayes() very different performance

I am an R novice and having some difficulty. I was hoping R would be a good (flexible, easy) way to do machine learning of textual data. A few years ago, I wrote a naive Bayesian classifier (from ...
2
votes
2answers
66 views

why an advanced LSTM model produce the same results as a simpler one?

I have implemented the model proposed in this article which is a text classification model that uses sentence representation rather than only word representation to classify texts. ...
2
votes
1answer
56 views

How to justify the usage of 200 dimensions in word vectors instead of the 300 dimensions?

When employing machine learning methods in NLP, most of studies use 200 or 300 dimensional vectors. 300 dimensional embeddings carry more information and this, therefore, is considered to produce ...
2
votes
1answer
59 views

Google NLP AutoML

I am doing research for Google NLP AutoML, What methodologies they have used, techniques, models, feature selection, hyper parameter optimization, etc. I could not find any paper on how google built ...
2
votes
0answers
20 views

NLP based Data Preprocessing Method to Improve Disease Name Prediction Using CRF and Word Embedding

I built a model( using CRF along bi lstm) to Predict New Disease Name/Entities from medical text data but the problem is Disease name appears only 5,6 times in 1 text file but on average text file ...
2
votes
0answers
15 views

How does a CBoW model convert a word to a vector?

A CBOW model actually takes multiple words as inputs and a targeted central word as the output. So, the trained model actually maps several words to a single one, I mean it takes context words and ...
2
votes
1answer
32 views

Is there a way to rank the Extracted Named Entities based on their importance/occurence in a document?

Looking for a way to rank the tens and hundreds of named entities present in any document in order of their importance/relevance in the context. Any thoughts ? Thanks in advance!
2
votes
0answers
31 views

how to work with NLP with other features

My dataset looks like this ...
2
votes
1answer
21 views

How to segment old digitized newspapers into articles

I'm working on a large corpus of french daily newspapers from the 19th century that have been digitized and where the data are in the form of raw OCR text files (one text file per day). In terms of ...
2
votes
1answer
15 views

Classification of substrings?

What is the appropriate method to find n-grams/sub-phrases/parts-of-sequences that are referring to a specific topic or belong to a certain category? For instance: Imagine a topic of "transfer of ...
2
votes
0answers
30 views

pros and cons of lexical vs machine learning methods for text mining

I wanted to know what are the pros and cons are of using lexical methods and machine learning methods for classifying texts based topic. I have used a simple method of mining documents related to a ...
2
votes
0answers
150 views

SpaCy vs AllenNLP?

I have used a little of both spaCy and allenNLP in my NLP projects. I like them both as they work very well with PyTorch (my DL framework choice!). But, I still cannot decide which one to master in a ...
2
votes
0answers
56 views

Predicting word from a set of words

My task is to predict relevant words based on a short description of an idea. for example "SQL is a domain-specific language used in programming and designed for managing data held in a relational ...
2
votes
2answers
68 views

Using nlp to analyze accident report

I want to use Natural Language Processing to analyze traffic accident reports and from the text determine two things: Direction of vehicle travel (just compass directions like north, southeast, etc.)...
2
votes
0answers
23 views

identifying the primary and secondary keywords in sentense

want to identify the primary and secondary keywords which are having an impact to sentences or comparison between 2 keywords. below is the example India and China has highest population in the ...
2
votes
0answers
124 views

Convert natural language text to structured data

Convert natural language text to structured data. I'm developing a bot to help user assist in identifying Apparels. The problem is to convert natural language text to structured data (list of ...
2
votes
0answers
88 views

Scraping financial web data

I recently started working as a data scientist and I am starting a web scraping and NLP project using Python. The idea is to create a program that searches for public information on the company's ...
2
votes
0answers
123 views

Paragraph Generator using BERT or GPT

I am trying to generate similar sentences, called paragraph generation. For example, what is the name of the eldest brother of ram? - For these paragraphs can be - who is the oldest brother of ram? , ...
2
votes
0answers
71 views

What is the motivation for row-wise convolution and folding in Kalchbrenner et al. (2014)?

I was reading the paper by Kalchbrenner et al. titled A Convolutional Neural Network for Modelling Sentences and am struggling to understand their definition of convolutional layer. First, let's take ...
2
votes
0answers
178 views

Keras value error: Operands could not be broadcast with with shapes(100,100) - GRU

I am trying to use Hierarchical Attention Networks for classification of news articles using 20 newsgroup dataset that i downloaded from the internet. I came across this code of the implementation and ...
2
votes
0answers
104 views

how to extract the Top contributing labels/words in universal-sentence-encoder-large - TransformerModel?

I'm using the universal-sentence-encoder-large (Transformer Model) encoding process for embedding and then using the embedding for Clustering - Basically for unsupervised learning. I want to get the ...
2
votes
2answers
159 views

Transform single-label data set into multi-label data set

I received a data set containing a string of text and a label that categorizes that text into one of 50 categories. I'm hoping to build a model that predicts which category a string of text belongs in....
2
votes
0answers
29 views

I have data of some movies and their subtitles.I want to classify them based on their ratings

I will convert the subtitles into vectors and use them as features to classify the movies into different categories based on their ratings.The problem that I am facing is my feature vector is much ...
2
votes
0answers
459 views

Combine multiple features for text classification

Recently I started reading more about NLP and following tutorials in Python in order to learn more about the subject. I'm trying to make my own classification algorithm (the text sends a positive/...
2
votes
1answer
27 views

Identifying documents similar to specific clusters

Through performing clustering on a set of 1,000,000 text documents, I have identified 100 clusters. I am particularly interested in, say, 10 of the clusters. Imagine, I now have an additional set of ...
2
votes
1answer
27 views

Classifying objects based of a varying number of the same type of feature vector for each object

For a congressional session, I have created a doc2vec model of speeches made. Using the vectors from this model, I have a dataset of each congressperson, their political affiliation, and a list of the ...
2
votes
1answer
43 views

How to compute unseen bi-grams in a corpus (for Good-Turing Smoothing)

Consider a (somewhat nonsensical) sentence - "I see saw a see saw" The observed bi-grams would be: "I see""see saw""saw a"and,"a see". My aim is to smoothen out the probability mass of the bi-gram ...