WorldCat Identities

Ingria, Robert

Overview
Works: 12 works in 22 publications in 1 language and 22 library holdings
Genres: Periodicals 
Roles: Editor
Publication Timeline
.
Most widely held works by Robert Ingria
The Delphi Natural Language Understanding System( Book )

2 editions published in 1994 in English and held by 2 WorldCat member libraries worldwide

This paper presents Delphi, the natural language component of the BBN Spoken Language System. Delphi is a domain- independent natural language question answering system that is solidly based on linguistic principles, yet which is also robust to ungrammatical input. It includes a domain-independent, broad-coverage grammar of English. Analysis components include an agenda-based best-first parser and a fallback component for partial understanding that works by fragment combination. Delphi has been formally evaluated in the ARPA Spoken Language program's ATIS (Airline Travel Information System) domain, and has performed well. Delphi has also been ported to a spoken language demonstration system in an Air Force Resource Management domain. We discuss results of the evaluation as well as the porting process
BBN: Description of the PLUM System as Used for MUC-6( Book )

2 editions published in 1995 in English and held by 2 WorldCat member libraries worldwide

This paper provides a quick summary of our technical approach, which has been developing since 1991 and was first fielded in MUC-3. First a quick review of what is new is provided, then a walk through of system components. Perhaps most interesting is out analysis, following the walk through, of what we learned through MUC-6 and of what directions we would take now to break the performance barriers of current information extraction technology
BBN: Description of the PLUM System as Used for MUC-4( Book )

2 editions published in 1992 in English and held by 2 WorldCat member libraries worldwide

Traditional approaches to the problem of extracting data from texts have emphasized hand-rafted linguistic knowledge. In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed as part of a DARPA-funded research effort on integrating probabilistic language models with more traditional linguistic techniques. Our research and development goals are * more rapid development of new applications, * the ability to train (and re-train) systems based on user markings of correct and incorrect output, * more accurate selection among interpretations when more than one is found, and * more robust partial interpretation when no complete interpretation can be found. A central assumption of our approach is that in processing unrestricted text for data extraction, a non-trivial amount of the text will not be understood. As a result, all components of PLUM are designed to operate on partially understood input, taking advantage of information when available, and not failing when information is unavailable. We had previously performed experiments on components of the system with texts from the Wall Street Journal, however, the MUC-3 task was the first end-to-end application of PLUM. Very little hand-tuning of knowledge bases was done for MUC-4; since MUC-3, the system architecture as depicted in figure 1 has remained essentially the same. In addition to participating in MUC-4, since MUC-3 we focused on porting to new domains and a new language, and on performing various experiments designed to control recall/precision tradeoffs. To support these goals, the preprocessing component and the fragment combiner were made declarative; the semantics component was generalized to use probabilities on word senses; we expanded our treatment of reference; we enlarged the set of system parameters at all levels; and we created a new probabilistic classifier for text relevance which filters discourse events
BBN PLUM: MUC-4 Test Results and Analysis( Book )

2 editions published in 1992 in English and held by 2 WorldCat member libraries worldwide

Our mid-term to long-term goals in data extraction from text for the next one to three years are to achieve much greater portability to new languages and new domains, greater robustness, and greater scalability. The novel aspect to our approach is the use of learning algorithms and probabilistic models to learn the domain-specific and language. specific knowledge necessary for a new domain and new language. Learning algorithms should contribute to scalability by making it feasible to deal with domains where it would be infeasible to invest sufficient human effort to bring a system up. Probabilistic models can contribute to robustness by allowing for words, constructions, and forms not anticipated ahead of time and by looking for the most likely interpretation in context. We began this research agenda approximately two years ago. During the last twelve months, we have focused much of our effort on porting our data extraction system (PLUM) to a new language (Japanese) and to two new domains. During the next twelve months, we anticipate porting PLUM to two or three additional domains. For any group to participate in MUC is a significant investment. To be consistent with our mid-term and long- term goals, we imposed the following constraints on ourselves in participating in MUC-4: * We would focus our effort on semi-automatically acquired knowledge. * We would minimize effort on handcrafted knowledge, and most generally. * We would minimize MUC-specific effort. Though the three self-imposed constraints meant our overall scores on the objective evaluation were not as high as if we had focused on handtuning and handcrafting the knowledge bases, MUC-4 became a vehicle for evaluating our progress on the long-term goals
BBN BYBLOS and HARC February 1992 ATIS Benchmark Results( Book )

2 editions published in 1992 in English and held by 2 WorldCat member libraries worldwide

We present results from the February '92 evaluation on the ATIS travel planning domain for HARC, the BBN spoken language system (SLS). In addition, we discuss in detail the individual performance of BYBLOS, the speech recognition (SPREC) component. In the official Scoring, conducted by NIST, BBN's HARC system produced a weighted SLS score of 43.7 on all 687 evaluable utterances in the test set. This was the lowest error achieved by any of the 7 systems evaluated. For the SPREC evaluation BBN's BYBLOS system achieved a word error rate of 6.2% on the same 687 utterances and 9.4% on the entire test set of 971 utterances. These results were significantly better than any other speech system evaluated
BBN PLUM: MUC-3 Test Results and Analysis( Book )

2 editions published in 1991 in English and held by 2 WorldCat member libraries worldwide

