scispace - formally typeset
Search or ask a question

Showing papers on "Natural language understanding published in 2013"


Proceedings Article
01 Aug 2013
TL;DR: A sembank of simple, whole-sentence semantic structures will spur new work in statistical natural language understanding and generation, like the Penn Treebank encouraged work on statistical parsing.
Abstract: We describe Abstract Meaning Representation (AMR), a semantic representation language in which we are writing down the meanings of thousands of English sentences. We hope that a sembank of simple, whole-sentence semantic structures will spur new work in statistical natural language understanding and generation, like the Penn Treebank encouraged work on statistical parsing. This paper gives an overview of AMR and tools associated with it.

1,197 citations


Book
01 Jul 2013
TL;DR: This book discusses the development of knowledge acquisition techniques in the field of text-based learning and discusses their applications in the context of education and research.
Abstract: In the last few years, a number of NLP researchers have developed and participated in the task of Recognizing Textual Entailment (RTE). This task encapsulates Natural Language Understanding capabilities within a very simple interface: recognizing when the meaning of a text snippet is contained in the meaning of a second piece of text. This simple abstraction of an exceedingly complex problem has broad appeal partly because it can be conceived also as a component in other NLP applications, from Machine Translation to Semantic Search to Information Extraction. It also avoids commitment to any specific meaning representation and reasoning framework, broadening its appeal within the research community. This level of abstraction also facilitates evaluation, a crucial component of any technological advancement program. This book explains the RTE task formulation adopted by the NLP research community, and gives a clear overview of research in this area. It draws out commonalities in this research, detailing the intuitions behind dominant approaches and their theoretical underpinnings. This book has been written with a wide audience in mind, but is intended to inform all readers about the state of the art in this fascinating field, to give a clear understanding of the principles underlying RTE research to date, and to highlight the short- and long-term research goals that will advance this technology.

348 citations


Patent
06 Mar 2013
TL;DR: In this article, a Natural Language Understanding system for indexing free text documents is presented, which utilizes typographical and functional segmentation of text to identify those portions of free text that carry meaning.
Abstract: A Natural Language Understanding system is provided for indexing of free text documents. The system according to the invention utilizes typographical and functional segmentation of text to identify those portions of free text that carry meaning. The system then uses words and multi-word terms and phrases identified in the free to text to identify concepts in the free text. The system uses a lexicon of terms linked to a formal ontology that is independent of a specific language to extract concepts from the free text based on the words and multi-word terms in the free text. The formal ontology contains both language independent domain knowledge concepts and language dependent linguistic concepts that govern the relationships between concepts and contain the rules about how language works. The system according to the current invention may preferably be used to index medical documents and assign codes from independent coding systems, such as, SNOMED, ICD-9 and ICD-10. The system according to the current invention may also preferably make use of syntactic parsing to improve the efficiency of the method.

187 citations


PatentDOI
Gokhan Tur1, Dilek Hakkani-Tur1, Larry Heck1, Minwoo Jeong1, Ye-Yi Wang1 
21 Feb 2013
TL;DR: In this article, search queries that hit structured web pages are automatically mined for information that is used to semantically annotate the queries and the automatically annotated queries may be used for automatically building statistical unsupervised slot filling models without using a semantic annotation guideline.
Abstract: Structured web pages are accessed and parsed to obtain implicit annotation for natural language understanding tasks. Search queries that hit these structured web pages are automatically mined for information that is used to semantically annotate the queries. The automatically annotated queries may be used for automatically building statistical unsupervised slot filling models without using a semantic annotation guideline. For example, tags that are located on a structured web page that are associated with the search query may be used to annotate the query. The mined search queries may be filtered to create a set of queries that is in a form of a natural language query and/or remove queries that are difficult to parse. A natural language model may be trained using the resulting mined queries. Some queries may be set aside for testing and the model may be adapted using in-domain sentences that are not annotated. The models may be tested using these implicitly annotated natural-language-like queries in an unsupervised fashion.

60 citations


Patent
05 Mar 2013
TL;DR: In this paper, features are disclosed for determining an element of a user utterance or intent in conjunction with one or more related elements of the user utterances or user intent, and the NLU module may determine or verify the values associated with recognized named entities using a data store of known values.
Abstract: Features are disclosed for determining an element of a user utterance or user intent in conjunction with one or more related elements of the user utterance or user intent. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a natural language understanding (“NLU”) module. The NLU module may perform named entity recognition, intent classification, and/or other processes on the ASR results. In addition, the NLU module may determine or verify the values associated with the recognized named entities using a data store of known values. When two or more named entities are related, their values may be determined and/or verified in conjunction with each other in order to preserve the relationship between them.

