Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [computational-linguistics]

A branch of science that uses computers and mathematical methods to construct and investigate linguistic theory. Its technological and algorithmic implementation is called NLP.

1
vote
0answers
58 views

which formal languages rule does human language break?

This post is discussing human language and formal languages. According to the professor, human language is a kind of broken formal languages. So, which formal languages rule does human language ...
2
votes
2answers
208 views

What causes relative frequency of consonants?

So, can you point me to some research, what causes the relative frequency of consonants in various languages?The fact that vowels are more common than consonants is obviously caused by phonotactics, ...
-2
votes
1answer
110 views

what does broken formal languages mean?

I am learning Stanford CS224N: natural language processing with Deep Learning. Chris said "a little bit broken formal languages" in Lecture 1. what does that mean? can any one give a concrete ...
0
votes
0answers
21 views

what are the 2 similar notions exactly in cs224n Lecture 2 | Word Vector Representations: word2vec?

I cannot get what Chris is saying about distributional sth in Lecture 2 of cs224n. He is distinguishing 2 similar notions (distributional similarity and distributed representations) I know they very ...
4
votes
2answers
234 views

How to interpret this form of Heaps' Law?

Heaps' Law basically is an empirical function that says the number of distinct words you'll find in a document grows as a function to the length of the document. The equation given in the Wikipedia ...
1
vote
1answer
42 views

Relationship between two words part of the same sentence

I'm looking for some help on strategy to be used for finding out if word is spoken in relation to another word. For ex: The pool is dirty. Here dirty is spoken w.r.t pool However, The pool was great ...
0
votes
0answers
47 views

Dictionary pruning and real-word errors detecting

Dear colleagues, do you know something about experimentations similar to experiment from "An examination of undetected typing errors" by Fred J. Damerau and Eric Mays but for Russian or Ukrainian ? ...
3
votes
1answer
54 views

What are uses of Dependency Parsing in NLP / Computational Linguistics?

Dependency Parsing seems to be present in most of the NLP toolkits out there. What is not clear and what I have trouble finding in Google is what are actual practical, or even research, applications ...
3
votes
0answers
24 views

What is the term for a specific type of collocation analysis

I am trying to write a text processing script in R. I am interested in finding a word (from a list of words I have selected) only if it is in the same sentence as another word. Eventually I would ...
4
votes
0answers
41 views

PoS tagger - technical corpus

I try to find corpus with technical language to train my model, but I cannot find it. Do you know if there are any tagged PoS corpus in English related with technical language?
2
votes
1answer
69 views

Get Prolog (other functional programming language) rules/facts from LKB or similar system

My goal is to take simple sentence such as Grass is green and convert it to Prolog rule/fact. It does not have to be Prolog, but any other functional programming language with which I can perform ...
0
votes
0answers
40 views

Introductory texts in Computational Linguistics [duplicate]

I am looking for good introductory texts in Computational Linguistics involving NLP.
-1
votes
2answers
51 views

How to generate similar sentence by given sentence?

I'd like to generate a similar sentence by a given sentence. e.g. by given "Mike, this is an apple." can generate "Tom, this is a pear." Which software can I use for such generation? ...
2
votes
0answers
53 views

How relevant is WordNet nowadays?

How relevant is WordNet (both the original Princeton's and all other WordNets) as a tool for researchers now, decades later? Do researchers consider it valuable? And does the general research ...
0
votes
0answers
7 views

Using Penn Treebank to create tense and aspect tags

I am working on a project where I am trying to get verbs tagged from a block of text, showing the tense, aspect and mood. Do you know of anyone who has already used Penn's POS tags (or a similar tag ...
3
votes
2answers
77 views

Computational/Formal Approaches to Paragraph-Level Semantics

There are several frameworks that have been built by both linguists and computer scientists to deal with the problem of semantic representation of sentences, most notably Abstract Meaning ...
3
votes
2answers
97 views

Understanding Feature Grammar syntax

Background: I am a software dev who doesn't really know much about linguistics but I am trying to learn some of it for an application I'm making I am trying to understand Feature Grammar syntax, and ...
1
vote
1answer
54 views

What problems does co-articulation cause in speech recognition?

