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
37 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
66 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 ...
2
votes
2answers
112 views

Is there a way to understand the type of a sentence?

I am a beginner, just started studying around NLP, specifically various language models. So far, my understanding is that - the goal is to understand/produce natural language. So far the methods I ...
1
vote
2answers
62 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 ...
0
votes
0answers
12 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 (...
1
vote
1answer
555 views

BERT - What are the segment and position embeddings used in here?

They only reference in the paper that the position embeddings are learned, which is different from what was done in ELMo. ELMo paper - https://arxiv.org/pdf/1802.05365.pdf BERT paper - https://arxiv....
0
votes
1answer
89 views

What's the commercial usage of “image captioning”?

If "image captioning" is utilized to make a commercial product, what application fields will need this technique? And what is the level of required performance for this technique to be usable?
1
vote
0answers
37 views

Smielapp design feasible now?

Consider a SmielApp1, pronounced smile-app. It's a proposed app for Android, iOS, LINUX, and other phone, tablet, laptop, and desktop environments.2 The system requirements are a microphone, a speaker,...
3
votes
1answer
19 views

Natural language recommendation system: to pre-classify inputs or not?

Does it help to "pre-classify" natural language inputs using labeled input fields? E.g., "Who," "What," "Where," "When," "Why," "How," and "How much?" Or is a single, monolithic, free-form, long-text ...
4
votes
4answers
146 views

Asking about the combination of NLP and ML

I am new to this community, I just have a question : is doing a M.S. in the combination of Natural Language Processing and Machine Learning worth it? What are the opportunities that can be opened by ...
3
votes
2answers
371 views

How to recognise metaphors in NLP?

Is there software available which can extract metaphors from texts? eg: His words cut deeper than a knife. Or a simpler form like : eg: Life is a journey that must be travelled no matter how bad ...
-1
votes
1answer
64 views

How do I create chatbots without machine learning?

I am looking for an non-ML method for two chat bots to communicate to each other about a specific topic. I am looking for an "explainable AI" method, as opposed to a "black-box" one (like a neural ...
3
votes
2answers
159 views

Handling emotion in informal text (Hi vs HIIIIII!!!!)?

This is a question related to Neural network to detect "spam"?. I'm wondering how it would be possible to handle the emotion conveyed in text. In informal writing, especially among a ...
0
votes
1answer
120 views

LSTM language model not working

I am trying to use a Keras LSTM neural network for character level language modelling. As the input, I give it the last 50 characters and it has to output the next one. It has 3 layers of 400 neurons ...
0
votes
1answer
41 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
0answers
12 views

Is Fuzzy control equal to grounded motion primitives?

In the literature, many papers are written about Fuzzy control systems. Usually they are based on diagrams which shows the relationship between input signal and control signal. The interesting aspect ...
1
vote
2answers
30 views

Is there bidirection sequence-to-sequence neural machine translation?

I have heard about bidirectional RNN LSTM units (endcoders-decoders), but my question is - is there bidirectional neural machine translation, that uses A->B weights for the translation in the opposite ...
0
votes
1answer
35 views

Grouping products and naming groups

I'm working on a home tool that will help create a shopping list from a list of recipes chosen for a coming week. This boils down to: Extracting ingredients and their quantities from recipes. ...
2
votes
2answers
90 views

In speech recognition, what kind of signal is used?

Speech is a major primary mechanism of communication between humans. With respect to artificial intelligence, which signal is used to identify the sequence of words in speech?
4
votes
4answers
472 views

Can Machine Learning be applied to decipher the script of lost ancient languages?

Can Machine Learning be applied to decipher the script of lost ancient languages? (Languages that many years ago were being used, but currently are not used in the human societies and have been ...
1
vote
1answer
18 views

How can I evaluate the performance of a system that generates text?

I am preparing to perform research comparing the performance of two different systems that probabilistically generate the next word of an input sentence. For example, given the word 'the', a system ...
0
votes
0answers
10 views

Which Domain specific language are available for Mocap?

Motion capture (Mocap) is about recording human motions in 3d space. In most cases, a marker based tracking is used, but some newer development goes into markerless capture. The result of the mocap ...
0
votes
2answers
96 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 ...
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 ...
3
votes
1answer
60 views

Does an advanced Dialogue state tracking eliminate the need of intent classifier and slot filling models in dialogue systems/ chatbots?