59 citations


Patent
11 Mar 2013
TL;DR: In this article, a human-machine dialogue system is described which has multiple computer-implemented dialogue components including ASR, natural language understanding (NLU) and semantic re-ranking module.
Abstract: A human-machine dialogue system is described which has multiple computer-implemented dialogue components. A user client delivers output prompts to a human user and receives dialogue inputs from the human user including speech inputs. An automatic speech recognition (ASR) engine processes the speech inputs to determine corresponding sequences of representative text words. A natural language understanding (NLU) engine processes the text words to determine corresponding NLU-ranked semantic interpretations. A semantic re-ranking module re-ranks the NLU-ranked semantic interpretations based on at least one of dialogue context information and world knowledge information. A dialogue manager responds to the re-ranked semantic interpretations and generates the output prompts so as to manage a dialogue process with the human user.

47 citations


Journal ArticleDOI
TL;DR: This article presents the approach to building a complete Semantic Web Search Using Natural Language (SWSNL) system, which includes preprocessing, semantic analysis, semantic interpretation, and executing a SPARQL query to retrieve the results.
Abstract: As modern search engines are approaching the ability to deal with queries expressed in natural language, full support of natural language interfaces seems to be the next step in the development of future systems. The vision is that of users being able to tell a computer what they would like to find, using any number of sentences and as many details as requested. In this article we describe our effort to move towards this future using currently available technology. The Semantic Web framework was chosen as the best means to achieve this goal. We present our approach to building a complete Semantic Web Search Using Natural Language (SWSNL) system. We cover the complete process which includes preprocessing, semantic analysis, semantic interpretation, and executing a SPARQL query to retrieve the results. We perform an end-to-end evaluation on a domain dealing with accommodation options. The domain data come from an existing accommodation portal and we use a corpus of queries obtained by a Facebook campaign. In our paper we work with written texts in the Czech language. In addition to that, the Natural Language Understanding (NLU) module is evaluated on another domain (public transportation) and language (English). We expect that our findings will be valuable for the research community as they are strongly related to issues found in real-world scenarios. We struggled with inconsistencies in the actual Web data, with the performance of the Semantic Web engines on a decently sized knowledge base, and others.

46 citations


01 Nov 2013
TL;DR: This paper provides a first investigation over existing textual inference paradigms in order to propose a generic framework able to capture major semantic aspects in Human Robot Interaction and find an effective synergy between HRI and NLU.
Abstract: This paper provides a first investigation over existing textual inference paradigms in order to propose a generic framework able to capture major semantic aspects in Human Robot Interaction (HRI). We investigate the use of general semantic paradigms used in Natural Language Understanding (NLU) tasks, such as Semantic Role Labeling, over typical robot commands. The semantic information obtained is then represented under the Abstract Meaning Representation. AMR is a general representation language useful to express different level of semantic information without a strong dependence to the syntactic structure of an underlying sentence. The final aim of this work is to find an effective synergy between HRI and NLU.

42 citations


Book ChapterDOI
18 Jul 2013
TL;DR: LightSIDE as mentioned in this paper is a software tool for text assessment for the domains and tasks relevant to them, which enables new, non-expert users to access machine learning for text classification.
Abstract: Machine learning, as an approach for managing large scale challenges in text, has seen a strong uptick in interest in recent years. Tasks which were once unimaginable to automate computationally are now becoming commonplace. Few domains showcase this advancement so clearly as natural language understanding, and the application of machine learning to written text. In this work, we present LightSIDE, a software tool enabling new, non-expert users to access this technology for text assessment for the domains and tasks relevant to them.

34 citations


Proceedings Article
14 Jul 2013
TL;DR: This paper describes research on identifying conceptual metaphors based on corpus data using as little background knowledge as possible, to ease transfer to new languages and to minimize any bias introduced by the knowledge base construction process.
Abstract: 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 minimize 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.