Perhaps the most important facts about our participation in MUC-3 reflect our starting point and goals. In March, 1990, we initiated a pilot study on the feasibility and impact of applying statistical algorithms in natural language processing. The experiments were concluded in March, 1991 and lead us to believe that statistical approaches can effectively improve knowledge-based approaches [Weishedel, et al., 1991a, Weischedel, Meteer, and Schwartz, 1991]. Due to nature of that effort, we had focused on many well-defined algorithm experiments. We did not have a complete message processing system; nor was the pilot study designed to create an application system. For the Phase I evaluation, we supplied a module to New York University. At the time of the Phase I Workshop (12-14 February 1991) we decided to participate in MUC with our own entry. The Phase I Workshop provided invaluable insight into what other sites were finding successful in this particular application. On 25 February, we started an intense effort not just to be evaluated on the FBIS articles, but also to create essential components (e.g., discourse component and template generator) and to integrate all components into a complete message processing system. Although the timing of the Phase II test (6-12 May) was hardly ideal for evaluating our site's capabilities, it was ideally timed to serve as a benchmark prior to starting a four year plan for research and development in message understanding. Because of this, we were determined to try alternatives that we believed would be different than those employed by other groups, wherever time permitted. These are covered in the next section. Our results were quite positive, given these circumstances. Our max-tradeoff version achieved 45% recall and 52% precision with 22% overgenerating (See Figure 2). PLUM can be run in several modes, trading off recall versus precision and overgeneration
A New Approach to Text Understanding( Book )

2 editions published in 1992 in English and held by 2 WorldCat member libraries worldwide

This paper first briefly describes the architecture of PLUM, BBN's text processing system, and then reports on some experiments evaluating the effectiveness of the design at the component level. Three features are unusual in PLUM's architecture: a domain independent deterministic parser, processing of (the resulting) fragments at the semantic and discourse level, and probabilistic models
BBN: Description of the PLUM System as Used for MUC-5( Book )

2 editions published in 1993 in English and held by 2 WorldCat member libraries worldwide

Traditional approaches to the problem of extracting data from texts have emphasized hand-crafted linguistic knowledge. In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed as part of an ARPA-funded research effort on integrating probabilistic language models with more traditional linguistic techniques. Our research and development goals are: * more rapid development of new applications, * the ability to train (and re-train) systems based on user markings of correct and incorrect output, * more accurate selection among interpretations when more than one is found, and * more robust partial interpretation when no complete interpretation can be found. We began this research agenda approximately three years ago. During the past two years, we have evaluated much of our effort in porting our data extraction system (PLUM) to a new language (Japanese) and to two new domains. Three key design features distinguish PLUM: statistical language modeling, learning algorithms and partial understanding. The first key feature is the use of statistical modeling to guide processing. For the version of PLUM used in MUC-5, part of speech information was determined by using well-known Markov modeling techniques embodied in BBN's part-of-speech tagger POST [5]. We also used a correction model, AMED [3], for improving Japanese segmentation and part-of-speech tags assigned by JUMAN. For the microelectronics domain, we used a probabilistic model to help identify the role of a company in a capability (whether it is a developer, user, etc.). Statistical modeling in PLUM contributes to portability, robustness, and trainability. The second key feature is our use of learning algorithms both to obtain the knowledge bases used by PLUM's processing modules and to train the probabilistic algorithms. A third key feature is partial understanding. All components of PLUM are designed to operate on partially interpretable input
The BBN Spoken Language System( Book )

2 editions published in 1989 in English and held by 2 WorldCat member libraries worldwide

We describe HARC, a system for speech understanding that integrates speech recognition techniques with natural language processing. The integrated system uses statistical pattern recognition to build a lattice of potential words in the input speech. This word lattice is passed to a unification parser to derive all possible associated syntactic structures for these words. The resulting parse structures are passed to a multi-level semantics component for interpretation
BBN: Description of the PLUM System as Used for MUC-3( Book )

2 editions published in 1991 in English and held by 2 WorldCat member libraries worldwide

Traditional approaches to the problem of extracting data from texts have emphasized handcrafted linguistic knowledge. In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed as part of a DARPA-funded research effort on integrating probabilistic language models with more traditional linguistic techniques. Our research and development goals are * more rapid development of new applications, * the ability to train (and re-train) systems based on user markings of correct and incorrect output, * more accurate selection among interpretations when more than one is found, and * more robust partial interpretation when no complete interpretation can be found. We have previously performed experiments on components of the system with texts from the Wall Street Journal, however, the MUC-3 task is the first end-to-end application of PLUM. MI components except parsing were developed in the last 5 months, and cannot therefore be considered fully mature. The parsing component, the MIT Fast Parser [4], originated outside BBN and has a more extensive history prior to MUC-3. A central assumption of our approach is that in processing unrestricted text for data extraction, a non-trivial amount of the text will not be understood. As a result, all components of PLUM are designed to operate on partially understood input, taking advantage of information when available, and not failing when information is unavailable
New feeling( )

in English and held by 1 WorldCat member library worldwide

Early Talking Heads fanzine
Adaptive Natural Language Processing( Book )

1 edition published in 1991 in English and held by 1 WorldCat member library worldwide

A handful of special purpose systems have been successfully deployed to extract prespecified kinds of data from text. The limitation to widespread deployment of such systems is their assumption of a large volume of handcrafted, domain-dependent, and language-dependent knowledge in the form of rules. A new approach is to add automatically trainable probabilistic language models to linguistically based analysis. This offers several potential advantages: (1) Trainability by finding patterns in a large corpus, rather than handcrafting such patterns. (2) Improvability be re-estimating probabilities based on a user marking correct and incorrect output on a test set. (3) More accurate selection among interpretations when more than one is produced. (4) Robustness by finding the most likely partial interpretation when no complete interpretation can be found
 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  Kids General Special  
Audience level: 0.95 (from 0.82 for New feelin ... to 0.99 for Adaptive N ...)

Languages
English (22)