Questions tagged [natural-language-processing]

For questions related to natural language processing, which is 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.

119 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
1
vote
0answers
23 views

Conversational AI

I'm wondering if anyone knows about any projects that break down conversations for an AI. I'll explain what I mean - I've seen a lot of hardcoded responses, but nothing that allows an AI to break a ...
1
vote
0answers
31 views

Generate QA dataset from large text corpus

I have a corpus of a domain data in form of 10-15 books pdf and some articles and my end-goal is to make a question-answering system particular to that domain. For that, I would need a dataset on Q/A ...
1
vote
0answers
40 views

Does the human brain use beam search for text generation?

As far as I understand, beam search is the most widely used algorithm for text generation in NLP. So I was wondering: does the human brain also use beam search for text generation? If not, then what?
1
vote
1answer
18 views

Convolutional Sequence to Sequence Learning kernel parameters

I am reading the paper Convolutional Sequence to Sequence Learning by Facebook AI researchers and having trouble to understand how the dimensions of convolutional filters work here. Please take a look ...
1
vote
1answer
37 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 ...
1
vote
1answer
374 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
79 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

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 ...
1
vote
2answers
283 views

Is it a good idea to use BERT to answer a FAQ with semantic similarity?

I have been looking for BERT for many tasks. I would like to compare the performance to answer an FAQ, using BERT semantic similarity and BERT Q/A. However, I'm not sure it is a good idea to use ...
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
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 ...
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 ...
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 ...
1
vote
0answers
28 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
2answers
65 views

What is the difference between automatic transcription and automatic speech recognition?

What is the difference between automatic transcription and automatic speech recognition? Are they the same? Is my following interpretation correct? Automatic transcription: it converts the speech to ...
1
vote
0answers
18 views

How to train chat bot on infinite non-stationary data?

I have continual simulated data of million sentences of two simulated persons talking to each other in a room and I want to model one of the persons speech. Now, during this period things in the room ...
1
vote
0answers
15 views

How to annotate a teleoperated robot?

Most robotics challenges like Robocup soccer, micromouse and the Amazon picking challenge are oriented on fully autonomous systems. A motion controller gets started, the operator takes away his hands ...
1
vote
0answers
14 views

Intelligent Text Combination

Let's say we have 2 blocks of text, where there are some similarities as in 2 interpretations of the same story. Is there any solution that would recognize these consistencies and ultimately be able ...
1
vote
0answers
38 views

How could I learn tree paths given word embeddings?

I need to map from a vector space representation onto a tree structure. A possible solution: given a word vector as input, produce a path in the tree from the root down to the node that most closely ...
1
vote
0answers
72 views

Multi-channel CNNs and channels

In language models, CNNs can extract different n-gram features from the input. From my current understanding, these models are called "multi-channel CNNs". I'm referring to these materials: https://...
1
vote
0answers
40 views

How to understand marginal loglikelihood objective function as loss function (explanation of an article)?

I am reading article https://allenai.org/paper-appendix/emnlp2017-wt/ http://ai2-website.s3.amazonaws.com/publications/wikitables.pdf about training neural network and the loss function is mentioned ...
1
vote
0answers
34 views

Preset Intent list

I'm trying to build a chat analysis that could identify the intent of check price. Has any kind of preset intent list to train my chatbot already been done ? Data: A data set for "check price" ...
1
vote
0answers
29 views

Pre priming a network for white space

When a human looks at a page. He notices the sets of letters are grouped together separated by white space. If the white space was replaced by another character say z, it would be harder to ...
1
vote
0answers
96 views

Can semantic paraphrasing be used for a workflow management system?

The term paraphrasing is used for converting input text into output text with small modifications on the semantic level. Paraphrasing is used by managers to distribute work items to employees. It is a ...
1
vote
0answers
26 views

Sequence to sequence machine learning / NMT - converting numbers into words

I want to do some sequence to sequence modelling on source data that looks like this: /-0.013428/-0.124969/-0.13435/0.008087/-0.269241/-0.36849/ with target data ...
1
vote
0answers
77 views

How can I create a chatbot application where the user can create its own bot?

I am trying to create a chatbot application where the user can create its own bot, like Botengine. After going through google, I saw I need some NLP API to process the user's query. As per wit.ai ...
1
vote
0answers
63 views

Sentence classification and named identity detection with automatic retraining

I am learning AI and trying out my first real life AI application. What I am trying to do is taking as an input various sentences, and then classifying the sentences into one of X number of categories ...
1
vote
0answers
59 views

Would Capsule Neworks and Topic Modeling used together make sense?