I know it becomes harder to find the start and end of phonemes due to co-articulation. I want to know about other problems that co-articulation causes in speech recognition.
4
votes
1answer
111 views

Rule-based or Statistics-based approach for generating plain language grammar rules from a text

Disclaimer: I am a software developer, not a computational linguist and I am not super familiar (though I am mildly familiar) with the field. Happy to learn and be corrected though! My use-case: I ...
2
votes
1answer
40 views

Is there an online Esperanto word stem “diagrammer?”

I'm wondering if there is a site or resource that will take an Esperanto word and diagram the different components. For example, given "malsanulejo," the "diagrammer" would return something like: mal-...
6
votes
1answer
78 views

How can I know if a log-likelihood score is high enough?

I am trying to understand if some terms can be considered as distinctly American or British. So for example I was studying the term "aubergine" and the normalized frequency in the American corpus is ...
1
vote
0answers
25 views

Maximally dissecting lexicon according to meaning (heuristically)

I'm trying to find a set of N English terms that maximally express the 'space of meaning' that all words are encapsulated within. I don't know the correct nomenclature to describe what I'm looking for ...
5
votes
1answer
64 views

Word length as a function of word frequency?

I was wondering if any studies have been done in corpus linguistics which look at word length (number of phonemes per word) as a function of the word's frequency of use? Thanks! EDIT: Never mind, ...
2
votes
0answers
15 views

How to convert CHAT to TextGrid in a batch?

Siarad corpus is a corpus of spoken Welsh (~40 hours, all transcribed, glossed and translated!). I want to analyze some conversations using Praat. Praat uses the TextGrid format, but the Siarad corpus ...
3
votes
2answers
66 views

Computational applications of construction grammars

Are there NLP applications (either natural language understanding or generation) which make use of the Construction Grammar framework? On a related note, does there exist a logically organized list ...
2
votes
0answers
51 views

Is “help” a causal verb?

As part of my research, I extract causal (cause-effect) relations from natural text. Sometimes, there are words in the text that signal a causal relation like "because" or "since." And, some other ...
0
votes
0answers
29 views

parsing British National Corpus into words

I need to calculate inverse document frequency from BNC. Does anybody has any code or know how to parse this dataset to extract texts? After extracting texts do I need to stem(get the base form of ...
-3
votes
1answer
37 views

For each word in a corpus, find how many senses it has according to WordNet [closed]

I've come across this exercise in my studies and I do not know how to challenge, I've tried to follow examples though I can never find anything online that truly is symmetrical to what I'm trying to ...
3
votes
1answer
49 views

Why not use a Lookup taggers?

I do understand that a lookup tagger is one of the simplest ones to implement as it is able to map each word a single POS. Why shouldn't we use it compared to bigram tagger?
0
votes
1answer
72 views

Jiang & Conrath when two words are the same

I would like to normalize the result of Jiang & Conrath similarity measure by dividing it by the maximum value(normally should be when both synsets are the same). I am using the implementation of ...
6
votes
1answer
116 views

Statistical Methods in Etymology

Etymologists tend to categorize the probability of theories under formulaic labels. These range from "uncertain" over "tentative" or "not convincing" to "established", "accepted" or "nonsense". P ...
3
votes
0answers
66 views

Are there any computational linguists who still use prolog?

My understanding is that in the 90's and early 2000's, expert systems and logical rules dominated the field of natural language processing/computational linguistics, but that for the last 10 years, ...
0
votes
1answer
42 views

The determiner “a” in lambda form

In the sentence: A man loves Mary The lambda notation of the determiner 'a' is: λY.λX.∃z.Y(z)∧X(z) What about the general determiner 'a'? Is the lambda notation the same? or it should be: λX.∃z....
1
vote
3answers
64 views

Looking for tool to split german text into sentences

I want to train a german embedding and need to split text into sentences. That is not easy since "z. B." and "Dr." are not endings of a sentence. Does anybody know a tool to do that for german texts? ...
0
votes
1answer
100 views

Syntax tree for this sentence [closed]

I am trying to find best way to get a syntax tree for this sentence: Planting seeds helps you grow your farm I thought of this: -------- S1 --------- | | --...
2
votes
2answers
123 views

Given both a word and the corresponding IPA, how to match/map the letters together?

