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

Filter by
Sorted by
Tagged with
18
votes
2answers
3k views

What is the bleu score of professional human translators?

Machine translation models are usually evaluated using bleu score. I want to get some intuition for this score. What is the bleu score of professional human translator? I know it depends on the ...
12
votes
3answers
20k views

Natural Language to SQL query

I have been working on developing a system "Converting Natural Language to SQL Query". I have read the answers from the similar questions, but was not able to get the information that I was looking ...
9
votes
2answers
270 views

what machine/deep learning/ nlp techniques are used to classify a given words as name, mobile number, address, email, state, county, city etc

I am trying to generate an intelligent model which can scan a set of words or strings and classify them as names, mobile numbers, addresses, cities, states, countries and other entities using machine ...
8
votes
2answers
251 views

How prevalent is `C/C++` in machine learning development?

I am currently a data scientist mostly doing NLP, and I do most of my work inPython. Since I didn't get a CS degree in undergrad, I've been limited to very high ...
7
votes
1answer
1k views

Lemmatization Vs Stemming

I have been reading about both these techniques to find the root of the word, but how do we prefer one to the other? Is "Lemmatization" always better than "Stemming"?
7
votes
1answer
4k views

Why do we need to add START <s> + END </s> symbols when using Recurrent Neural Nets for Sequence-to-Sequence Models?

In the Sequence-to-Sequence models, we often see that the START (e.g. <s>) and END (e.g. </s>) symbols are added to ...
7
votes
1answer
212 views

Why is word prediction an obsession in Natural Language Processing?

I have heard how great BERT is at masked word prediction, i.e. predicting a missing word from a sentence. In a Medium post about BERT, it says: The basic task of a language model is to predict ...
7
votes
1answer
205 views

Understanding of naive bayes: computing the conditional probabilities

For a task on sentiment analysis, suppose we have some classes represented by $c$ and features $i$. We can represent the conditional probability of each class as: $$P(c | w_i) = \frac{P(w_i|c) \cdot ...
5
votes
1answer
623 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, ...
4
votes
3answers
745 views

What is the best question generation state of art with nlp?

I was trying out various projects available for question generation on GitHub namely NQG,question-generation and a lot of others but I don't see good results form them either they have very bad ...
4
votes
1answer
57 views

How should I treat these non-English documents in the NLP task?

So I have a small corpus of about 30k documents and about 50 documents in this corpus are in other languages (Persian, Chinese, Arabic, German, Spanish etc). I will be using this corpus for training a ...
4
votes
4answers
502 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, "...
4
votes
1answer
111 views

Can CBOW model only accept fixed number of words?

I have a question about CBOW prediction. Suppose my job is to use 3 surrounding words w(t-3), w(t-2), w(t-1)as input to predict one target word w(t). Once the model is trained and I want to predict a ...
3
votes
2answers
60 views

What are the elements in a BERT word embedding?

As far as I understand, BERT is a word embedding that can be fine-tuned or used directly. With older word embeddings (word2vec, Glove), each word was only represented once in the embedding (one ...
3
votes
2answers
386 views

Trying to implement a “smart compose” feature

I found this post on Gmail's smart compose feature, and it got me thinking about trying to implement it myself. https://ai.googleblog.com/2018/05/smart-compose-using-neural-networks-to.html The text ...
3
votes
1answer
74 views

How to cluster n-grams?

I just wanted to know how to cluster n-grams based on their semantics. Like clustering together n-grams that are semantically similar by leveraging the distributional hypothesis suggesting that ...
3
votes
2answers
28 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
1answer
52 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
0answers
91 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
141 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 ...
2
votes
3answers
75 views

NLP and one-class classifier building

I have a big dataset containing almost 0.5 billions of tweets. I'm doing some research about how firms are engaged in activism and so far, I have labelled tweets which can be clustered in an activism ...
2
votes
2answers
166 views

What are tokens and tokenizations?

I'm a high school senior who is new to data science, and would like to get into natural language processing. I currently know nothing about NLP, and the information online can be overwhelming. What ...
2
votes
2answers
65 views

Need help with entity tagging

I need to design a system which can identify movie and production company names in a sentence. The approach that comes to my ...
2
votes
2answers
2k 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
2answers
21 views

Creating pronunciation dictionary for ASR

I am working on ASR(automatic speech recoginition) on Somali data as master thesis and now I am stuck with how to create a phonetics or pronunciation dictionary for it. I searched over net and could ...
2
votes
2answers
39 views

What is the easiest way to identify a gender for a noun (in french)?

