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.

Filter by
Sorted by
Tagged with
2
votes
2answers
136 views

What is the best/state-of-the-art logic for representing English language?

I know people have used lambda terms which "compile into" first-order logic, but based on what I have seen that is not particularly great for representing complex sentences with causal or temporal ...
1
vote
0answers
27 views

Language model created with SRILM does not sum to 1

I created an n-gram language model on the Penn Treebank using the following command: ngram-count -text $trainfile -order 5 -lm $temp/templm.ptb -gt3min 1 -gt4min 1 -kndiscount -interpolate -unk This ...
2
votes
2answers
591 views

Automatic sentence segmentation of recorded speech with text

Given recorded speech with known text, is there an automated way to find the start/end time points of each sentence within the recording? Google Cloud Speech API does not appear to return any time ...
3
votes
1answer
698 views

How to interpret the dependency parse tree of an English Slot Grammar?

I am reading the paper titled Deep parsing in Watson (DOI: 10.1147/JRD.2012.2185409) and need help understanding this figure: This is the paragraph that describes the tree in the figure above: An ...
2
votes
2answers
112 views

Speech and Language Processing without Representation of Language?

While reading in the literature about text processing I found this scientific paper about text classification using artificial neural nets. The authors feed their convolutional neural network with ...
0
votes
1answer
41 views

How to return only the person names who belong to a group?

I could classify words in all sentences in a text file as PERSON, LOCATION, ORGANIZATION etc. using Stanford's Named Entity Recognition. But how to extract names of a specific group of persons (eg: ...
4
votes
2answers
130 views

Text classification of semantic relations within text

I am already familiar with some text (document) classification algorithms after processing into a Bag-of-words & tf-idf representation. Classification algorithms such as Multionmial Naive Bayes, ...
0
votes
0answers
66 views

How to train an NLP model(which is to be deployed) without over-fitting?

I have about 40,000 documents( of which 6,000 are test set) I ran cross validation, selected a model that works well for me and recorded a 98% recall with a document classification task. Now, to ...
0
votes
0answers
49 views

Induction of semantics for grammars of natural languages (as opposed to syntax)

I am learning about combinatory categorial grammars and the formal semantics of natural language, course by Partee http://people.umass.edu/partee/MGU_2005/MGU05_formal_semantics.htm (especially ...
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 ...
1
vote
1answer
2k views

What are the most useful programming languages for computational linguists? [closed]

What programming languages should aspiring computational linguists learn? Why? Thanks!
2
votes
0answers
31 views

Is there relationship (and translation) between Link Grammars and Combinatory Categorial Grammars?

Is there relationship (and translation) between Link Grammars and Combinatory Categorial Grammars? Link Grammars have very unusual parse structure - links between words, but CCGs have parse trees. ...
0
votes
2answers
255 views

'there' vs 'it' expletive insertion

These are my conditions for detecting an expletive position: if spec IP has been assigned non 'null' Case and is not theta marked. However, after this I struggle to choose between 'it' and 'there'. ...
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 ...
2
votes
0answers
158 views

Combinatory Categorial Grammar developments and lexicon for German language?

I am trying to apply Cornell Semantic Parsing framework (implementation of Combinatory Categorial Grammars CCG) to the German language. This framework takes natural language texts, learns grammar and ...
2
votes
1answer
80 views

Why does the CLAWS5 tagset separate “of” from all other prepositions?

The well-known CLAWS5 tagset, for tagging English language lexemes etc, has one tag PRF, specifically for tagging the preposition "of", while other prepositions get the tag PRP, which is for all ...
8
votes
4answers
1k views

What are the current hurdles to automatic audio to IPA transcription?

I have heard several people tell me that automatic segmentation and transcription to (narrow) IPA of fieldwork-quality audio is impossible at the moment, and even from laboratory-quality audio ...
4
votes
3answers
2k views

Where can I find a free text corpus for the Hindi language?

I need a text corpus for my NLP project in Hindi, however all the corpora I found are not free for downloading. Is there any free annotated Hindi text corpus at all? If yes, where can I find it?
2
votes
1answer
92 views

named entities recognition using stanfordNERTagger

I am trying to get the named entities in a small test using stanford NER tagger. Here is the code: from nltk.tag import StanfordNERTagger st = StanfordNERTagger('english.all.3class.distsim.crf.ser') ...
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 ...
6
votes
4answers
1k views

What are multi-word concepts (technical terms) called and how are they found?

Go to this website: http://parts-of-speech.info/ Now go to this Wikipedia article: https://en.wikipedia.org/wiki/Evolutionary_psychology Grab the first paragraph and feed it into POS tagger to see the ...
0
votes
1answer
94 views

Pointing words in a sentence to their specific dictionary defininition

I would like to parse a piece of text (Spanish if possible, otherwise English) and point each word in the text to its correct entry in a dictionary. For example: I turned her down. would point to ...
2
votes
2answers
980 views

Linguistics concept about meaning of words according to a context

Several linguistics questions about the meaning in context of words: How is called in linguistics the fact some words have a meaning only with other words? How is it called when a word changes ...
1
vote
1answer
101 views

How to assess sentence complexity [closed]

I'm not really a linguist but I am analysing some medical free text so that I'll be able to extract various phrases using regular expressions. I have noticed that the sentences are usually very ...
3
votes
2answers
65 views

Should compounded words through agglutination be treated as unigrams or n-grams? [closed]

In a statistical language model, should one tokenize compounded words through agglutination as words by themselves (unigrams) or should they be tokenized into n-grams? Example: Staatspolizei (ISO ...
3
votes
1answer
52 views

