Cognition Technologies Achieves Another Milestone Toward True Semantic Search

PRLog (Press Release) – Nov 05, 2009 – LOS ANGELES – Cognition  Technologies, the next-generation Semantic Natural Language Processing (NLP) company, announces a significant advancement in its Semantic Search capabilities through the release of its advanced syntactic parser module.  Cognition’s powerful Search technology is currently available as an embedded component within applications to make them “semantically aware.”  Examples of this include LexisNexis Concordance and Merrill Lextranet within the legal e-discovery and litigation support markets, where it is being used to cut document review time and costs by 30-50 percent and significantly improve search precision and recall across large data sets. Other applications enhanced by Cognition’s advanced Semantic NLP include interpretation of voice interaction, user question interpretation, mobile Search, customer sentiment analysis, medical informatics and publishing.

Cognition’s advanced syntactic parser greatly enhances Cognition's Search technology by making fuller use of meaning relationships between words (syntactic context), particularly between the verbs and arguments in a sentence which is a key piece in the language-understanding puzzle.  The parser improves upon the already high accuracy of the pre-parser system by significantly reducing error rates in word meaning disambiguation (i.e. understanding the correct meaning of a word based upon the context in which it is used).  This is accomplished with no decrease in query speed and only a moderate increase in indexing time.

Cognition’s syntactic parser is a CYK (Cocke-Younger-Kasami algorithm, a bottom-up parsing method) deductive chart parser for MCFGs (Multiple Context-Free Grammars, a mildly context sensitive grammar formalism) which leverages Cognition's extensive Semantic Map of the English language.  It is successful, in part, due to the robust and comprehensive representation of syntactic and semantic features in Cognition’s Semantic Map, which is the world’s largest map, containing more than 506,000 word stem (word root) and 536,000 word sense (word meaning) entries.

“Beyond accuracy improvement, Cognition’s advanced syntactic parser is an essential step towards realization of the Semantic Web which evolves content from simple data to real information,” said Dr. Kathleen Dahlgren, Cognition’s founder and CTO. “A parser is needed to facilitate content understanding because, in the process of understanding, we need to recognize the relationships between things (e.g. who did what to whom?), the references of pronouns (e.g. who was “he” in a text?), relationships of events (e.g. time sequence, causal sequence), and numerical values (e.g. one vs. many).”

Examples of Search accuracy improvements due to the introduction of the new advanced parser are:  

Query: “Which car companies tanked?”

The pre-parser system incorrectly interprets “tanked” as “to gas up” while the advanced parser recognizes the correct meaning as “to fail or decline” because, in this case, it is an intransitive verb usage and Cognition’s sub-categorizations (syntactic feature data) prefer this meaning for this sentence.

Query: “What happened after Rome fell to the Visigoths?”

The pre-parser system incorrectly interprets “fell” as the stem “fell” as in “to fell a tree.”  The advanced parser recognizes that “fell” followed by a prepositional phrase is a better match for the “concede or defeat” sense of the stem “fall” and correctly picks that stem.

Query: “When did the U.S. begin building monuments?”

The pre-parser system incorrectly analyzes “building” as the noun meaning “edifice or structure.”  The advanced parser system recognizes that “building” must be a verb in the sentence and correctly picks the “construct” meaning of the stem “build.”

More information about this capability and Cognition’s Semantic NLP™ technology is available on its Web site at www.cognition.com, along with the ability to perform queries on several well-known data sets, such as Wikipedia™.

About Cognition:
Cognition Technologies, based in Los Angeles, has developed a revolutionary Semantic Natural Language Processing (NLP) technology which adds word and phrase meaning and “understanding” to computer applications, enabling them to be more human-like in their processing of information.   Cognition's Semantic Map, the underlying technology developed over the past 24 years, is the largest and most extensive in existence. Applications and technologies which utilize Cognition's Semantic NLP™ technology are positioned to take full advantage of Web 3.0 (the Semantic Web).

Cognition ► Giving technologies new meaning.™

Media Contact:
Scott Jarus
Cognition Technologies
310-641-7200 x210
Scott.Jarus@cognition.com