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.

646 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
7
votes
2answers
176 views

How to implement hierarchical labeling classification?

I am currently working on the 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 ...
5
votes
2answers
58 views

N-grams for RNNs

Given a word $w_{n}$ a statistical model such a Markov chain using n-grams predicts the subsequent word $w_{n+1}$. The prediction is by no means random. How is this translated into a neural model? I ...
5
votes
1answer
50 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!
5
votes
0answers
9k 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-...
5
votes
2answers
308 views

Changing 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 ...
4
votes
0answers
210 views

How to use multiple text features for NLP classifier?

I am trying to build text classifier, Usually, we have one text column and ground truth. But I am working on a problem where dataset contains many text features. I am exploring different ways how to ...
4
votes
1answer
287 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 Subject-Verb-Object (SVO) triples if you want a triple like (word, word, word). Can you give the sentence as ...
4
votes
1answer
163 views

How do we pass data to a RNN?

Let's say we have A1, A2, ... , Am different articles in the corpus and each of them has W1, W2, ....., Ww words. We are training a language model on them. Do we: Scheme 1 Take the first batch of ...
4
votes
1answer
45 views

averaging multiple scores on small chunks of data or raw score on single collated data

I am using IBM Watson tool to determine tones (https://tone-analyzer-demo.mybluemix.net/) and personality scores (https://personality-insights-livedemo.mybluemix.net/) on different files containing ...
3
votes
3answers
177 views

Dot product for similarity in word to vector computation in NLP

In NLP while computing word to vector we try to maximize log(P(o|c)). Where P(o|c) is probability that o is outside word, given that c is center word. Uo is word vector for outside word Vc is word ...
3
votes
1answer
34 views

Detecting grammatical errors with BERT

We fine-tuned BERT (bert-base-uncased) model with CoLA dataset for sentence classification task. The dataset is a mix of ...
3
votes
1answer
68 views

Word2Vec: Why do some dimensions of an embedding have an interpretation, and why does addition/subtraction of embedding vectors work?

I'm reading about Word2Vec from this source: http://jalammar.github.io/illustrated-word2vec/. Below is the heatmap of the embeddings for various words. In the source, it's claimed that we can get an ...
3
votes
1answer
113 views

In smoothing of n-gram model in NLP, why don't we consider start and end of sentence tokens?

When learning Add-1 smoothing, I found that somehow we're adding 1 to each word in our vocabulary but not considering start-of-sentence and end-of-sentence as two words in the vocabulary. Let me throw ...
3
votes
0answers
407 views

How to choose threshold for gensim Phrases when generating bigrams?

I'm generating bigrams with from gensim.models.phrases, which I'll use downstream with TF-IDF and/or gensim.LDA ...
3
votes
1answer
77 views

Sentiment analysis of tweets (Train model on a labelled dataset and use on some other unlabelled data)

I have a huge amount of tweets on a particular topic say 'ABC' and the data is not labelled. I want to perform multi-class sentiment analysis of these tweets. I tried many unsupervised clustering ...
3
votes
0answers
29 views

Dataset availability for automatic text summarization

I'm working on an automatic text summarization NLP problem and looking for a dataset with USA legal case reports similar to the Australian legal case reports dataset in UCI repository. Can you please ...
3
votes
0answers
40 views

Change the way spacy works - Custom properties for training and prediction

Spacy detects the entities using its predefined algorithm. It parses tokens in text considering position of tokens with respect to tokens surrounding it. It also takes into consideration the POS ...
3
votes
1answer
131 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 ...
3
votes
4answers
52 views

Pre-trained models

I am starting off with machine learning so could someone tell if there is some site where one can find the current best performing trained models for any specific problem like sentiment analysis or ...
3
votes
0answers
25 views

Back-Translation model for German and English

Do you know of any pre-trained models for back translation between German and English? I am aware that there are ways to include a monolingual corpus into the training of a machine translation model (...
3
votes
1answer
71 views

How do I visualize data for a natural language processing project?

I am using a question-and-answer dataset. My neural network takes a question and an article content, and outputs where an answer starts (as an integer). To visualize my data, how should I process it ...
3
votes
1answer
244 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 ...
3
votes
1answer
370 views

How to find possible subjects for given verb in everyday object domain

I am asking for tools (possibly in NLTK) or papers that talk about the following: e.g. Input: Vase(Subject1) put(verb) Ans I am looking for: flower, water Is there a tool that can output subjects (...
3
votes
1answer
106 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 ...
3
votes
1answer
309 views

How to train millions of doc2vec embeddings using GPU?

