Welcome to OStack Knowledge Sharing Community for programmer and developer-Open, Learning and Share
Welcome To Ask or Share your Answers For Others

Categories

0 votes
1.1k views
in Technique[技术] by (71.8m points)

nlp - Determining Grammatical Validity of Text Input

I am looking for some way to determine if textual input takes the form of a valid sentence; I would like to provide a warning to the user if not. Examples of input I would like to warn the user about:

"dog hat can ah!"

"slkj ds dsak"

It seems like this is a difficult problem, since grammars are usually derived from textbanks, and the words in the provided sentence input might not appear in the grammar. It also seems like parsers maybe make assumptions that the textual input is comprised of valid English words to begin with. (just my brief takeaway from playing around with Stanford NLP's GUI tool). My questions are as follows:

  1. Is there some tool available to scan through text input and determine if it is made up of valid English words, or at least offer a probability on that? If not, I can write this, just wondering if it already exists. I figure this would be step 1 before determining grammatical correctness.
  2. My understanding is that determining whether a sentence is grammatically correct is done simply by attempting to parse the sentence and see if it is possible. Is that accurate? Are there probabilistic parsers that offer a degree of confidence when ambiguity is encountered? (e.g., a proper noun not recognized)
  3. I hesitate to ask this last question, since I saw it was asked on SO over a decade ago, but any updates as to whether there is a basic, readily available grammar for NLTK? I know English isn't simple, but I am truly just looking to parse relatively simple, single sentence input.

Thanks!

question from:https://stackoverflow.com/questions/65851581/determining-grammatical-validity-of-text-input

与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
Welcome To Ask or Share your Answers For Others

1 Answer

0 votes
by (71.8m points)

A starting point are classification models trained on the Corpus of Linguistic Acceptability (CoLA) task. There are several recent blog articles on how to fine tune the BERT models from HuggingFace (python) for this task. Here is one such blog article. You can also find already fine-tuned models for CoLA for various BERT flavors in the HuggingFace model zoo.


与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
Welcome to OStack Knowledge Sharing Community for programmer and developer-Open, Learning and Share
Click Here to Ask a Question

...