32 citations


Patent
11 Mar 2013
TL;DR: In this paper, the NLU processing arrangement includes an anaphora processor that accesses different information sources characterizing dialogue context, linguistic features, and NLU features to identify unresolved anaphoras in the text words needing resolution in order to determine a semantic interpretation.
Abstract: An automatic conversational system has multiple computer-implemented dialogue components for conducting an automated dialogue process with a human user. A user client delivers dialogue output prompts to the human user and receives dialogue input responses from the human user including speech inputs. An automatic speech recognition engine processes the speech inputs to determine corresponding sequences of representative text words. A natural language understanding (NLU) processing arrangement processes the dialogue input responses and the text words to determine corresponding semantic interpretations. The NLU processing arrangement includes an anaphora processor that accesses different information sources characterizing dialogue context, linguistic features, and NLU features to identify unresolved anaphora in the text words needing resolution in order to determine a semantic interpretation. A dialogue manager manages the dialogue process with the human user based on the semantic interpretations.

Journal ArticleDOI
TL;DR: This review surveys what is possible, and also outlines current research directions forAbstract, structured, representations of knowledge such as lexicons, taxonomies, and ontologies, calling on the proliferation of interlinked resources already available on the web for background knowledge and general information about the world.
Abstract: structured, representations of knowledge such as lexicons, taxonomies, and ontologies have proven to be powerful resources not only for the system- atization of knowledge in general, but to support practical technologies of doc- ument organization, information retrieval, natural language understanding, and question-answering systems. These resources are extremely time consuming for people to create and maintain, yet demand for them is growing, particularly in specialized areas ranging from legacy documents of large enterprises to rapidly changing domains such as current affairs and celebrity news. Consequently, re- searchers are investigating methods of creating such structures automatically from document collections, calling on the proliferation of interlinked resources already available on the web for background knowledge and general information about the world. This review surveys what is possible, and also outlines current research directions. C

15 Dec 2013
TL;DR: This chapter is to introduce the theoretical foundation underlying ARTEMIS, a knowledge-based system which is intended to simulate natural language understanding in the framework of Role and Reference Grammar, and to enhance this functional model in order to make argumental constructions play a decisive role in the computational analysis of the deep semantics in the text.
Abstract: Few researchers in natural language processing are nowadays concerned with linguistically-aware applications. On the contrary, the prevailing trend is towards the search of engineering solutions to practical problems, where researchers are motivated by the immediate gratification from the stochastic paradigm. As a result, there have been few attempts to confront the new challenges in linguistics from the natural language processing approach. The goal of this chapter is to introduce the theoretical foundation underlying ARTEMIS, a knowledge-based system which is intended to simulate natural language understanding in the framework of Role and Reference Grammar. More specifically, we will focus on how to enhance this functional model in order to make argumental constructions play a decisive role in the computational analysis of the deep semantics in the text.

Patent
27 Mar 2013
TL;DR: In this article, a man-machine interactive spoken dialogue system consisting of a speech recognizing module, an error correcting module, a natural language understanding module and a dialogue managing module is presented.
Abstract: The invention discloses a man-machine interactive spoken dialogue system. The man-machine interactive spoken dialogue system comprises a speech recognizing module, an error correcting module, a natural language understanding module, a dialogue managing module, a natural language generating module and a speech synthesizing module, wherein the speech recognizing module is used for recognizing speech of a user into words, the error correcting module is used for correcting morphological and grammatical errors of the words output by the speech recognizing module, the natural language generating module is used for recognizing the words with error corrected by the error collecting module into semanteme, the dialogue managing module is used for generating dialogue semanteme according to the semanteme generated by the natural language generating module, the natural language generating module is used for generating dialogue words from the dialogue semanteme output by the dialogue managing module, and the speech synthesizing module is used for generating dialogue speech from the dialogue words generated by the natural language generating module. The invention further discloses a realizing method of the man-machine interactive spoken dialogue system. The man-machine interactive spoken dialogue system is capable of answering questions of a user and actively talking about relative topics with the user, so that a real spoken dialogue language environment is created.

Posted Content
TL;DR: This paper is an investigation on how to initiate research in WSD for under-resourced languages by applying Word Sense Induction (WSI) and suggests some interesting topics to focus on.
Abstract: Word Sense Disambiguation (WSD), the process of automatically identifying the meaning of a polysemous word in a sentence, is a fundamental task in Natural Language Processing (NLP). Progress in this approach to WSD opens up many promising developments in the field of NLP and its applications. Indeed, improvement over current performance levels could allow us to take a first step towards natural language understanding. Due to the lack of lexical resources it is sometimes difficult to perform WSD for under-resourced languages. This paper is an investigation on how to initiate research in WSD for under-resourced languages by applying Word Sense Induction (WSI) and suggests some interesting topics to focus on.

