LEXISTEMS SensibleSummaries splash image.

Welcome to true document summarization. Meaning-based. State-of-the-Art.

SensibleSummaries is very easy to use and appreciate: just select, paste or drop a document, and in 1 click you get its content back as a text, PDF or vocal summary.

Available as a software API or plug-and-play server appliance, SensibleSummaries brings summarization to any of your applications and runs on any infrastructure, including your own exclusively.

Because Sensiblesummaries is GAFAMs-free, it can be trained on specific documents and vocabularies, keeps costs under control, secures data end-to-end and complies with GDPR and all other privacy regulations.

Time is what you make of it.

Discover why adopting SensibleSummaries is the most sensible business decision you can make today...

SensibleSummaries' critical features
  • Functional

    • Summarizes any text or document
    • Text, PDF or vocal summaries: 1-click operation
    • Summaries' lengths and bias adjustable to user or organization preferences
    • Fully adaptable to corporate or vertical vocabularies
    • Generative or extractive summarization
    • 3 supported languages: English, French, Spanish; any other on demand
    • Directly pluggable to any CMS, search engines or business applications.
  • Technical

    • Available as a software or hardware solution (API / server appliance)
    • API mode installable on any infrastructure, including 100% on-premises
    • Optimized GPU requirements.
  • Eco-responsibility

    • Eco-responsible from design to production use
    • Optional carbon metrics returned with all summaries.
  • Availability and support

    • Available and supported worldwide by the SENSIBLE Alliance.
  • GAFAM-free and therefore

    • ...sensibly cost-effective via subscription or one-off pricings
    • ...fully secured and compliant with all Privacy regulations end-to-end.
SensibleSummaries solves your information overload pain points

More and more to know in less and less time...

SensibleSummaries gives you the gist of any text or document -- in your preferred format.

Time
Problem: Your collaborators can't keep up with everything they have to know.
Solution: In (really) one click, SensibleSummaries sums up any textual content. In text, PDF or vocal format. Read, download or listen. Your time, your preferences.
Costs
Problem: Your teams spend hours reading or searching information.
Solution: Abstracts or highlighted originals slash read times and reading reluctance; staff productivity and performance is immediately improved.
Multilingualism
Problem: You have to read documents in languages other than your native one(s).
Solution: SensibleSummaries works in a variety of languages, and delivers easy-to-understand abstracts. Names and numbers are left untouched. The rest is as plain as ABC.
Integration
Problem: Your information workflow is based on search engines, CMSes and/or custom applications.
Solution: SensibleSummaries is easy to add to existing applications and document frameworks. A simple click or voice command and a sensible summary is ready.
More solved painpoints...
Custom processing
Problem: You need additional processing along with summarization.
Solution: Like all LEXISTEMS solutions, SensibleSummaries can be augmented with custom plugins or blackboxes. Name it, we'll connect it.
Scalability
Problem: All users in your organizations want it.
Solution: As a Docker-based API or server appliance(s), SensibleSummaries scales horizontally to as many users as desired.
Security
Problem: The documents you have to read are sensitive.
Solution: In API or server appliance mode, SensibleSummaries can be deployed 100% on premises or on your own infrastructure. Network traffic is secured via http2 end-to-end, with complete shielding from network access.
Compliance
Problem: GDPR, DPA, CCPA... Your organization is legally bound and compliance is your professional responsibility.
Solution: SensibleSummaries complies by design with privacy and other business-specific data regulations, current and future. Nothing to worry about on this front either.
Examples of SensibleSummaries use cases

Wikipedia Spanish

Context - Wikipedia is a valuable test case because of its variety in contents and styles, even though a factual bias is encouraged. This bias is precisely one of the main interests here: simple facts is what most summaries users want, and anyone can appreciate the pertinence of the result from reading the source. We present the Spanish version as Spanish is one of the lesser available language in summarization. French and English versions are available as well.

Documents type - This demo features a selection of articles on many topics - artistic, technical, historical, biographical - and of different lengths. As with other SensibleSummaries demos, the source area also accepts pasted text (any content, from Wikipedia or not).

France's supreme Court Decisions

Context - The Cour de Cassation is France's highest jurisdiction in matters of civil and criminal law. Its Decisions are often archived in digital format and that's what made this use case interesting: the many imperfections of the source texts (see the example capture, see the comments below) add a layer of complexity to the specific legal phrasing. References are often implied in reasoning or wording. General and case-specific remarks are of equal importance. Decisions' structures follow quite different received patterns... All these combined result in countless difficulties of understanding and risks of misinterpretation.