I am working on an app where in order to process some data, I need to be able to identify the gender for some selected words. My data is in French. The feature I am looking for should be able to tell ...
2
votes
3answers
130 views

Which neural network to choose for classification from text/speech?

I am considering two tasks: Dialog Act Classification from Text (e.g. classify to: question; opinion; ...) Emotion Recognition from Speech (e.g. happy; calm; sad; ...) Which DL model should perform ...
2
votes
1answer
365 views

Fine-tuning NLP models

In computer vision, if we don't have a large training set, a common method is to start with a pre-trained model for some related task (e.g., ImageNet) and fine-tune that model to solve our problem. ...
2
votes
1answer
75 views

Machine Learning and Natural Language Processing : Project Initiation

I am in the research phase of a long project and am willing to get some useful feedback from your side about the most appropriate project path to take. Current situation: A large team of so called ...
2
votes
1answer
1k views

Why are Chunking and IOB tags necessary?

I've just come across chunking and I can't get my head around why is it necessary? I know that it is used for 'named entity recognition'. I have few questions: Why and how is Chunking helpful? Plus ...
2
votes
1answer
23 views

Extracting name, date and total from a set of heterogeneous receipts

So, this is how the problem goes: I am trying to extract information from scanned receipts like this, What I have been told is that I would get the textual data from a OCR software, so in short I ...
2
votes
1answer
25 views

How to group chat messages by topic?

I am a newbie in this field. Developer since 20 years and more but never done anything (except tutorials) with ML, DL, and NLP. Though I've already read a bunch of articles and tutorials about this ...
2
votes
1answer
23 views

Is there a way to cluster words based on how similarly they sound?

I have a list of words for a fictional world I've made (don't judge lol). My ultimate goal is to generate more words that sound like them through a markov generator, but for now, I'm trying to build ...
2
votes
1answer
520 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 ...
2
votes
3answers
171 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/...
2
votes
1answer
187 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: ...
2
votes
2answers
307 views

Training an AI to play Starcraft 2 with superhuman level of performance?

I'm interested in working on challenging AI problems, and after reading this article (https://deepmind.com/blog/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment/) by DeepMind and ...
2
votes
0answers
22 views

What could be proper terms for a research direction in natural language processing to measure meaningfulness?

For some time, I did assessments to design metrics on how to recognize well-written and meaningful software requirements. Then I decided to work with Stack Overflow question posts because they are a ...
2
votes
0answers
9 views

Generate Intro-Text for Newsletter

I am trying to implement the following idea. For a daily newsletter I would like to generate an engaging and funny intro text, such as: Good morning. Sorry if there are beer stains and buffalo ...
2
votes
1answer
106 views

Document embedding vs locality sensitive hashing for document clustering

I would like to compare two methods: locality sensitivity hashing and document embedding to get the similarity between two documents. Both of those methods encode information of a document in a ...
2
votes
0answers
18 views

Step extraction from a paragraph

Came across an interesting problem: Given a paragraph describing how to do a process, need to break it down to various steps. Basically, need to determine for each sentence in the paragraph, if this ...
2
votes
0answers
32 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
35 views

Assigning tags to posts using predefined set of tags

I want to tag the text of a post with a predefined set of tags. A post could have multiple tags such as health, addiction, etc. I want to recommend up to $5$ tags. Total of $60$ tags is present. ...
2
votes
0answers
24 views

Natural language Generator using Data from table

I am working on some natural language generator part. eg.1 Input to it will be Col1 Col2 Col3 A B 13 X Y 14 Output should be two sentence, one ...
2
votes
1answer
229 views

How does BERT deal with catastrophic forgetting?

In the ULMFit paper authors propose a strategy of gradual unfreezing in order to deal with catastrophic forgetting. That is, when the model starts be fine-tuned according to a downstream task, there ...
2
votes
0answers
32 views

How to prepare the data for text generation task

First, I'm not sure whether the model contains the encoder during training. EOS means end-of-sentence. Encoder and decoder are part of transformer network. If without-encoder, training time: ...
2
votes
1answer
28 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 ...
2
votes
0answers
25 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 ...
2
votes
0answers
107 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 ...
1
vote
1answer
70 views

What is a 'hidden state' in BERT output?

I'm trying to understand the workings and output of BERT, and I'm wondering how/why each layer of BERT has a 'hidden state'. I understand what RNN's have a 'hidden state' that gets passed to each ...