Questions tagged [natural-language-processing]

For questions related to natural language processing, which concerned with the interactions between computers and human (or natural) languages, in particular how to create programs that process and analyze large amounts of natural language data.

Filter by
Sorted by
Tagged with
0
votes
0answers
26 views

How do I create syntactically correct sentences given several words?

Is there an AI application that can produce syntactically (and semantically) correct sentences given a bag of words? For example, suppose I am given the words "cat", "fish", and "lake", then one ...
1
vote
1answer
35 views

Can AI help summarize article or abstract sentence keyword?

I'm wondering if AI now can help us abstract summary or general idea of long article, for example novel or historical stories, or abstract most important keyword from sentence; Would you please tell ...
2
votes
0answers
50 views

ChatBot applications [Academia]

I am in education and I'm wondering about the use of chatbot-like tools to facilitate automated discussions among students. The chatbot domain of knowledge would be purposely restricted to a specific ...
1
vote
0answers
70 views

How does bidirectional encoding allow the predicted word to indirectly “see itself”?

Before the release of BERT we used to say that it is not possible to train bidirectional models by simply conditioning each word on its previous and next words, since this would allow the word that’s ...
0
votes
0answers
33 views

Semantic search engine for a set of documents in python

I want to create a semantic search for a set documents with terms that could not appear on the set. Is there some code for that? I'm working on python.
1
vote
1answer
180 views

How to make meaningful sentences from a set of words?

I have set of topics generated using LDA and like {code, language, test , write, function}, {class, public, method, string, int} etc and I want to make meaningful sentence/sentences from these words ...
1
vote
2answers
75 views

Which algorithm should I use to map an input sentence to an output sentence?

I am new to NLP realm. If you have an input text "The price of orange has increased" and output text "Increase the production of orange". Can we make our RNN model to predict the output text? Or what ...
1
vote
0answers
28 views

Generate text from single word/topic using pre-trained language models such as GPT or BERT?

I have a dataset of 100000 documents each labelled with a topic to it. I want to create a model such that given a topic, the model can generate a document from it. I came across language models GPT, ...
4
votes
1answer
54 views

Cold start collaborative filtering with NLP

I’m looking to match two pieces of text - e.g. IMDb movie descriptions and each person’s description of the type of movies they like. I have an existing set of ~5000 matches between the two. I ...
2
votes
0answers
18 views

Multi-field text input for LSTM

I'm using LSTM to categorize medium-sized pieces of text. Each item to be categorized has several free-form text fields, in addition to several categorical fields. What is the best approach to using ...
0
votes
0answers
9 views

Why does fasttext have out-of-vocabulary and computational complexity problems while wordpiece does not?

For https://github.com/google-research/bert/issues/355 , why does fasttext have out-of-vocabulary and computational complexity problems while wordpiece does not ?
1
vote
0answers
24 views

Why do we need agents in Knowledge Query and Manipulation Language?

A multi-agent system is composed of multiple interacting intelligent agents on which KQML (Knowledge Query and Manipulation Language) is implemented. But I am confused on the nature of agents and why ...
3
votes
0answers
20 views

Why does all of NLP literature use noise contrastive estimation loss for negative sampling instead of sampled softmax loss?

A sampled softmax function is like a regular softmax but randomly selects a given number of 'negative' samples. This is difference than NCE Loss, which doesn't use a softmax at all, it uses a ...
0
votes
2answers
230 views

Use BERT to answer a FAQ with semantic similarity

I have been looking for BERT for many tasks and I would like to compare performance to answer a FAQ using BERT semantic similarity and BERT Q/A. However, I'm not sure it is a good idea to use ...
1
vote
2answers
121 views

How can I make meaningful English sentences from given set of words?

I have a set of topics and each topic consists of a set of words. I want to make meaningful English sentences from these words. Each topic consist of 5 to 10 words and these words are relevant to each ...
0
votes
1answer
27 views

Algorithms and strategies to help judges rule cases

I'm a Rails developer with a lot of web experience, but none (still) in AI. I'm working in a web text editor that judges use to writing their sentences. The goal is to start to use AI to help the ...
1
vote
1answer
47 views

Skip-Gram Model Training

Suppose we want to predict context words $w_{i-h}, \dots, w_{i+h}$ given a target word $w_i$ for a window size $h$ around the target word $w_i$. We can represent this as: $$p(w_{i-h}, \dots, w_{i+h}|...
0
votes
0answers
35 views

Facebook's Dr QA with multiple choice questions?