Documents type - The Court's Decisions are processed in raw electronic format: blocks of unstructured text (single database string-type records) with often deficient punctuation and casing due to initial OCR ingestion.

French Senate Reports

Context - France's Senators produce numerous Reports on the country's problems, trends and evolutions. As with every 100+ pages documents, summarization is a huge time saver even though, given the extreme variety of topics and forms in this use case, some Reports summaries are not yet perfect (they're just state-of-the-art). PDF summaries are generated on the backend side and directly readable / downloadable in frontend. When in text only, summaries are delivered in markdown format in order to preserve the documents' initial structure. In either format, they're available in about 30 seconds.

Documents type - In this use case, the Reports are stored in a dedicated repository to which a SensibleSummaries API is connected (contrary to most other use cases presented here, users cannot paste content). The Reports selector adapts to the repository's updates.

Daily Mail abstracts

Context - The Daily Mail is one of UK's most famous popular newspapers, covering topics from politics to entertainment, society, sports, celebs, etc., in styles not always "royal". This test case generates very short articles abstracts (text or vocal) that help catch up with the news in no time. On the same model, demos are available for US English, French, Spanish, Mexican Spanish, Colombian Spanish and Ecuadorian Spanish papers.

Documents type - This test case features widely available sources with and without HTML formatting. A hundred of random articles is provided for each newspaper, but any text can be pasted into the "input" area, including text copied directly from media websites.

French Press headlines

Context - Compared to the Daily Mail abstracts demo presented above, this test case focuses on producing headlines ("chapos" in journalistic French) instead of abstracts. A headline is a paragraph that separates an article's title from its body. It is meant to tease or entice the reader into reading further, not to summarize the whole article. The task is therefore distinctive from pure summarization, requiring a different level of understanding.

Documents type - We used published articles from a variety of French newspapers and trade magazines. The articles cover the widest possible variety of topics, lengths, styles and vocabularies. As with other SensibleSummaries demos, content can be pasted and "headlined" in one click, with text and/or vocal results.

Your SensibleSummaries ROI

All documents summarization solutions are not created equal.

Here is why SensibleSummaries is the soundest choice ROI-wise:

Immediate
SensibleSummaries is ready to deploy, wherever and however you want. No complex setup. Time‑to‑summarization is immediate.
Customizable
SensibleSummaries' AI models can be adapted to organizations' specific documents, formats and vocabularies for even more precision.
Cost-effective
SensibleSummaries' pricing options match your budget with predictable, no hidden costs.
LEXISTEMS SensibleSummaries ROI diagram.
Elastic
SensibleSummaries scales along your user base and documents volume. Adopt it once and expand with it.
Secure
In API or server appliance mode, SensibleSummaries runs entirely on your infrastructure through http2, with complete shielding from network access.
Compliant
SensibleSummaries enforces all data and privacy regulations, current and future.

speedBenchmarks

ROUGE metrics

(Generative summaries)

English French Spanish
Business 35.99 / 14.08 / 29.11 33.91 / 12.59 / 27.48 36.82 / 14.40 / 29.46
Press 44.17 / 21.47 / 41.11 45.20 / 21.56 / 41.88 44.78 / 22.01 / 41.70
Legal - 59.10 / 43.98 / 49.97 -

In percentages. For summarization, 0% and 100% are not considered worst and best.

ROUGE, or Recall-Oriented Understudy for Gisting Evaluation, is a set of metrics for evaluating automatic summarization.

In the table above, the first figure is the standardized ROUGE-1 score (F1 subscore), which represents the performance of capturing as many information as possible in unigrams, and keeping them accurate in generating the summaries (unigrams better reflect the fluency of the summarized text).

The second figure is the standardized ROUGE-2 score (F1 subscore), which represents the conservation of bigrams (typically an entity and a specifier). This metric reflects the fidelity to the original wording for name chunks whose rephrasing would be detrimental to understanding the summarized result.

The third figure is the standardized ROUGE-L, which represents the similarity between source and summary.

Please note that ROUGE scores depend largely on the nature and average length of the source documents. In the table above, scores also take into account LEXISTEMS' meaning-based approach, whereas ROUGE is known as a more syntactical than semantical instrument. We encourage you to compare them to the literature, keeping in mind the difference between extractive and generative (aka abstractive) summarization.

handymanTechnical requirements

verifiedCertifications

Availability - Pricing - Support

Meet SensibleSummaries

Time is money.

In a one-to-one session or an interactive video call, see for yourself how SensibleSummaries will benefit your business...