Full Natural Language Research Articles

Using Enriched Samples for Semi-Automated Vocabulary Expansion to Identify Rare Events in Clinical Text: Sexual Orientation as a Use Case.

We demonstrate the utility of concept lexicon expansion and evaluation using enriched samples of patients and documents with sexual orientation as a use case for rare event detection in electronic medical records. Using this approach, we found 7 additional words and 21 misspellings beyond our initial set of five seed words. We can use the expanded vocabulary to further develop a full natural language processing system to identify instances where sexual orientation is documented.

Automatic translation of Arabic text-to-Arabic sign language

Arabic sign language (ArSL) is a full natural language that is used by the deaf in Arab countries to communicate in their community. Unfamiliarity with this language increases the isolation of deaf people from society. This language has a different structure, word order, and lexicon than Arabic. The translation between ArSL and Arabic is a complete machine translation challenge, because the two languages have different structures and grammars. In this work, we propose a rule-based machine translation system to translate Arabic text into ArSL. The proposed system performs a morphological, syntactic, and semantic analysis on an Arabic sentence to translate it into a sentence with the grammar and structure of ArSL. To transcribe ArSL, we propose a gloss system that can be used to represent ArSL. In addition, we develop a parallel corpus in the health domain, which consists of 600 sentences, and will be freely available for researchers. We evaluate our translation system on this corpus and find that our translation system provides an accurate translation for more than 80% of the translated sentences.

Engineering doc2vec for automatic classification of product descriptions on O2O applications

In this paper, we develop an automatic product classifier that can become a vital part of a natural user interface for an integrated online-to-offline (O2O) service platform. We devise a novel feature extraction technique to represent product descriptions that are expressed in full natural language sentences. We specifically adapt doc2vec algorithm that implements the document embedding technique. Doc2vec is a way to predict a vector of salient contexts that are specific to a document. Our classifier is trained to classify a product description based on the doc2vec-based feature that is augmented in various ways. We trained and tested our classifier with up to 53,000 real product descriptions from Groupon, a popular social commerce site that also offers O2O commerce features such as online ordering for in-store pick-up. Compared to the baseline approaches of using bag-of-words modeling and word-level embedding, our classifier showed significant improvement in terms of classification accuracy when our adapted doc2vec-based feature was used.

Human-machine conversations to support multi-agency missions

In domains such as emergency response, environmental monitoring, policing and security, sensor and information networks are deployed to assist human users across multiple agencies to conduct missions at or near the 'front line'. These domains present challenging problems in terms of human-machine collaboration: human users need to task the network to help them achieve mission objectives, while humans (sometimes the same individuals) are also sources of mission-critical information. We propose a natural language-based conversational approach to supporting humanmachine working in mission-oriented sensor networks. We present a model for human-machine and machine-machine interactions in a realistic mission context, and evaluate the model using an existing surveillance mission scenario. The model supports the flow of conversations from full natural language to a form of Controlled Natural Language (CNL) amenable to machine processing and automated reasoning, including high-level information fusion tasks. We introduce a mechanism for presenting the gist of verbose CNL expressions in a more convenient form for human users. We show how the conversational interactions supported by the model include requests for expansions and explanations of machine-processed information.

Spoken English Language Development Among Native Signing Children With Cochlear Implants

Bilingualism is common throughout the world, and bilingual children regularly develop into fluently bilingual adults. In contrast, children with cochlear implants (CIs) are frequently encouraged to focus on a spoken language to the exclusion of sign language. Here, we investigate the spoken English language skills of 5 children with CIs who also have deaf signing parents, and so receive exposure to a full natural sign language (American Sign Language, ASL) from birth, in addition to spoken English after implantation. We compare their language skills with hearing ASL/English bilingual children of deaf parents. Our results show comparable English scores for the CI and hearing groups on a variety of standardized language measures, exceeding previously reported scores for children with CIs with the same age of implantation and years of CI use. We conclude that natural sign language input does no harm and may mitigate negative effects of early auditory deprivation for spoken language development.

Automatic Identification of Conceptual Metaphors With Limited Knowledge

Full natural language understanding requires identifying and analyzing the meanings of metaphors, which are ubiquitous in both text and speech. Over the last thirty years, linguistic metaphors have been shown to be based on more general conceptual metaphors, partial semantic mappings between disparate conceptual domains. Though some achievements have been made in identifying linguistic metaphors over the last decade or so, little work has been done to date on automatically identifying conceptual metaphors. This paper describes research on identifying conceptual metaphors based on corpus data. Our method uses as little background knowledge as possible, to ease transfer to new languages and to mini- mize any bias introduced by the knowledge base construction process. The method relies on general heuristics for identifying linguistic metaphors and statistical clustering (guided by Wordnet) to form conceptual metaphor candidates. Human experiments show the system effectively finds meaningful conceptual metaphors.

