Questions tagged [natural-language-processing]

Natural language processing (NLP)

Filter by
Sorted by
Tagged with
0
votes
1answer
55 views

CYK result de-transformation

Suppose we have a rules derived from a treebank. And in order to get a syntax tree of a given sentence we use the cyk algorithm. In order to use the cyk we should convert the rules into chomsky normal ...
1
vote
0answers
30 views

How can Kneser-Ney Smoothing be integrated into a neural language model?

I found a paper titled Multimodal representation: Kneser-Ney Smoothing/Skip-Gram based neural language model. I am curious about how the Kneser-Ney Smoothing technique can be integrated into a feed-...
0
votes
0answers
110 views

More Information about these Question Answering Systems

My question is about the multi-hop question answering systems described in the page https://hotpotqa.github.io/ and reproduced in the following picture: I am interested in the models BFR-Graph, GSAN-...
1
vote
1answer
50 views

What kind of bigram probability smoothing is this?

I hope it isn't off topic but I need to understand this example. Given the corpus 12 1 13 12 15 234 2526 and smoothing factor of ...
0
votes
2answers
346 views

N-gram language model question

I have this question I found regarding n-gram modelling in the Speech and language processing text book: ...
0
votes
1answer
39 views

Which algorithm for predicting the next word(s) based on previous words, given a sentence?

I want to input some words, and out comes the next word(s). Neural nets are really hot at the moment, and I'm afraid of throwing a neural net at something, when one is not really needed. Or... maybe ...
0
votes
0answers
17 views

n-grams textbook question

I have this question I found regarding n-gram modeling in the Speech and Language Processing textbook by Daniel Jurafsky: Suppose we didn’t use the end-symbol ...
0
votes
0answers
9 views

Interpolation for maximum likelihood estimate of unigram and bigram

We are given the following corpus, modified from the one in the chapter: ...
0
votes
1answer
160 views

More Information about the Question Answering System called LUKE

LUKE is a new state-of-art in question answering system and after googled keywords LUKE Studio Ousia NAIST and RIKEN AIP (I suppose LUKE is a colaboration between several research centers) I couldn't ...
0
votes
0answers
22 views

Natural Languages

Can one imply that natural languages can be described by regular grammar? Is that what happens through NPL? Trying to understand the subject of how spoken language can be converted to data and how.
22
votes
1answer
888 views

Compression of domain names

I am curious as to how one might very compactly compress the domain of an arbitrary IDN hostname (as defined by RFC5890) and suspect this could become an interesting challenge. A Unicode host or ...
1
vote
1answer
78 views

Explain better this new inventory for Word Sense Disambiguation

My question is about CSI (Coarse Sense Inventory), described in the paper CSI A Coarse Sense Inventory for 85% Word Sense Disambiguation (C Lacerra, M Bevilacqua, T Pasini, R Navigli). Before the ...
0
votes
0answers
22 views

Optimal algorithm for making queries to a database

There is a database of, let's say, 500k English two-word combinations (e.g. "clover arc", "minister horse"). I can search for an arbitrary string and I will get a list of the alphabetically first 1000 ...
1
vote
1answer
96 views

Is there a meta text processing concept in CS?

I understand that text processing could be done in various ways on top of operating systems: Shell utilities for processing a file (and/or a file name): tr, ...
2
votes
1answer
135 views

Similar news detection

How do top news portals detect similar news? For example https://www.bbc.com/news/world-asia-china-51431087, if you go to this webpage, you can see the "More on this story" section at the bottom of ...
4
votes
0answers
33 views

How to identify measure words in Chinese text?

Measure words (aka classifiers) are used in Chinese to "measure" things, e.g. 三杯牛奶 Three glasses of milk 那个人 That person 一只乌鸦 One crow 一公斤豆腐 A kilo of tofu We don't have an equivalent in ...
3
votes
1answer
59 views

Phrase generation approaches

In generating reports, sometimes there is a need to produce quite involved phrases in one of natural languages given numerical or boolean parameters. To get a feel of it, it is enough to take a look ...
0
votes
0answers
18 views

What is the main concept of using lexical,linguistic, semantic or syntactic approach in NLP for cyberbullying

Am really in need of some explanation, am working on a nlp cyberbullying detection tool which i will deploy to the web using django framework, however, am stuck on some idea, can someone explain to me....
0
votes
0answers
8 views

Contingency Table Confusion NLP

Hello for the contingency table: [true positive, false negative, false positive, true negative]. I am having a hard time remembering the difference between these terms because all the terms are ...
3
votes
1answer
5k views

How to calculate an accurate estimated reading time of text?