Given both the word and the corresponding IPA equivalent, is there any stable algorithm for mapping the letter of each word to the IPA letter? For example, given close-quote and IPA kloʊzkwoʊt -- I'd ...
6
votes
2answers
107 views

Dataset/Database similar to WALS in Vowel/Phonology

I am wondering if there is any database similar to The World Atlas of Language Structures (WALS)(https://wals.info/). In the case that it is specifically more geared towards phonological aspects of ...
0
votes
1answer
60 views

How to find the 'average' of a word [closed]

I am trying to extract words that are similar between several documents. I would then like to extract the 'average' of the similar words Input Document 1 Document 2 ...
2
votes
0answers
39 views

Software for finding syllogisms in treebank data?

Is there treebank search software that can locate a syllogism, identifying its major and minor premises and terms? cf. Eyal Mozes, “A Deductive Database Based on Aristotelian Logic,” Journal of ...
0
votes
0answers
36 views

What do you call the process of resolving the subject of a conjunct?

I have the sentence We kick ass and take names. Running this sentence through Google's dependency parser gives: As you can see, "we" is tagged as the subject of "kick". However "we" is not tagged ...
3
votes
1answer
1k views

Are European Union parallel multilingual texts ideal for machine learning of machine translation?

Are European Union parallel multilingual texts - regulations, directives, especially the debates of European parliament - ideal for machine learning of machine translation, e.g. with neural networks? ...
0
votes
0answers
10 views

Lemmas that fit semantic restrictions of arguments in verbnet

VerbNet produces for each argument of a verb a label denoting semantic restrictions on that argument if such exist. These labels are not actual lemmas, but rather general qualities like "abstract", "...
5
votes
2answers
100 views

Can we simulate the pronunciation of sounds that we can't make?

There's certain non-filled places in the IPA chart because we physically can't pronounce them. For example, a velar trill or glottal trill. Using computers, is it possible that we could simulate how ...
1
vote
1answer
53 views

Dataset of subject-verb-object/adverb-verb/adjective-noun pairs

Does there exist a dataset which contains a list of subject-verb-object triplets or adverb-verb/adjective-noun pairs that occur within a certain (large) corpus? If not, what would be the most ...
1
vote
1answer
75 views

How can I identify Grammatical Categories in a sentence?

Please excuse the fact that I'm not an academically trained Linguist. I am working on a computer program with example sentences and their equivalents in different languages. The idea I am trying to ...
0
votes
0answers
26 views

What are the “expressive” parts of a language actually called?

Languages provide ways to express: Ordering Temporal (yesterday, today), Spatial (above, below, before, after, inside, outside, ...), Quantitative (larger, smaller,...) Relationships Spatial (...
2
votes
5answers
186 views

Algorithm for figuring out the pronunciation of a word

Wondering how we pronounce words. I feel like I learned this when I was a kid in school with all the language rules, but now I can't remember. I am trying to think about how we pronounce words. How ...
1
vote
0answers
16 views

Why does matching any root of a question to any root of potential answers gives better text understanding results?

I'm trying to find a way to prevent Intelligent Agents with Reading Comprehension and Question Answering abilities to answer question from documents from a given dataset. After dependency parsing we ...
3
votes
1answer
44 views

What is the definition of a causally coherent text?

I am trying to measure the causal coherence of text documents using NLP techniques to test a hypothesis (as far as I understand, there are different types of coherence in text but I am focusing on ...
2
votes
0answers
35 views

How to quantify and compare different ways of segmenting and transliterating (reading) a text in terms of uncertainty/leeway?

I. Let us say we have a syllabary of n symbols. II. Let us have three ways or methods of transliterating a text written using the symbols of the syllabary: The first method considers the syllabary ...