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.

160 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
7
votes
0answers
168 views

Combinatory Categorial Grammar (комбинаторная категориальная грамматика) developments and lexicon for Russian language?

I am trying to apply Cornell Semantic Parsing framwork https://github.com/cornell-lic/spf (implementation of Combinatory Categorial Grammars CCG) to Russian language. This framework takes natural ...
7
votes
1answer
383 views

Representing knowledge extracted from output of dependency parsing

I am working on a problem to represent knowledge extracted from a paragraph and rank it to produce abstractive summaries. I have implemented dependency parsing using Stanford NLP, which gives dot ...
6
votes
0answers
284 views

Formal Language theory (context free grammars, pushdown automata)

Does anyone know any good introductions to Formal Language theory and Formal Grammar, that covers the mathematical basis of Syntax and things like context free grammars and pushdown automata? In ...
5
votes
0answers
56 views

Which method measures the degree of disagreement in online comments?

I am researching Fake News as a topic at my university. Right now, I am searching for some literature in which a method for measuring the degree of disagreement in an online comment setting (Facebook, ...
5
votes
0answers
53 views

Combinatory Categorial Grammar for inflected languages?

Can combinatory categorial grammars be used for inflected languages like Slavic and Baltic languages? I am aware only of this thesis https://pwmarcz.pl/pm-thesis-final.pdf As far as I have ...
5
votes
0answers
149 views

Genitive forms (German)

Do you know any rule how I can decide (formally), wheter a German sentence contains a Genitivus subjectivus or a Genitivus objectivus? Example: "der Besuch des Botschafters". Here, the ambassador ...
5
votes
0answers
316 views

OCR program for IPA?

Is there a program that can convert a scan/image of IPA into any digital encoding? UTF-8 Unicode preferred, and low-cost preferred (open source would be especially nice).
4
votes
1answer
182 views

How to extract grammar rules from a language (grammar induction?) using a neural network like a LSTM

I have a simple artificial language. It has about 200 words and it has a grammar. I am trying to figure out how to learn that grammar, which I think is called grammar induction, then print those rules....
4
votes
0answers
54 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?
4
votes
0answers
87 views

Using (e.g.) Stanford NLP for retrieving specific “indirect” objects

I am a computer scientist using Stanford NLP for extracting a Semantic Graph from plain text. Through this tool I am already getting the universal dependencies but now I want to get all the possible ...
4
votes
0answers
238 views

The expressive power of languages : Information content in a sentence : How do we measure it

What is your name Isme shoma chi e Two sentences - same content. My question is about the way to measure information content in a language. How do we do this? Because quite evidently count of the ...
4
votes
0answers
103 views

What is the difference between AUG and CCG?

What is the difference between Applicative Universal Grammar and Combinatory Categorial Grammar? They both use type inference rules to define their grammars. Is it simply that CCG uses combinatory ...
4
votes
0answers
356 views

How to decrease CRF++ feature function set?

I have a problem with the CRF++ Package. CRF++ cannot handle large training parts-of-speech corpora (large tagset and large number of words). In fact, the number of feature functions automatically ...
3
votes
0answers
31 views

Computer analysis of ESL learners' mistakes

This is a very broad question; I'm trying to get a sense of the current state of this subfield of NLP and what relevant resources may already exist, so even tangential answers will be welcome. To what ...
3
votes
0answers
46 views

How to incorporate sentence end marker in POS tagging with viterbi algorithm?

I am self-reading the NLP book by Dan Jurafsky. In the book, the following equation is given for incorporating the sentence end marker in the Viterbi algorithm for POS tagging. I am confused why the ...
3
votes
0answers
88 views

How can I calculate the morphological similarity between sentences?

For my bachelor thesis i am probing various text similarity metrics for how much they incorporate different aspects of sentences. To get those aspects I use datasets that are annotated for semantic ...
3
votes
0answers
57 views

State of the art in controlled english languages?

https://en.wikipedia.org/wiki/Controlled_natural_language lists some controlled languages, of which Attempto Controlled English seems to be the most recent. However, are there any Attempto extensions, ...
3
votes
0answers
69 views

Computational linguist's estimate of minimum hours of speech needed to train a neural net to recognize speech

From a computational linguist's point of view, is there a lower limit on the number of hours of speech needed to train a neural net to translate speech to text? An estimate from CMU is 3000-5000 hours ...
3
votes
0answers
76 views

Does StanfordNLP have a problem with adverbs?

I suspect not, and I'm being dumb, but ... Usain ran quickest. is parsed (https://corenlp.run) as NNP VBZ JJS. Why JJS (Adjective, superlative) and not RBS (Adverb, superlative)? Using extended ...
3
votes
0answers
33 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 ...
3
votes
0answers
143 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, ...
3
votes
0answers
76 views

What features are good for dependency parsing?

I am trying to implement a graph based dependency parser. Since I come from a computer engineering perspective, I have trouble finding the features. Assuming that we have a (head,dependent) relation ...
3
votes
0answers
86 views

Is there a phrasal verb corpus somewhere online?

I'm working on a project where I have syntactic frames in the form of something like "N.agent V PP.stimulus", where each PP consists of a P and a N. I have a set list of verbs, and a list of PPs for ...
3
votes
0answers
103 views

How to get morphological information from Stanford POS tagger?