I am trying to train a doc2vec based on user browsing history (urls tagged to user_id). I use chainer deep learning framework. There are more than 20 millions (user_id and urls) of embeddings to ...
3
votes
1answer
132 views

Why does joint embedding of word and images work?

I often see some papers where the authors do point-wise multiplication of word and image embedding (e.g the image below). Why does this implementation works? I do not understand.
3
votes
0answers
105 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
0answers
60 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
0answers
177 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
0answers
346 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
451 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 ...
3
votes
0answers
294 views

How does the supposed “Unified Architecture for NLP” from Collobert and Weston 2008 really works?

In this paper (here) they suppose a "unified architecture for NLP" with deep neural networks with multitask learning My problem is to understand the layered architecture in figure 1, see ...
3
votes
2answers
103 views

Is NLP suitable for my legal contract parsing problem?

My company has a product that involves the extraction of a variety of fields from legal contract PDFs. The current approach is very time consuming and messy, and I am exploring if NLP is a suitable ...
2
votes
0answers
23 views

Medical NER for French language

I'm currently exploring the options to extract medical NER specifically for French language. I tried SpaCy's general French NER but it wasn't helpful to the cause (...
2
votes
0answers
42 views

Is it acceptable to append information to word embeddings?

Let's say I have my 300 dimensional word embedding trained with Word2Vec and it contains 10,000 word vectors. I have additional data on the 10,000 words in the form of a vector (10,000x1), containing ...
2
votes
1answer
50 views

Cosine Similarity but with weighting for vector indexes

I am very new to NLP and although this seems like a basic question I don't know how to search for an answer online. This is my problem: I have extracted and ranked keywords from 2 text sources: A ...
2
votes
0answers
142 views

improve NER model accuracy with spaCy dependency tree

I have search at lot, was not able to find a solution for my problem... I am training a NER model, that should detect two types of words: Instructions and Conditions. This is not the standard use-case ...
2
votes
0answers
25 views

What is the structure and dimension of input passed to neural network when training CBOW and SKIP GRAM word embedding

I am confused about input passed to neural network in natural language processing (NLP) when training CBOW word embedding from scratch. I read the paper and have ...
2
votes
1answer
59 views

Difference between text-based image retrieval and natural language object retrieval

I'm working on creating a model that locates the object in the scene (2D image or 3D scene) using a natural language query. I came across this paper on natural language object retrieval which mentions ...
2
votes
0answers
69 views

Loss first decreases and then increases

I am using pre-trained xlnet-base-cased model and training it further on real vs fake news detection dataset. I noticed a trend in accuracy for first epoch. ...
2
votes
1answer
55 views

word2vec: usefulness of context vectors in classification

I've been working on a NN-based classification system that accepts document vectors as input. I can't really talk about what I'm specifically training the neural net on, so i'm hoping for a more ...
2
votes
2answers
36 views

Resources for text classification algorithms

I'm mining raw Facebook comments (irrelevant) and i am looking for an algorithm that can classify their context as negative/positive/neutral. So you can think of the output in the form of two columns. ...
2
votes
1answer
114 views

KeyError: Selecting text from a dataframe based on values of another dataframe

I have the following two dataframes badges and comments. I have created a list of 'gold users' from ...
2
votes
2answers
308 views

Automatic topic labelling for topic modelling

I am just curious to know if there is a way to automatically get the lables for the topics in Topic modelling. It would be really helpful if there's any python implementation of it.
2
votes
0answers
168 views

Explain FastText model using SHAP values

I have trained fastText model and some fully connected network build on its embeddings. I figured out how to use Lime on it: complete example can be found in Natural Language Processing Is Fun Part 3: ...
2
votes
1answer
222 views

Clustering mixed data types - numeric, categorical, arrays, and text

I have a dataset with 4 types of data columns: ...
2
votes
1answer
139 views

FastText Model Explained

I was reading the FastText paper and I have a few questions about the model used for classification. Since I am not from NLP background, some I am unfamiliar with the jargon. In the figure, what ...
2
votes
1answer
30 views

Q&A answer comparison multiple sentences using

I have been working on a Q&A app that has a template of questions and answers. The hope is to take answer text from the user, and compare it to the correct answer. I’d like to weight it on the ...
2
votes
1answer
57 views

Weighting of words in lexicon based sentiment analysis

I have a a question regarding my current project, i am trying to do a lexicon based sentiment analysis on my data, where i calculate the sentiment score as following: $$ Score = \frac{\sum_{i}{word_i}...
2
votes
1answer
48 views

NER and context mapping

I want to extract various amounts and tenure of contracts from different contract documents that we have. For example : Mr xyz, this contact is valid for 3 Months and has to be executed within 1 ...

1
2 3 4 5
13