Is there such a thing as Facebook's Dr QA with multiple choice questions? Where the algorithm selects the most likely from 3 possible responses? The idea is to solve the following problem ...
0
votes
0answers
20 views

What are the reference papers of image captioning model 'all_img', 'att2in2', 'adaattmo' and 'topdown'?

I Want to cite the reference paper of The models appeared in this webpage: https://github.com/ruotianluo/ImageCaptioning.pytorch/blob/master/models/init.py But which papers do these four models '...
1
vote
0answers
14 views

any workaround to manipulate/transform recurrent CNN for sentence classification?

I learned how to build recurrent cnn model for text classification and sketched out my initial implementation. However, I am wondering how to transform recurrent <...
1
vote
1answer
109 views

Is Reinforcement Learning the future of Natural Language Processing?

I was reading about the grounding problem after seeing it mentioned in another answer today. The article states that, in order to avoid the "infinite regress" of defining all words with other words, ...
2
votes
1answer
82 views

How do I use neural networks to implement a chatbot?

I don't know anything about neural networks, but I got the information that making a chatbot with a neural network is very good. Is this really true? What do I need to know in order to build a chat ...
2
votes
1answer
58 views

Which matrix represents the similarity between words when using SVD?

Two words can be similar if they co-occur "a lot" together. They can also be similar if they have similar vectors. This similarity can be captured using cosine similarity. Let $A$ be a $n \times n$ ...
0
votes
0answers
22 views

Detecting an entity (location) in a text, using a corpus of smaller texts

I have a corpus of around 2000 texts, that are relatively short (+- 150 words). All of these texts are news articles about accidents that happened in the Netherlands. I'd like to extract the exact ...
0
votes
1answer
44 views

1D convolutions, word2vec, and $n$-grams

Suppose we are using word2vec and have embeddings of individual words $w_1, \dots, w_{10}$. Let's say we wanted to analyze $2$ grams or $3$ grams. Question 1 Why would adding all the possible $\...
1
vote
0answers
68 views

BERT intermediate layer utility

I'm looking for the BERT model you can find here. As I look to the attention mechanism, I don't understand why in the BERT encoder we have an intermediate layer between the attention and neural ...
2
votes
0answers
33 views

How to perform unsupervised anomaly detection from log file with mostly textual data?

I have a log file of the format, Index, Date, Timestamp, Module, App, Context, Session, Verbosity level, Description The log file can be considered as a master log, which consists of individual ...
0
votes
0answers
25 views

Word vector representation for feature extraction from log file

I am trying to generate a word vector representation of the textual descriptions of events from the log file in a distributed system. The logged events are time series data and correlated. During the ...
1
vote
1answer
28 views

Sentiment Analysis and Logistic Regression

Suppose we want to classify a review as good ($1$) or bad ($0$). We have a training data set of $10,000$ reviews. Also suppose we have a vocabulary of $100,000$ words $w_1, \dots, w_{100,000}$. So the ...
0
votes
0answers
13 views

Training Data of $n$-gram Language Models

Suppose $\textbf{w} = (w_1, \dots, w_k)$ is a sequence of words $w_1, \dots ,w_k$. Suppose we want to find $p(\textbf{w})$. In an $n$-gram language model, $$p(\textbf{w}) = \prod_{i=1}^{k+1} p(w_{i}|...
0
votes
1answer
46 views

What do the vectors of the center and outside word look like in word2vec?

In word2vec, the task is to learn to predict which words are most likely to be near each other in some long corpus of text. For each word $c$ in the corpus, the model outputs the probability ...
0
votes
0answers
18 views

Requirement Traceability

In my project I have around 10K requirements and 60K test cases. I would like to use some AI techniques to handle the requirement to Test case mapping. I don't know which AI methos or techniques I ...
0
votes
0answers
31 views

Extract personal information about a person from a list of documents and summarize it

I need to extract personal information about a person from a list of documents and summarize it to the user. If there are 2 people with the same name, the correct person should be identified. If the ...
3
votes
0answers
28 views

How would an AI visualize a story written in natural language?