I'm using the Stanford POS tagger to process German text and I'm interested in assessing the number (singular/plural) of the nouns in the sentence, so that I can classify them accordingly. This is ...
3
votes
0answers
160 views

Distribution of the set of meanings of a given word, in a corpus

I am looking to know about the distribution of word senses, of a particular word in a corpus. How often a word sense will occur out of all the occurrences of that word with any meaning. For example: ...
3
votes
0answers
25 views

Publication venues focusing on reproducing results

Is there any publication venue for natural language processing focusing on reproducing results from other papers?
3
votes
0answers
55 views

Are there any publicly available spell checking corpora?

I need some corpora that contain sentences with misspelled word(s) in order to evaluate the performance of my own spell checking approach. So, the corpora should define the right word alongside the ...
3
votes
0answers
237 views

Downloadable list of Romance-language cognates?

I'm looking for tables of cognates between French, Spanish and Italian (and potentially Latin, Portuguese, Catalan, etc.), so I can run some Python on them. If they could have extra information such ...
3
votes
0answers
189 views

Inside-outside algorithm (PCFG learning) and binarization

I am implementing the Inside-outside algorithm to estimate the parameters of a PCFG based on the train corpus. One observation (on existing implementations) is that, the grammar is converted into ...
3
votes
0answers
144 views

What are the foundational papers in computational phonology?

I'm working on a paper on the history of computational phonology. As I understand it, Chomsky & Halle's SPE acted as a catalyst for research in the field, namely by laying the foundations for two-...
3
votes
1answer
232 views

VerbNet semantic roles and preposition groups - how to determine matches

Using verbnet to test whether a sentence matches a frame, how does one determine whether the semantic role specified in the verbnet frame is appearing in the sentence or not? e.g. on this verbnet ...
3
votes
0answers
481 views

Stanford NLP parsers and idioms that have common semantic meaning

I have parsed the following sentence in the Stanford CoreNLP demo page and the Stanford parser demo page. Although both result in a parse that can imply purpose semantics (hinging on the advcl and the ...
3
votes
0answers
67 views

Any NLP performance timeline?

I am looking for any plots, etc. that show performance metrics on various NLP tasks as a function of year. E.g. the following figure shows the evolution of performance of face recognition systems:
3
votes
0answers
204 views

Where can I find Japanese-English (manually) word-aligned corpora?

I'm looking for as many very reliable Japanese-English corpora as possible so I'd like to ask: Are there any other manually aligned corpora besides KFFT's and Utiyama's? What are the most accurate ...
3
votes
0answers
297 views

Calculating margin of error for precision and recall

I commonly calculate the precision and recall for information pulled from text but I'm not sure how to calculate the margin of error for those precision and recall values. So for example, if I have a ...
2
votes
0answers
67 views

How to find the characteristics of a bunch of word Clusters?

My Motivations I'm trying to learn German and realized there's a confounding fact with the structure of German: every noun has a gender which seems unrelated to the noun itself in many cases. Unlike ...
2
votes
1answer
94 views

Non-projective tree sentences

I'm trying to generate the non-projective tree of the sentence: "A hearing is scheduled on the issue today." But with the Stanford Core NLP tool (https://corenlp.run/), I obtain a projective ...
2
votes
0answers
43 views

Word alignment for Switchboard Dialogue Acts Corpus

I am trying to connect the dialogue acts of the Switchboard Dialogue Acts Corpus with the word alignment timing information available here. I can see how it is possible to match up every utterance ...
2
votes
0answers
35 views

Grammar induction from grammaticality rules

Let's have formalisation of grammaticality judgments in some deduction system. Is it possible to learn/induce grammar from rules that govern grammaticality judgments? Is there theory, that connects ...
2
votes
0answers
78 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 ...
2
votes
1answer
289 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 ...
2
votes
0answers
60 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 ...
2
votes
0answers
37 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 ...
2
votes
0answers
455 views

What is the intuition behind the rules of Hobbs Algorithm?

I am trying to understand the Hobbs Algorithm. I am able to follow the algorithm and solve tree walking questions to find the antecedent of a pronoun, but I do not get the intuition behind the rules ...
2
votes
0answers
46 views

Connections between combinatory categorial grammars and abstract categorial grammars?

Are there connections/translation or common tools usage/adaptation between combinatory (concrete) categorial grammars (incl. Lambek calculus) and abstract categorial grammars? Can tools for one of ...
2
votes
0answers
45 views

What is the source of knowledge/discovery for the semantics? Automation of semantic science?

Natural sciences observe facts and make models. Mathematics more or less arbitrarly generates axioms and investigates all the possible consquences of them. What is the source of semantic knowledge (e....
2
votes
0answers
73 views

Data/Resource for adjectives related to nouns

I am looking for resource or some way(maybe using multiple resources) which can help me figure out which adjectives to use. For example: weight > 40 : heavier age > 40 : older I am not sure how to ...
2
votes
0answers
32 views

Any good, up-to-date advanced textbooks/handbooks in statistical parsing?

I was wondering if there are any good, up-to-date advanced textbooks in parsing, after having finished the preliminary treatments in Jurafsky & Martin and Manning & Schütze. Either ...