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.

123 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
0
votes
1answer
42 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
83 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
130 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
30 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
35 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 ?
0
votes
0answers
37 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
23 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 '...
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
56 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 $\...
0
votes
0answers
31 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 ...
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
0answers
25 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
34 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 ...
0
votes
1answer
32 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 : ...
0
votes
0answers
27 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 ...
0
votes
0answers
42 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
0answers
13 views

Any research that proposes ways to improve a semantic network from phonetic sequences?

Inputs: Time series of spectra representing human speech Semantic network (as a directed graph) associations Outputs: Modified version of the semantic network input Edge types in the graph (...
0
votes
1answer
46 views

What AI designs are suited for producing title replacements?

Problem: "For a given news article, generate another title for the article if the article is to be published under a different Publication." Which algorithm will be well suited for this? Should I use ...
0
votes
2answers
107 views

Content analysis tools

We want to figure out the connection between people, based on their speech. Assume, that a conversation is a poetry with lines belongs to characters. There are a lot of poetries and the lines are ...
-2
votes
1answer
109 views

I need a word database… Any qualities I should look for?

I need a word database to train from. I found a word2vec JS word vector database, but I need a method to teach it which words go in which patterns. Please note that I am not asking to have you ...