I am learning to create a dialogue system. The various parts of such a system are Intent classifier, slot filling, Dialogue state tracking (DST), dialogue policy optimization and NLG. While reading ...
3
votes
1answer
81 views

Neural network architecture for comparison

When someone wants to compare 2 inputs, the most widespread idea is to use a Siamese architecture. Siamese architecture is a very high level idea, and can be customized based on the problem we are ...
8
votes
3answers
6k views

Can BERT be used for sentence generating tasks?

I am a new learner in NLP. I am interested in the sentence generating task. As far as I am concerned, one state-of-the-art method is the CharRNN, which uses RNN to generate a sequence of words. ...
0
votes
0answers
27 views

Task and motion planning with domain specific languages

In a paper published 6 years ago a novel domain specific language (DSL) for character animation was presented. High-level action commands are described in the XML format for authoring a virtual human. ...
3
votes
1answer
110 views

How to model a plumber dispatcher with Artificial Intelligence?

The domain of emergency call for clogged pipelines has to do with taking a call and managing the reaction of plumber departments. It is mostly a group oriented communication situation between the ...
2
votes
2answers
61 views

How to know which kind of adverb in NLP Parts of Speech (POS) tagging?

There are 4 kinds of adverbs : Adverbs of Manner. For example, slowly, quietly Adverbs of Place. For example, there, far Adverbs of Frequency. For example, everyday, often Adverbs of Time. For ...
1
vote
2answers
38 views

Possible to translate generic English-language document into higher-order logic?

(Un-original) idea: Wouldn't it be cool if we could fact-check using an algorithm that could understand a whole bunch of documents (e.g. scientific papers) as higher-order logic? Question: What ...
0
votes
0answers
47 views

Datastructure for grounded grammar induction

Grammatical induction is the art of learning a grammar from training data. We have a domain-specific-language for example a Python dialect and should create for that dialect a grammar which is able to ...
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
69 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
1answer
35 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 ...
3
votes
1answer
87 views

Which model should I use to determine the similarity between predefined sentences and new sentences?

The Levenshtein algorithm and some ratio and proportion may handle this use case. Based on the pre-defined sequence of statements, such as "I have a dog", "I own a car" and many more, I must ...
0
votes
0answers
40 views

Usefulness of Data augmentation for non-overfitting network [NLP]

(Maybe related : Usefulness of Dropout for non-overfitting network) My neural network does not overfit. Using Data augmentation in a non-overfitting network can increase its accuracy ? Note : I'm ...
1
vote
0answers
39 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 ...
2
votes
1answer
85 views

How to find the category of a technical text on a surface-semantic-level

There are some predefined categories( Overview, Data Architecture,Technical Details, Applications etc). The requirement is to classify the input text of paragraphs into their resp. category. I cant ...
1
vote
1answer
116 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 ...
1
vote
0answers
33 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
27 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
1answer
54 views

Looking for NLP technique and drawing a blank

Within a piece of text, I'm trying to detect who did what to whom. For instance, in the following sentences: CV hit IV. CV was hit by IV. I'd like to know who hit whom. I can't remember what ...
1
vote
1answer
67 views

Calculation of GPU memory consumption on softmax layer doesn't match with the empirical result

I'm training a language model with 5000 vocabularies using a single M60 GPU (w/ actually usable memory about 7.5G). The number ...
1
vote
1answer
259 views

How to make a chatbot with NLP and Neural

I would like to have a chat to talk on a personal plan enough to pass the Turing test. I got to study some natural language processing (NLP) but some that usually hide a lot of mechanical, so I think ...
2
votes
1answer
88 views

How to build a commercial image captioning system?

Image Captioning is a hot research topic in the AI community. There are considerable image captioning models for research usage such as NIC, Neural Talk 2 etc. But can these research models be used ...
3
votes
1answer
317 views

How to parse conjunctions in Natural Language Processing in Python

Is there an accepted way in NLP to parse conjunctions (and/or) in a sentence? By following the example below; how would I parse, ...
2
votes
2answers
111 views

How does the 'Lorum ispum' generator work?

In the domain of natural language processing, a textgenerator is able to produce pseudo random output. The most famous one is SCIgen which was used to generate fake-science papers. The inner working ...