Configuration values & examples

A list of all settable values associated with a Semantria configuration

The mandatory values for creating a configuration are:

name
language_id

During config creation, an ID is assigned by Semantria. During update or delete, you pass the ID of the configuration you want to manipulate to Semantria in the URL.

General Settings

Setting

Default Value

Type

Description

alphanumeric_threshold

80

integer

Percentage of content that has to be alpha-numeric for processing to succeed. Documents that do not meet this threshold will be returned to you with a FAILED status.
Valid range: 0 - 100

callback_url

null

string

URL Semantria should POST data to when processed. Only set this if you are using the callback data retrieval method. If this is set, Semantria will enable callback and send documents to this URL. The URL must start with 'https://'

concept_topics_threshold

0.45

double

Confidence level a category (concept topic) match must have to be returned for a document.
Valid range: 0 - 1

entities_threshold

0.55

double

Confidence level an entity match must have to be returned for a document.
Valid range: 0 - 100

is_autoresponse_enabled

false

boolean

Whether to use the auto-response method for doc processing.

name

no default

string

Name of configuration.

language_id

no default

string

The two character ID of the language you are going to process with this config.

language_name

no default

string

Which language you are going to process with this config. This will be auto-filled by Semantria from the code when first processing.

pos_types

null

string

Which Parts of Speech to return
Accepts: All or one or more of Noun Verb Adjective. If setting more than one, separate with a comma.

summary_size

3

integer

Length of summary in sentences to return per document.

template_config

no default

string

Template id this config was created from, if any.

updated

no default

YYYY-MM-DD HH:MM:SS

UTC date and time this config was last updated.

Boolean Settings

The presence of an argument in the below settings turns that setting on, while absence turns the setting off

ANAPHORA_RESOLUTION

Option to turn on/off anaphora resolution.

ATTRIBUTES

Turn off/on attribute calculation for collection mode.

AUTO_CATEGORIES

Return automatic classification based on a pre-built taxonomy (not editable by the user).

BLACKLISTS

Option to respect lists of words that should not be returned as part of sentiment or themes.

CONCEPT_TOPICS

Return Concept Topics.

DETECT_LANGUAGE

Use Semantria-provided language detection library.

DETECT_PHRASES

Use Semantria algorithm to detect possible sentiment phrases.

DOC_CLASSIFICATION

Use user-provided model-based document classification.

ENTITIES_STEMMING

Stem entities.

ENTITY_OVERLAP

Can a single string return two entities that overlap. E.g. "Ford Fusion" is both a car and a company.

FACETS

Calculate facets in collection mode.

FACET_STEMMING

Stem facets.

FAIL_ON_LONG_SENTENCES

Fail documents with a sentence longer than 1,000 words.

FLATTEN_ALL_UPPERCASE

Turn all upper-case documents into lower-case for NLP purposes.

INTENTIONS

Return intentions.

MENTIONS

Return individual mention location information for NLP extracted items such as entities, themes and queries.

MODEL_SENTIMENT

Run user-provided model based sentiment.

NAMED_ENTITIES

Return entities discovered by NLP.

ONE_SENTENCE_MODE

Treat entire document as a single sentence for NLP purposes.

OPINIONS

Return opinions.

OVERRIDE_SENTIMENT_DICTIONARY

Don't use built-in sentiment dictionary, only user-provided one.

PROCESS_HTML

Try to extract text from well-formed HTML. This will treat the document as having HTML markup.

QUERY_TOPICS

Return Query Topics.

THEMES

Return themes.

INTENTIONS

Whether to retrieve intentions for a document or not.

SENTIMENT

Return sentiment phrases.

RELATIONS

Return relations.

SENTIMENT_PHRASES

Return extracted sentiment phrases.

TAXONOMY

Return results from user-defined taxonomy.

TOPIC_STEMMING

Stem content for query topics.

USER_ENTITIES

Return user-defined entities.

Example JSON output

An example of a JSON object for setting the values is below.

{
    "alphanumeric_threshold": 41,
    "concept_topics_threshold": 0.35,
    "entities_threshold": 40,
    "id": "ed7b6405-2bc2-443d-b6c4-0feab9050c5d",
    "is_autoresponse_enabled": false,
    "language_id": "en",
    "language_name": "English",
    "name": "english --- default",
    "pos_types": "all",
    "settings": [
        "OPINIONS",
        "FACETS",
        "MENTIONS",
        "NAMED_ENTITIES",
        "SENTIMENT_PHRASES",
        "TAXONOMY",
        "ATTRIBUTES",
        "ENTITIES_STEMMING",
        "AUTO_CATEGORIES",
        "ENTITY_OVERLAP",
        "QUERY_TOPICS",
        "RELATIONS",
        "FAIL_ON_LONG_SENTENCES",
        "FACETS_STEMMING",
        "DOC_CLASSIFICATION",
        "ONE_SENTENCE_MODE",
        "DETECT_LANGUAGE",
        "FLATTEN_ALL_UPPER_CASE",
        "TOPIC_STEMMING",
        "USER_ENTITIES",
        "RETURN_SOURCE_TEXT",
        "MODEL_SENTIMENT",
        "INTENTIONS",
        "OVERRIDE_SENTIMENT_DICTIONARY",
        "DETECT_PHRASES",
        "ANAPHORA_RESOLUTION",
        "BLACKLISTS",
        "CONCEPT_TOPICS",
        "THEMES",
        "PROCESS_HTML"
    ],
    "summary_size": 3,
    "updated": "2021-02-18T20:46:22.927Z"
}