I suppose the calculation should not be done by only two factors (average reading speed/words per minute, and word count). But at least by a third parameter, that in my opinion should measure the ...
2
votes
0answers
29 views

Question about word embeddings in a specific language model - GPT-2

How were the GPT-2 token embeddings constructed? The authors mention that they used Byte Pair Encoding to construct their vocabulary. But BPE is a compression algorithm that returns a list of ...
0
votes
0answers
18 views

What classifier can recognize differences in two text strings immediately?

I'm playing around with the TextBlob library for python. It has in it a NaiveBayesClassifier as well as a ...
0
votes
0answers
41 views

More information about the 10 types of information that can be useful for WSD (Word Sense Disambiguation)

Agirre and Martinez (Knowledge Sources for Word Sense Disambiguation) distinguish ten different types of information that can be useful for WSD (Word Sense Disambiguation): Part of speech (POS) ...
3
votes
0answers
46 views

Explain the process of formation of word senses in WordNet

Regarding the word sense disambiguation problem, read the following fact written on Knowledge-based Word Sense Disambiguation using Topic Models: Note that although WordNet is the most widely used ...
1
vote
0answers
42 views

What are open problems in computer science? [closed]

I should prepare some paper for a colloquium (kinda student-task) and it should cover the following points: (1) at least one notable discovery in theoretical informatics (or computer science) (2) at ...
1
vote
0answers
33 views

CYK algorithm - how to handle unknown terminals given in a sentence to parse?

There is a given treebank which we derive the Probabilistic context free grammar. I wonder how do one handles with a given sentence which includes terminals that don't exist in the derived rules? Is ...
1
vote
1answer
311 views

How does SpaCy make its dependency tree?

I discovered that SpaCy had the ability to make dependency trees. For instance given a question “To whom did the Virgin Mary allegedly appear in 1858 in Lourdes France?” We can create its dependency ...
1
vote
0answers
31 views

How can I find the perplexity of a text by the perplexity of its sentences?

For a bigram language model, I can calculate the perplexity of sentences of a test document. However, I'm not sure what would be the perplexity of the whole document. Should I get the average of the ...
3
votes
1answer
154 views

Bottom up chart parser adding active arc step

I am following Bottom up chart parsing algorithm from Natural Language Understanding book by James Allen. It is I couldn't understand the 3rd step. I thought that when active arc is added the dot ...
1
vote
0answers
38 views

Text Segmentation Problem give Word Frequencies in a Universe

Given a dictionary of words and their frequencies (how many times they appear in a universe and given a string(no spaces, punctuation, etc.). What is the best way to segment into individual words? I ...
2
votes
0answers
12 views

Are there any neural NLG systems which don't generate in left-to-right order?

For a while, all classification tasks in natural language processing were based on simple RNN's, which operate in a very word-by-word order. Adding gating mechanisms increased ability to "look back", ...
1
vote
0answers
31 views

Generalization of formal grammars - production rules with more general functions?

Usually formal grammars have production rules in the format N=tNt where simple concatenation function is used for the expansion of the nonterminal. https://www....
1
vote
1answer
88 views

Show that the Laplace smoothing for bigrams is a valid probability distribution

If we consider any smoothing technique like laplace or delta smoothing. Intuitively we can see that the we are stealing from sequences with non zero probablity and re distribute to sequences with zero ...
2
votes
1answer
114 views

How to represent symbolic knowledge using real numbers - theory about neural networks and natural/analog computing?

One can define the semantics of one definite word using the references to real world entities, relationships with the other words and other concepts and represent all this knowledge about this one ...
4
votes
2answers
119 views

Measuring the information of a document?

