jeff schneider
  • Member for 3 years, 11 months
  • Last seen more than 2 years ago
Is there a Machine Comprehension system integrating several different linguistic constructions?
Accepted answer
1 votes

Adam is correct, however, there are several companies who are working on large scale NLU / machine comprehension systems. Most companies have not yet released their offerings, or they've only released ...

View answer
Need an online freely available Anaphorically Annotated Corpus of English Language for Identification of Discourse Units
1 votes

This one was just released a couple months ago and is available for download. https://github.com/synapse-developpement/Discovery If the anaphoric references are not to your liking, run the Hugging ...

View answer
Mapping duration mentions to their actual verb event
2 votes

This is a hard problem... many vendors do a poor job of attaching prepositions (including Spacy and Allen AI), but they're all getting better. We use statistics tables to fix the attachment issues (as ...

View answer
Are there corpora which tag phrases by discourse- or conversational-function?
1 votes

I'd take a look at 'dialog acts' rather than general purpose discourse functions. This is a good place to start: https://dialogbank.uvt.nl/wp-content/uploads/tdb/2015/12/DialogBank-LRE-v8.pdf It ...

View answer
Extensive English word corpora
0 votes

You're mixing two concepts: words found in dictionaries (like gcide), and words found in a corpus (like COCA). The words in the dictionary will be stored in their base/lemma form, hence, you won't ...

View answer
How to determine temporal prepositions
Accepted answer
3 votes

Short Answer: Part of speech tags can not be used to determine temporal prepositions. Long Answer: If you really want to do this, extract the prepositional phrases, and run those phrases through '...

View answer
How to derive that a sentence is a question from parts of speech
2 votes

From a part of speech perspective, you'll be interested in the the tags that begin with "W" found here: https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html However, the PoS ...

View answer
Does each verb have a corresponding noun with the same meaning
Accepted answer
1 votes

(This was revised after some great feedback.) Your assertion is largely true, but not universally true. Strong candidates: modal verbs (could, should, ...), compound verbs (spread-eagle, roll-...

View answer
Computational/Formal Approaches to Paragraph-Level Semantics
3 votes

When we implemented our software for 'paragraph analysis' it ended up looking like a 'union of propositions' with two minor changes. 1. paragraphs were often preceded by headings which we used to set ...

View answer
What is about-sentiment called?
Accepted answer
5 votes

Google NLP and others call this 'Entity Sentiment Analysis' (versus document sentiment analysis). Also see "aspect based sentiment', e.g., https://arxiv.org/pdf/1805.07043.pdf Finally, look at OpenAI'...

View answer
Why some verbs have -tion while others don't, when being nounified
2 votes

It's worth noting that there are a number of well known patterns. They're not perfect, but they usually work. There's likely 50 common patterns and another 150 that are less common.

View answer
How can we use the same word in multiple different ways and distinguish the senses so easily?
Accepted answer
3 votes

The number of words humans produce are 'just enough' to allow you (and hopefully another party) to disambiguate the content. We don't stop speaking, or writing until we believe we've disambiguated the ...

View answer
Latest research on the meaning of prepositions
1 votes

The best resource I have found on prepositions is The Preposition Project, see: http://www.clres.com/prepositions.html It will be a tremendous resource to help you understand how prepositions are ...

View answer
Looking for semantic hierarchy, tagset or connected active research
3 votes

ConceptNet has the "is a type of" relations stored, for example: http://conceptnet.io/c/en/king They've preloaded many great sources (Cyc, dbpedia, wordnet, etc). The issue is, the words aren't ...

View answer
"As long as", "So long as", in logic (ambiguity?)
-1 votes

"As long as" and "so long as" are considered discourse connectives. Our discourse analysis software labels it as: while(SomeCondition = true). For example: while("I live" = TRUE), then ("I love you");...

View answer
What functional motivations are there for the choice of light verb constructions over full verbs?
1 votes

Per your request, this is only an opinion... Some speakers will align a question's construction pattern with an answer. The LVC question, "Did you make a decision?" Will result in the LVC response, "...

View answer
What's the term for a word which contains an affix?
-1 votes

Affixation (def), "the result of adding an affix to a root word" (WordNet)

View answer
Where would I go to find a hierarchical list of occupations in English?
-1 votes

Here are approximately 1,000 professions in the English language. Enjoy. https://s3.amazonaws.com/dictionary-legendary/Professions.txt

View answer
How to extract meaning of colloquial phrases and expressions in English
2 votes

This is very difficult. I'll recommend three things: Use the U of I CogComp shallow parser to get phrases (not CoreNLP), see: http://nlp.cogcomp.org/ It's much better at picking up phrases, IMO. If ...

View answer
Word Sense Disambiguation of Words Describing a Set of Documents
1 votes

Nouns/entities help to determine the verb sense, and verb senses influence the noun sense. Complements & prep phrases help with both. "The dog walked along the bank of the river." (along river ...

View answer
Is there any corpus for technical English? (E.g., computers, IT, modern technology)
4 votes

Ironically, your best bet is: https://archive.org/download/stackexchange

View answer
Natural Language Processing Meta-Super-Dictionary
1 votes

You have two input choices: 1. analyze dictionaries (wordnet, worknik or wiktionary), 2. use word embeddings (word2vec, glove, elmo). Use this data with a WSD (word sense disambiguation) solution. ...

View answer