Jan Kleindienst

Bio: Jan Kleindienst is an academic researcher from IBM. The author has contributed to research in topics: Dialog system & Dialog box. The author has an hindex of 26, co-authored 96 publications receiving 3507 citations. Previous affiliations of Jan Kleindienst include Nuance Communications.

Systems and methods for implementing modular DOM (Document Object Model)-based multi-modal browsers

Abstract: Systems and methods for building multi-modal browsers applications and, in particular, to systems and methods for building modular multi-modal browsers using a DOM (Document Object Model) and MVC (Model-View-Controller) framework that enables a user to interact in parallel with the same information via a multiplicity of channels, devices, and/or user interfaces, while presenting a unified, synchronized view of such information across the various channels, devices and/or user interfaces supported by the multi-modal browser. The use of a DOM framework (or specifications similar to DOM) allows existing browsers to be extended without modification of the underling browser code. A multi-modal browser framework is modular and flexible to allow various fat client and thin (distributed) client approaches.

Text Understanding with the Attention Sum Reader Network

Abstract: Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these datasets, the associated text comprehension task is well suited for deep-learning techniques that currently seem to outperform all alternative approaches. We present a new, simple model that uses attention to directly pick the answer from the context as opposed to computing the answer using a blended representation of words in the document as is usual in similar models. This makes the model particularly suitable for question-answering problems where the answer is a single word from the document. Ensemble of our models sets new state of the art on all evaluated datasets.

Text Understanding with the Attention Sum Reader Network

Abstract: Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these datasets, the associated text comprehension task is well suited for deep-learning techniques that currently seem to outperform all alternative approaches. We present a new, simple model that uses attention to directly pick the answer from the context as opposed to computing the answer using a blended representation of words in the document as is usual in similar models. This makes the model particularly suitable for question-answering problems where the answer is a single word from the document. Ensemble of our models sets new state of the art on all evaluated datasets.

Systems and methods for providing conversational computing via javaserver pages and javabeans

Abstract: A new application programming language is provided which is based on user interaction with any device which a user is employing to access any type of information. The new language is referred to herein as a “Conversational Markup Language (CML). In a preferred embodiment, CML is a high level XML based language for representing “dialogs” or “conversations” the user will have with any given computing device. For example, interaction may comprise, but is not limited to, visual based (text and graphical) user interaction and speech based user interaction. Such a language allows application authors to program applications using interaction-based elements referred to herein as “conversational gestures.” The present invention also provides for various embodiments of a multimodal browser capable of supporting the features of CML in accordance with various modality specific representations, e.g., HTML based graphical user interface (GUI) browser, VoiceXML based speech browser, etc.

Command boundary identifier for conversational natural language

Abstract: An apparatus for automatically identifying command boundaries in a conversational natural language system, in accordance with the present invention, includes a speech recognizer for converting an input signal to recognized text and a boundary identifier coupled to the speech recognizer for receiving the recognized text and determining if a command is present in the recognized text, the boundary identifier outputting the command if present in the recognized text. A method for identifying command boundaries in a conversational natural language system is also included.

Bidirectional Attention Flow for Machine Comprehension

Abstract: Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use attention to focus on a small portion of the context and summarize it with a fixed-size vector, couple attentions temporally, and/or often form a uni-directional attention. In this paper we introduce the Bi-Directional Attention Flow (BIDAF) network, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization. Our experimental evaluations show that our model achieves the state-of-the-art results in Stanford Question Answering Dataset (SQuAD) and CNN/DailyMail cloze test.

Intelligent Automated Assistant

Abstract: An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset.

Abstract: This paper presents our recent work on the design and development of a new, large scale dataset, which we name MS MARCO, for MAchine Reading COmprehension. This new dataset is aimed to overcome a number of well-known weaknesses of previous publicly available datasets for the same task of reading comprehension and question answering. In MS MARCO, all questions are sampled from real anonymized user queries. The context passages, from which answers in the dataset are derived, are extracted from real web documents using the most advanced version of the Bing search engine. The answers to the queries are human generated. Finally, a subset of these queries has multiple answers. We aim to release one million queries and the corresponding answers in the dataset, which, to the best of our knowledge, is the most comprehensive real-world dataset of its kind in both quantity and quality. We are currently releasing 100,000 queries with their corresponding answers to inspire work in reading comprehension and question answering along with gathering feedback from the research community.

Method and system for enabling connectivity to a data system

Abstract: A method and system that provides filtered data from a data system (16). In one embodiment that system includes an API (application programming interface) and associated software modules to enable third party applications to access an enterprise data system. Administrators are enabled to select specific user interface (UI) objects (72), such as screens, views, applets, columns and fields to voice or pass-through enable via a GUI (108) that presents a tree depicting a hierarchy of the UI objects (72) within a user interface of an application (14). An XSLT style sheet is then automatically generated to filter out data pertaining to UI objects (72) that were not voice or pass-through enabled. In response to a request for data, unfiltered data are retrieved from the data system and a specified style sheet is applied to the unfiltered data to return filtered data pertaining to only those fields and columns that are voice or pass-through enabled.

Systems and methods for responding to natural language speech utterance

Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.