I'd like to measure how much information a document $D$ contains. Clearly, the New York Times published yesterday contains more information than my diary wrote on the same day. But, I do not know ...
4
votes
0answers
21 views

How to represent sentences with their dependency parses as input to an RNN?

I am working on a task embedding sentences into a lower-dimensional space according to style, both grammatical and lexical. As such, I want to have as input the linear ordering of tokens in each ...
3
votes
0answers
39 views

How to compute the loss and backprop of word2vec skip-gram using hierarchical softmax?

So we are calculating the loss $$J(\theta) = -\frac{1}{T}\sum_{t=1}^T\sum_{-m \leq j \leq m} \log P(w_{t+j}|w_t;\theta)$$ and to do this we need to calculate $$P(o|c) = \frac{\exp(u_o^Tv_c)}{\sum \...
1
vote
1answer
108 views

How to transform lambda function to multi-argument lambda function and how to rewrite or approximate terms?

I am trying to do the formal semantics (Montague grammar, abstract categorial grammar) of natural language and encode the sentence John is boss. The type system has ...
2
votes
1answer
24 views

Marginalise edge weights on graph

I have a directed acyclic graph with a score on each edge. The score of a path is defined to be the sum of the scores on the edges along this path. The probability of a path is the score of such a ...
5
votes
2answers
765 views

Estimate entropy, based upon observed frequency counts

Suppose I have $n$ independent observations $x_1,\dots,x_n$ from some unknown distribution over a known alphabet $\Sigma$, and I want to estimate the entropy of the distribution. I can count the ...
1
vote
0answers
311 views

How can node2vec help find similar “roles” within a graph (nodes whose connections have similar structure within the graph)?

I have a question on the node2vec algorithm described in this paper. Node2vec is a deep learning algorithm that word2vec to graphs to learn embeddings. The authors claim that it can help find nodes ...
2
votes
1answer
1k views

Subsampling of Frequent Words in Word2Vec

I am reading through the following paper: https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf Under section 2.3 on page 4 the authors ...
1
vote
1answer
98 views

Question on word probability for hierarchical softmax used in natural language processing

I am reading the following paper: https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf On page 4 of the paper they describe the ...
0
votes
1answer
48 views

Naive Bayes' Classification and Using the Entire Vocabulary in the Denominator

I am working through the NLP notes for Naive Bayes' classification here: https://web.stanford.edu/~jurafsky/slp3/6.pdf Below $c$ is the class of the observation and $w_i$ is the $i$th word of a text ...
2
votes
0answers
16 views

How does the Earley parser accept the input string as syntactically correct?

https://en.wikipedia.org/wiki/Earley_parser An input string of length $n$ is syntactically correct if at least one $(S \rightarrow X_1 ... X_m • 0)$ is in $E_n$. Why is this the case ? The part ...
2
votes
0answers
61 views

Proving the probability of zero occurrences in training using Good-Turing maximum likelihood estimate

Background Good-Turing (GT) smoothing is used in language models to estimate the counts of words in the test set that have not been seen in the training set. In GT smoothing, $N_c$ is the count of ...
1
vote
1answer
31 views

How to figure out whether two texts refer to the same object or event

Let's assume there is something happen in the world - Football world cup final. And team-1 beat team-2 with the score 3:2. So there is whole bunch of articles on every website about it, each contains ...
0
votes
0answers
32 views

Any references/current work on anomaly detection in conversations?

Suppose I have a lot of data on conversations between humans and chatbots (human text, chatbot text, times, media used for chat, etc), and I want to be able to detect anomalies in these conversations. ...
2
votes
1answer
1k views

Semantic natural language processing - from texts to logical expressions? Universal knowledge base?

My question is - is there a semantic natural language processing that tries to understand the meaning of the texts and that tries to derive the consequences of the understood meaning? Is there a ...
1
vote
0answers
41 views

In NLP, tokens not seen in training sample, but you know or don't know what they are

In NLP, do you distinguish tokens that you don't observe in a training sample and still expect that they may occur in a test sample, between those you know what they are, and those you don't know ...