Can AI transform natural language text describing real scenarios to visual images and videos ? How does as AI interprets say a Harry Potter story if it has to reproduce it in form of videos ? Would be ...
2
votes
1answer
29 views

How much the dialects recognition and speech recognition are relevant?

In this tutorial, they build a speech recognition model to classify a one-second audio clip as one of ten predefined words. Suppose that we modified this problem as the following: Given an Arabic ...
2
votes
0answers
26 views

Translate product names with AI

I frequently need to translate product names for hundreds of similar products -- and I have a list of past product names. Is it possible to train AI to review past translations and translate? It doesn'...
1
vote
0answers
68 views

Dialects classification using deep learning

Dialects differ a lot between cities in my country, Syria. People sometimes express themselves using different local phrases and idioms which refer to the same topic. So, I came up with the idea of ...
0
votes
0answers
25 views

Isolate the speech of two people in an audio record with two people only

I would like to find a way to isolate the speech of each of the people in an audio record so I can create a file of that form : ...
2
votes
0answers
75 views

How do the Sine and Cosine functions encode position in the “Attention is All You Need” paper?

After going through both the "Illustrated Transformer" and "Annotated Transformer" blog posts, I still don't understand how the sinusoidal encodings are representing the position of elements in the ...
1
vote
0answers
42 views

How can/should I use AI to populate a game (in the game theory sense) from text input

I'm wanting to conduct game theoretic analyses of ongoing conflict situations (e.g. the US/North Korea negotiations; Syrian conflict; etc) as reported in the news media. I believe that AI may help me ...
2
votes
3answers
301 views

A Sentence with Different Parse Tree Structures

I just read about Parse Tree for parsing a sentence as an Input for NLP Task. In my understanding, a valid Parse Tree of a sentence should have be validated by linguistic expert. So, I concluded, a ...
1
vote
0answers
27 views

Current status of semantics in natural language

It seems to me that current work in semantics of natural language processing is based on Tarski's book such as "Logic, Semantics, Metamathematics; Papers From 1923 To 1938", which is far from ...
1
vote
1answer
87 views

How to make chatbot using NLP like Dialogflow?

I want to apply the concept that exists in the Dialogflow API in my e-commerce website. I get some references in this regard : Tokenization Part Of Speech Named Entity Recognition Rule based I ...
0
votes
0answers
25 views

NLP Task Proposal: I spy with my little eye

I order to build better artifical agents (AA) we need the right tasks and data to train on. The task I have in mind is the well-know game "I spy with my little eye", where agent A has to guess the ...
6
votes
2answers
250 views

How do we know if GPT-2 is a better language model?

You may have heard of GPT2, a new language model. It has recently attracted attention from the general public as the foundation that published the paper, OpenAI, ironically refused to share the whole ...
2
votes
1answer
77 views

Anomaly Detection in distributed system using generated log file

I am developing an AI tool for anomaly detection in a distributed system.  The system supports an interface that combines several individual logs into a single log file generating approx. 7000 entries/...
4
votes
0answers
44 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 I am struggling to understand their definition of convolutional layer. First, let's ...
0
votes
1answer
35 views

Detect named entities inside words using spaCy

I am using rasa nlu for training an NLU system to detect intents and slots. Now, some languages have word endings with their nouns (like Finnish, e.g. "in Berlin" -> "Berliinissä"). I have tried to ...
0
votes
0answers
36 views

What is the right way to convolve over word embeddings?

I have two word embeddings $w_1$ and $w_2$ with dimension 100 as input to a convolutional neural network. It should learn the similarity between these two words. I am now concerned with the applied ...
0
votes
2answers
65 views

Do I need an encoder-decoder architecture to predict the next item of a sequence?

I am trying to understand how RNNs are used for sequence modelling. On a tutorial here, it mentions that if you want to translate say a sentence from English to French you can use an encoder-decoder ...