Evaluating the usability of natural language query languages and interfaces to Semantic Web knowledge bases

The need to make the contents of the Semantic Web accessible to end-users becomes increasingly pressing as the amount of information stored in ontology-based knowledge bases steadily increases. Natural language interfaces (NLIs) provide a familiar and convenient means of query access to Semantic Web data for casual end-users. While several studies have shown that NLIs can achieve high retrieval performance as well as domain independence, this paper focuses on usability and investigates if NLIs and natural language query languages are useful from an end-user's point of view. To that end, we introduce four interfaces each allowing a different query language and present a usability study benchmarking these interfaces. The results of the study reveal a clear preference for full natural language query sentences with a limited set of sentence beginnings over keywords or formal query languages. NLIs to ontology-based knowledge bases can, therefore, be considered to be useful for casual or occasional end-users. As such, the overarching contribution is one step towards the theoretical vision of the Semantic Web becoming reality.

Evaluating the Usability of Natural Language Query Languages and Interfaces to Semantic Web Knowledge Bases

The need to make the contents of the Semantic Web accessible to end-users becomes increasingly pressing as the amount of information stored in ontology-based knowledge bases steadily increases. Natural language interfaces (NLIs) provide a familiar and convenient means of query access to Semantic Web data for casual end-users. While several studies have shown that NLIs can achieve high retrieval performance as well as domain independence, this paper focuses on usability and investigates if NLIs and natural language query languages are useful from an enduser’s point of view. To that end, we introduce four interfaces each allowing a different query language and present a usability study benchmarking these interfaces. The results of the study reveal a clear preference for full natural language query sentences with a limited set of sentence beginnings over keywords or formal query languages. NLIs to ontology-based knowledge bases can, therefore, be considered to be useful for casual or occasional end-users. As such, the overarching contribution is one step towards the theoretical vision of the Semantic Web becoming reality.

Industry Watch: Is 2007 the Year of Question-Answering?

Back at the beginning of 2000, I was a member of a working group tasked to come up with some guidelines for revamping my University's website.During one of our meetings, someone made the suggestion thatdecisions about howto structure and present information on the website should be driven by the kinds of questions that users come to the site with.Suddenly a light went on, and there appeared an idea for data gathering that might provide us withsome useful information. To find out what people really wanted to know whenthey visited the website, we would replace the University's searchengine by a page that invited the user to type in his or her query as a full natural language question. Appropriately chosen examples would be given todemonstrate that using real questions delivered better pages as a result. The data gathered would tell us what people were really looking for, more than could be gleaned from conventional search queries, and would therefore help usto better structure the information available on the website.

The infrageneric classification of Eragrostis (Poaceae)

SummaryVan den Borre, A. & Watson, L.: The infrageneric classification of Eragrostis (Poaceae). – Taxon 43: 383‐422. 1994. – ISSN 0040‐0262.A world‐wide sample of 53 Eragrostis, 1 Diandrochloa and 2 Eragrostiella species was examined in terms of 442 newly recorded characters. These data were stored in the DELTA system and used for generating full natural language descriptions. A selection of morphological and anatomical characters (58 and 60, respectively) were analysed through a variety of phenetic and cladistic methods, revealing significant character correlations and intrageneric species relationships. The analyses are discussed in detail. A revised description of the genus Eragrostis is presented, and two subgenera are recognized, and fully described.

PBS: An economical natural language query interpreter

A natural language interface, named PBS, to a bibliographic information retrieval system, is described, which receives natural language search statements from an end-user and identifies search facets and implied Boolean logic operators. The program is intended for use in conjunction with an intermediary program (OAK) for online database searching, operating in a user's personal computer. Such a program must be fast and make minimal demands on memory, which places severe restrictions on storage of dictionaries and thesauri needed for full natural language interpretation. This initial version deals with a single domain, bibliographic files, almost all of which use the same attributes, such as subject, author, or journal name. The objective of PBS is to identify terms in a natural language query, classify them by attribute, recognize the boolean logic stated or implied, conflate terms that have minor spelling variations, and present the terms to the intermediary program, organized by facet or term category. In testing, the main difficulty resulted from false identification of journal names. Yet, in light of the editorial capabilities of OAK, which allow a user to correct a query before it is given to an IRS, PBS can be regarded as a workable natural language interface that can alleviate some of the problems inherent in native command languages. © 1993 John Wiley & Sons, Inc.