Journal ArticleDOI
TL;DR: As an exercise for the language learner, a computerized adventure game has much to offer, and commercial examples in English exhibit impressive language- handling abilities as well as intriguing plots.
Abstract: As an exercise for the language learner, a computerized adventure game has much to offer. Commercial examples in English exhibit impressive language- handling abilities as well as intriguing plots. Our list of the features such a program would have, if modified for instructional purposes, is followed by a description of our work to date on such a project.

01 Jan 2013
TL;DR: A more effective and efficient way to marshal inferences from background knowledge to facilitate deep natural language understanding is developed and implemented on real text.
Abstract: We have recently begun a project to develop a more effective and efficient way to marshal inferences from background knowledge to facilitate deep natural language understanding. The meaning of a word is taken to be the entities, predications, presuppositions, and potential inferences that it adds to an ongoing situation. As words compose, the minimal model in the situation evolves to limit and direct inference. At this point we have developed our computational architecture and implemented it on real text. Our focus has been on proving the feasibility of our design.

Proceedings Article
14 Jul 2013
TL;DR: USI Answers-a natural language question answering system for semi-structured industry data that allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation is described.
Abstract: This paper describes USI Answers-a natural language question answering system for semi-structured industry data. The paper reports on the progress towards the goal of offering easy access to enterprise data to a large number of business users, most of whom are not familiar with the specific syntax or semantics of the underlying data sources. Additional complications come from the nature of the data, which comes both as structured and unstructured. The proposed solution allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation. The application is in use by more than 1500 users from Siemens Energy. We evaluate our approach on a data set consisting of fleet data.

Book ChapterDOI
09 Jul 2013
TL;DR: Tractor as discussed by the authors is a system for understanding English messages within the context of hard and soft information fusion for situation assessment, which processes a message through syntactic processors, and represents the result in a formal knowledge representation language.
Abstract: Tractor is a system for understanding English messages within the context of hard and soft information fusion for situation assessment. Tractor processes a message through syntactic processors, and represents the result in a formal knowledge representation language. The result is a hybrid syntactic-semantic knowledge base that is mostly syntactic. Tractor then adds relevant ontological and geographic information. Finally, it applies hand-crafted syntax-semantics mapping rules to convert the syntactic information into semantic information, although the final result is still a hybrid syntactic-semantic knowledge base. This paper presents the various stages of Tractor's natural language understanding process, with particular emphasis on discussions of the representation used and of the syntax-semantics mapping rules.

Journal ArticleDOI
TL;DR: A theoretical framework for metaphor understanding based on the embodied mechanism of concept inquiry is proposed, and ontology is introduced as the knowledge representation method in metaphor understanding, and metaphor mapping is formulated as ontology mapping.
Abstract: Language understanding is one of the most important characteristics for human beings. As a pervasive phenomenon in natural language, metaphor is not only an essential thinking approach, but also an ingredient in human conceptual system. Many of our ways of thinking and experiences are virtually represented metaphorically. With the development of the cognitive research on metaphor, it is urgent to formulate a computational model for metaphor understanding based on the cognitive mechanism, especially with the view to promoting natural language understanding. Many works have been done in pragmatics and cognitive linguistics, especially the discussions on metaphor understanding process in pragmatics and metaphor mapping representation in cognitive linguistics. In this paper, a theoretical framework for metaphor understanding based on the embodied mechanism of concept inquiry is proposed. Based on this framework, ontology is introduced as the knowledge representation method in metaphor understanding, and metaphor mapping is formulated as ontology mapping. In line with the conceptual blending theory, a revised conceptual blending framework is presented by adding a lexical ontology and context as the fifth mental space, and a metaphor mapping algorithm is proposed.

Journal ArticleDOI
TL;DR: The paper addresses the need for an ontology- and meaning-based approach for natural-language-understanding and information-processing computational systems and introduces a specific approach, the Ontological Semantic Technology, and several aspects of meaning representation are addressed in its terms.

Patent
07 Nov 2013
TL;DR: In this article, an arrangement and corresponding method for distributed natural language processing is described, where a set of local data sources is stored on a mobile device and a local natural language understanding (NLU) match module is used on the mobile device to determine one or more local interpretation candidates.
Abstract: An arrangement and corresponding method are described for distributed natural language processing. A set of local data sources is stored on a mobile device. A local natural language understanding (NLU) match module on the mobile device performs natural language processing of a natural language input with respect to the local data sources to determine one or more local interpretation candidates. A local NLU ranking module on the mobile device processes the local interpretation candidates and one or more remote interpretation candidates from a remote NLU server to determine a final output interpretation corresponding to the natural language input.

