Linguistic Analysis

Welcome to the Linguistic Analysis API Forum

Categories

API – Any ideas or feedback pertaining to features or enhancements to Linguistic Analysis API.

Documentation – Any ideas or suggestions for the API Reference or Documentation.

Language Support – Submit a request to have a particular language supported.

Samples & SDK Request – Let us know if you would like to see a Code sample or SDK provided.

How can we improve Linguistic Analysis for Cognitive Services?

(thinking…)

Enter your idea and we'll search to see if someone has already suggested it.

If a similar idea already exists, you can support and comment on it.

If it doesn't exist, you can post your idea so others can support it.

Enter your idea and we'll search to see if someone has already suggested it.

  1. Provide Linguistic Analysis API Keys

    My 30 day trial is expired. There is no way to renew that I can see, there is no option to subscribe in Azure.

    For now I'm using Google Natural Language (which does provide some lemmas - not as good as Office NLP but OK).

    1 vote
    Sign in
    Check!
    (thinking…)
    Reset
    or sign in with
    • facebook
    • google
      Password icon
      I agree to the terms of service
      Signed in as (Sign out)

      We’ll send you updates on this idea

      0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
    • Analysed text does not get displayed

      Hi,
      I found a bug when I try the following text : I'm working in Innovalus

      But the POS Tags and Tokens are getting extracted.
      (TOP (S (NP (PRP I)) (VP (VBP 'm) (VP (VBG working) (PP (IN in) (NP (NNP Innovalus)))))))

      [I'm] text is not handled, but when I expand it to [I am] it is working fine.

      1 vote
      Sign in
      Check!
      (thinking…)
      Reset
      or sign in with
      • facebook
      • google
        Password icon
        I agree to the terms of service
        Signed in as (Sign out)

        We’ll send you updates on this idea

        0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
      • Combine the tag with the token side by side in the results

        Hi,

        Currently, it isn't easy to parse the results. Fetching this:

        (TOP (SBARQ (WHADVP (WRB How)) (SQ (VP (VBP are)) (NP (PRP you)) (NN today) (. ?))))

        requires a lot of string manipulation. In a scenario where you'd want to keep only the verbs, you'd have a lot of work. Why not doing something similar as what Stanford does? So, in the results, we'd have the tokens and their corresponding tag side by side like this for instance:
        {
        "Len": 5,
        "NormalizedToken": "Hello",
        "Offset": 16,
        "RawToken": "Hello",
        "Tag":"UH"
        }

        that'd make it easier to extract only tags you're interested in…

        1 vote
        Sign in
        Check!
        (thinking…)
        Reset
        or sign in with
        • facebook
        • google
          Password icon
          I agree to the terms of service
          Signed in as (Sign out)

          We’ll send you updates on this idea

          0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
        • Linguistics Analysis: correct categorization of speech disfluency

          Currently, speech parts such as "um" and "like" appear to be categorized as nouns or adverbs (depending on context). It would be great to detect these speech disfluencies. I have an idea for an app to help with feedback for public speaking.

          1 vote
          Sign in
          Check!
          (thinking…)
          Reset
          or sign in with
          • facebook
          • google
            Password icon
            I agree to the terms of service
            Signed in as (Sign out)

            We’ll send you updates on this idea

            2 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
          • Complete Swagger specification

            The Swagger spec for the API is incomplete. It is missing response definitions for each of the operations available.

            1 vote
            Sign in
            Check!
            (thinking…)
            Reset
            or sign in with
            • facebook
            • google
              Password icon
              I agree to the terms of service
              Signed in as (Sign out)

              We’ll send you updates on this idea

              0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
            • Lemma detail in token result

              It would be nice if linguistic api token result includes lemma for the word.

              Part of speech with it even better. (to catch the standard with other NLP libraries.

              2 votes
              Sign in
              Check!
              (thinking…)
              Reset
              or sign in with
              • facebook
              • google
                Password icon
                I agree to the terms of service
                Signed in as (Sign out)

                We’ll send you updates on this idea

                1 comment  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
              • Don't see your idea?

              Linguistic Analysis

              Feedback and Knowledge Base