Correcting the names in NLP

I have a dataset where lot of names are written like man1sh instead of manish, vikas as v1kas. How can one correct these names in NLP?
0
votes
1answer
111 views

How to extract rows with only meaningful text in a column

I have a large excel file like the following: Timestamp Text Work Id 5/4/16 17:52 rain a lot the packs maybe damage. Delivery XYZ 5/4/16 18:29 wh....
3
votes
0answers
106 views

n-gram language model smoothing [closed]

I use the corpora of webtext to train n-gram model in NLTK.And i use katz back-off smoothing to solve 0 count-problem.But one problem is:while the smoothing used in based-on characters language model,...
1
vote
1answer
55 views

Stanford NER tagger

I am trying to use Stanford NER tagger from the following link:NER tagger I output format I have chosen 'slashTags' and entered the following sentence: While in France, Christine Lagarde discussed ...
0
votes
0answers
17 views

What is posting act tagging in transformational learning?

We have presented a novel application of transformation-based learning to the problem of identifying postings in chat-room conversations. Posting act tagging aids in the formation of models of social ...
4
votes
1answer
196 views

Where can I find training data for dialects of Hindi?

I am working on a NLP project that aims at identifying different dialects of Hindi language. My über goal is to generate dialogs in once the program identifies which dialect is given. I tried ...
1
vote
0answers
32 views

How To incorporate TurboParser Instead of MaltParser for improved results like from online demo?

I have successfully installed Semafor on Linux Mint 18.1 and I can run it. But the results I get from my version differs drastically from the online demo. I realized that online demo uses TurboParser, ...
2
votes
0answers
92 views

Hidden Markov Models: Linking states to labels after EM training

The tl;dr version first: I have the following problem: I implemented Baum Welch for ergodic HMMs. I do it like this: I pass the model two number C1 and C2, it builds a fully connected state machine ...
3
votes
1answer
58 views

Is there a computer-readable Hiberno-English pronunciation dictionary?

For American English, there's the CMUDict, but is there one for Irish pronunciation? If there isn't, is there a way to translate American to Irish pronunciation?
-2
votes
2answers
986 views

Do any English verbs end in -s or -es that are singular?

I'm trying to automatically determine if a verb is singular/plural in a program, I cannot think or find on Google any verb that ends in -s or -es before conjugation. Are there any?
0
votes
0answers
92 views

Corpus for text classification with annotated support phrases

I am looking for corpora for text classification with annotated support phrases. Support phrases = phrases that explain why a text was given a label. For example, if the text is "The patient works ...
1
vote
1answer
111 views

NLP text classification approach for smart devices

As a project, I have been trying to understand the low-level heuristic approach from the perspective of a device attempting to behave smart, like Alexa and the likes Generally speaking, it starts ...
2
votes
1answer
143 views

File structures for named entity recognition datasets

I am looking for a list of file structures used by named entity recognition datasets. I am aware of the file structures mentioned below. What other file structures are there? CONLL 2003 Inline ...
2
votes
1answer
531 views

C&C/Boxer Source Code

I’ve been trying to find C&C tools and Boxer online and found this link in many places (http://svn.ask.it.usyd.edu.au/trac/candc) but the link does not work for me. Is there another place to find ...
3
votes
3answers
472 views

Compare 2 english text corpora

I have 2 English text corpora. One is people talking about topic "A" while other is people talking about topic "B". From a language point of view - the way people express themselves on topic "A" is ...
1
vote
1answer
71 views

Help understanding letter sets

I am trying to understand the working of an old computer speech synthesizer (SAM for the commodore64) which uses a series of rules to break English text into a string of phonemes. The rules make some ...
7
votes
1answer
386 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 ...
0
votes
0answers
1k views

Split sentence into phrases and words

I need a direction, advice where to search information. I want to split sentences into separate words and phrases. For example this sentence "Tommy has a lot of job experience" has the phrase "a lot ...
1
vote
0answers
143 views

Synonym/hyponyms/hypernym detection data set

I am looking for data sets that I could use to train and benchmark a system that detects synonyms, hyponyms and hypernyms in a text. For example, in the sentence In statistics, logistic ...
1
vote
1answer
314 views

Gold standard corpus size?

I have a 25 MB corpus (2.300.000 words) to annotate with a rule based system. What is the ideal size of a gold standard corpus that I should create in order to evaluate the tool? Many thanks for your ...
1
vote
0answers
65 views

“Did” as a habitual / emphatic marker in Southern varieties of British English

I'm currently doing research on the salience of did as an emphatic marker in Southern varieties of British English as illustrated in (1). I'm comparing this with the salience of did as a habitual ...
2
votes
1answer
72 views

Automatically retrieving all the sub-concepts associated to a given concept

I wonder if you know how automatically obtain all the sub-concepts associated to a given concept. For example, given the concept car, I would like to automatically retrieve concepts such as: wheel, ...
0
votes
0answers
106 views

Library of regular expressions for lexical relations in a corpus

I would like to ask if there is a library of regular expressions for mining patterns reflecting lexical semantic relations from a corpus. These patterns should cover a wide variety of aspects synonymy ...
5
votes
3answers
621 views

Are there tools to build domain specific corpus? [closed]

I would like to build a domain specific corpus. By this I mean a corpus from a specific knowledge area, for instance Law, Psychiatry, or Klingon language. I am currently using a Wikipedia corpus, and ...

1
3 4
5
6 7
13