Proceedings ArticleDOI
04 Nov 2013
TL;DR: The modeling of a methodology based on stochastic Petri-nets (SPN) to explain the transformation of a natural language (NL) sentence into a state machine representation as stated in [16].
Abstract: Natural language processing and understanding is an attractive field and many techniques and tools for document processing have been developed. Most of the techniques use either statistical models or graph-based approaches. Here we present the modeling of a methodology based on stochastic Petri-nets (SPN) to explain the transformation of a natural language (NL) sentence into a state machine representation as stated in [16]. In particular, we initially convert NL sentences into graphs using the (Agent → Action → Patient) kernel and then we convert the graphs into SPN graph descriptions in order to efficiently offer a model of semantically represent and understand natural language events of a document. The selection of the SPN graph model is due to its capability for efficiently representing structural and functional knowledge.

Patent
11 Mar 2013
TL;DR: In this article, a human-machine dialogue system is described which has multiple computer-implemented dialogue components, including an automatic speech recognition (ASR) engine and a natural language understanding (NLU) engine.
Abstract: A human-machine dialogue system is described which has multiple computer-implemented dialogue components. A user client delivers output prompts to a human user and receives dialogue inputs including speech inputs from the human user. An automatic speech recognition (ASR) engine processes the speech inputs to determine corresponding sequences of representative text words. A natural language understanding (NLU) engine processes the text words to determine corresponding semantic interpretations. A dialogue manager (DM) generates the output prompts and responds to the semantic interpretations so as to manage a dialogue process with the human user. The dialogue components share context information with each other using a common context sharing mechanism such that the operation of each dialogue component reflects available context information.

Patent
27 Nov 2013
TL;DR: In this paper, the authors present a semi-supervised or unsupervised method for building classifiers in semi-and un-supervision manner using a human-generated map which identifies categories of transcriptions.
Abstract: Disclosed herein are systems, methods, and computer-readable storage devices for building classifiers in a semi-supervised or unsupervised way. An example system implementing the method can receive a human-generated map which identifies categories of transcriptions. Then the system can receive a set of machine transcriptions. The system can process each machine transcription in the set of machine transcriptions via a set of natural language understanding classifiers, to yield a machine map, the machine map including a set of classifications and a classification score for each machine transcription in the set of machine transcriptions. Then the system can generate silver annotated data by combining the human-generated map and the machine map. The algorithm can include different branches for when the machine transcription is available, when partial results are available, when no results are found for the machine transcription, and so forth.

Patent
28 Aug 2013
TL;DR: In this paper, an utterance audio data is partitioned into multiple portions, and incremental speech recognition results may be generated from one or more of the portions, which are then used to determine a user's intent from the utterance.
Abstract: Incremental speech recognition results are generated and used to determine a user's intent from an utterance. Utterance audio data may be partitioned into multiple portions, and incremental speech recognition results may be generated from one or more of the portions. A natural language understanding module or some other language processing module can generate semantic representations of the utterance from the incremental speech recognition results. Stability of the determined intent may be determined over the course of time, and actions may be taken in response to meeting certain stability thresholds.