This is actually something I have been researching a bit on my own. Most movie scripts can be structurally analysed by using writing theory such as Dramatica. Dramatica is based upon hierarchy of ...
1
vote
0answers
41 views

Number of utterances

Currently I am working with two large speech databases and I was asked to build one subset from each one in order to get two representative subsets with the same number of utterances. My question is: ...
1
vote
0answers
24 views

Commercial API Q: is there an api for converting vision tags into a caption?

There are many machine learning api for scanning images but they just return a bunch of tags. https://azure.microsoft.com/en-gb/services/cognitive-services/computer-vision/ ...
1
vote
0answers
254 views

Analogies and similarity

The more I think about machine learning the more I realize the importance of finding similarities by using analogies as a way of learning. If I want to categorize words into hierarchical tree this ...
1
vote
0answers
117 views

Natural language processing with a continuous dependent variable

I have a large number of observations. Each observation contains: dependent variable: a scores ranging from 0 - 100 independent variable: a large article I want to know which words or phrases ...
1
vote
0answers
35 views

Any software to guess idea flow (basic ideas/statements and their derivations) throughout text?

Is there any existing software which analyzes idea flow in the text (or between different texts, e.g scientific articles) and for example visualizes it with some graph?
1
vote
0answers
80 views

Problem with the PLN classifier

I'm developing a chatbot, and to get the answer I'm using the Naive Bayes classifier by sorting the questions and answers. For those who want to see the whole project code and more definitions follow ...
1
vote
1answer
119 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, ...
1
vote
1answer
36 views

Searching for dataset in specifix context for NLP, sentiment analysis

I would like to create an NPC engine for games which are in a fantasy context like Lord of the Rings, Warcraft, Skyrim, Dragon Age etc. This engine should be able to determine the polarity of the ...
1
vote
1answer
117 views

Question in NLP

I'm working on a project,whereby; one of the actors is "Teacher" and it's role will be, insert the course name, outcomes of skills, then insert the question, student degree and automatically will be ...
0
votes
1answer
19 views

Is the Mask Needed for Masked Self-Attention During Inference with GPT-2

My understanding is that masked self-attention is necessary during training of GPT-2, as otherwise it would be able to directly see the correct next output at each iteration. My question is whether ...
0
votes
0answers
31 views

How to create an automatic Aimbot coach?

In the gaming community an Aimbot is used to extend the human capabilities of playing a game. An average human user has only a limited capabilities of mastering a game. The amount of actions per ...
0
votes
0answers
10 views

How does transformer network learn to decide in a single step?

I read this In Google AI blog: link: https://ai.googleblog.com/2017/08/transformer-novel-neural-network.html S1 : " the Transformer can learn to immediately attend to the word “river” and make this ...
0
votes
0answers
19 views

Understanding how continuous bag of words method learns embedded representations

I'm reading notes on word vectors here. Specifically, I'm referring to section 4.2 on page 7. First, regarding points 1 to 6 - here's my understanding: If we have a vocabulary $V$, the naive way to ...
0
votes
1answer
37 views

Preparation of input data

Tell me why my val_acc is always the same and how to solve this problem? I saw several topics on the Internet specifically on this problem but they did not help me (for example, use SGD with different ...
0
votes
0answers
45 views

How do I do further (domain-specific) pre-training with Google BERT in preparation for subsequent fine-tuning?

How do I do further (domain-specific) pre-training with Google BERT in preparation for subsequent fine-tuning? Another way to say this is: can you create a checkpoint file created from the final ...
0
votes
0answers
20 views

How can I do entity recognition given the features?

I constructed the features from this tutorial: https://sklearn-crfsuite.readthedocs.io/en/latest/tutorial.html#features. But I did not understand the process of making the model. After doing the ...
0
votes
0answers
88 views

How Seq2Seq with Bidirectional RNN works?

First of all the scope of the question is as follows - we have Sequence2Sequence architecture with: Decoder: Bidirectional LSTM Encoder: regular (single directional) LSTM What I know: When you ...
0
votes
0answers
6 views

What services are available for interpreting batches of text in order to determine their topic and/or summary?

I'm aware of the services from Microsoft and AWS, that may be able to used for such an application. Please let me know how these fare, and if other similar services exist elsewhere: https://azure....
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 ...
0
votes
0answers
34 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.
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 ?