Journal ArticleDOI
TL;DR: The Indonesian Mind Map Generator 1 aims to help the user in easily making a Mind Map object by employing several Indonesian natural language understanding tools such as Indonesian POS Tagger, Indonesian Syntactic Parser, and Indonesian Semantic Analyzer, which is devised to alleviate the low availability of Indonesian language resources.
Abstract: Here, we describe our work in developing Indonesian Mind Map Generator that employs several Indonesian natural language understanding tools as its main engine. The Indonesian Mind Map Generator 1 aims to help the user in easily making a Mind Map object. The system consists of several Indonesian natural language understanding tools such as Indonesian POS Tagger, Indonesian Syntactic Parser, and Indonesian Semantic Analyzer. The methods used for developing each of Indonesian natural language understanding tools are devised to such an extend that they are enable to alleviate the low availability of Indonesian language resources. For Indonesian POS Tagger, we employed HMM and subsequently enhanced the result by using affix tree. As for the Indonesian Syntactic Parser, we compared the performance of CYK and Earley parser, which are known as common dynamic algorithms in PCFG. The Indonesian Semantic Analyzer consists of several components such as lexical semantic attachment, reference resolution, and Semantic Analyzer itself that transforms the parse tree result into first order logic representation. In our work, instead of using a rich resource on semantic information for each vocabulary, we defined several rules for the lexical semantic attachment based on POS Tags and certain words. Finally, to develop the Mind Map generator, we used the radial drawing method to visualize the first order logic representation and we also built a Mind Map editor to allow a user in modifying the Mind Map result. To evaluate the result, we conducted the experiments for each component mentioned previously. The POS Tagger accuracy achieved 96.5%, the Syntactic Parser achieved accuracy of 47.22%, and the Semantic Analyzer achieved accuracy of 62.5%. The final result of Mind Map object was evaluated by 5 respondents. The results of evaluationshowed that, for the simple sentence, the Mind Map object can be easily understood. 1. Background Nowadays, many education systems employ Mind Map symbols in explaining concepts that can be understood easily by the students. The idea of Mind Map is to use picture and color combination, which is compatible with how the brain works(1). Since Mind Map is a popular concept, people try to develop Mind Map editors to help the other sin drawing a Mind Map. One of the drawbacks is that, in these Mind Map editors, user has to draw the object from scratch, which can demotivate the user to start using the Mind Map editor. To handle such problems, several researches proposed a Mind Map generator tool to help the user in preparing the Mind Map object. By using a Mind Map generator tool, one doesn't have to draw the Mind Map object from scratch. User can edit the result of Mind Map generator tool and shorten the effort to draw the Mind Map object. Unfortunately, the Mind Map generator tool is only available for English text(2)(3). In English Mind Map generator, the basic approach is to employ natural language understanding tool in transforming English text into other representations such as syntactical representation or semantic representation. There was no research or product on developing Mind Map generator for Indonesian language. In the recent years, there have been several works on developing 1 The application can be accessed at http://mindmap.kataku.org

Proceedings ArticleDOI
12 Feb 2013
TL;DR: Using a publicly available WOZ tool, the integration of existing language technologies with a human wizard may help in designing a natural user inter- face for seniors and how such has the potential to underpin an iterative user-centred development process for language- based applications.
Abstract: This research aims at providing Voice controlled As- sistive (vAssist) Care and Communication Services for the Home to seniors suffering from fine-motor problems and/or chronic diseases. The constantly growing life expectancy of the European population increasingly asks for techno- logical products that help seniors to manage their activities of daily living. In particular, we require solutions which offer interaction paradigms that fit the cognitive abilities of elderly users. Natural language-based access can be seen as one way of increasing the usability of these services. Yet, the construction of robust language technologies such as Automatic Speech Recognition and Natural Language Understanding does require sufficient domain specific in- teraction data. In this paper we describe how we plan to obtain the relevant corpus data for a set of different applica- tion scenarios, using the Wizard of Oz (WOZ) prototyping method. Using a publicly available WOZ tool we discuss how the integration of existing language technologies with a human wizard may help in designing a natural user inter- face for seniors and how such has the potential to underpin an iterative user-centred development process for language- based applications.

Proceedings ArticleDOI
28 Oct 2013
TL;DR: The results show that natural language SDS could lead to a faster and more intuitive way of interacting with in-vehicle SDS and US and Chinese users especially preferred the natural language enabled system over the command and control system.
Abstract: An in-vehicle speech dialog system (SDS) can support visualhaptic interfaces and reduce eyes-off-road time while driving. This work evaluates two SDS that varied according to the degree of natural language understanding afforded by the speech dialog system. In a Wizard of Oz simulation, two alternative SDSs were tested in a driving simulator. The Lane Change Test was used to compare a command and control system with a system supporting natural language input. This driving simulator study was conducted using the same setup in Germany, USA, and China. 40 participants per country were instructed to perform interaction tasks from contexts like media, telephone, and navigation. The results show that natural language SDS could lead to a faster and more intuitive way of interacting with in-vehicle SDS. US and Chinese users especially preferred the natural language enabled system over the command and control system.

Book ChapterDOI
01 Jan 2013
TL;DR: In this paper, a computational cognitive modeling-inspired decomposition of the Turing test as classical "strong AI benchmark" is proposed, with the objective of evaluating human-style rationality, creativity-related capacities, and natural language understanding.
Abstract: After a short assessment of the idea behind the Turing Test, its actual status and the overall role it played within AI, I propose a computational cognitive modeling-inspired decomposition of the Turing test as classical “strong AI benchmark” into at least four intermediary testing scenarios: a test for natural language understanding, an evaluation of the performance in emulating human-style rationality, an assessment of creativity-related capacities, and a measure of performance on natural language production of an AI system I also shortly reflect on advantages and disadvantages of the approach, and conclude with some hints and proposals for further work on the topic