Articles

This paper describes Picky, a probabilistic agenda-based chart parsing algorithm which uses a technique called prob- abilistic prediction to predict which grammar rules are likely to lead to an acceptable parse of the input. In tests on ran- domly selected test data, "Picky generates fewer edges on av- erage than …...

We describe work which uses decision trees to estimate marginal probabilities in a maximum entropy model for pre- dicting the part-of-speech of a word given the context in which it appears. Two experiments are presented which ex- hibit improvements over the usual hidden Markov model ap- proach. 1....

Automatic part of speech tagging is an area of natural lan- guage processing where statistical techniques have been more successful than rule-based methods. In this paper, we present a simple rule-based part of speech tagger which automati- cally acquires its rules and tags with accuracy comparable to stochastic taggers. The …...

We describe two attempt to improve our stochastic language models. In the first, we identify a systematic overestimation in the traditional backoff model, and use statisticalreasoning to correct it. Our modifi- cation results in up to 6% reduction in the perplexity of various tasks. Although the improvement is modest, it …...

We present an algorithm to adapt a n-gram language model to a document as it is dictated. The observed partial document is used to esti- mate a unigram distribution for the words that already occurred. Then, we find the closest n- gram distribution to the static n.gram distribu- tion (using …...

We describe the results that SRI International achieved on the February 1992 ATIS Speech and Natural Language Sys- tem Test. The basic architecture of the system is described, including a set of parameters capable of altering the system's behavior and processing strategy. We report on several ex- periments that were …...

This paper describes three relatively domain-independent ca- pabilities recently added to the Paramax spoken language un- derstanding system: non-monotonic reasoning, implicit refer- ence resolution, and database query paraphrase. In addition, we discuss the results of the February 1992 ATIS benchmark tests. We describe a variation on the standard evaluation metric …...

This paper describes the status of the MIT ATIS system as of February 1992, focusing especially on the changes made to the SUMMIT recognizer. These include context-dependent phonetic modelling, the use of a bigram language model in conjunction with a probabilistic LR parser, and refinements made to the lexicon. Together …...

The speech understanding system we propose in this paper is based on the stochastic modeling of a sentence as a sequence of elemental units that represent its meaning. According to this paradigm, the original meaning of a sentence, can be decoded using a dynamic programming algorithm, although the small amount …...

3. THE WIZARD This paper presents SRU's first experiences collecting un- scripted speech data using the 'Wizard of Oz' technique to provide a genuine telephone-based route planning service. Although only a limited quantity of data has been collected so far, several valuable insights into the nature of future speech- based …...

The paper provides an overview of the research conducted at LIMSI in the field of speech processing, but also in the related ar- eas of Human-Machine Communication, including Natural Lan- guage Processing, Non Verbal and Multimodal Communication. Also presented are the commercial applications of some of the re- search projects. …...

This paper describes the AT&T ATIS data collection system, with emphasis on the development of the speech-in, speech- out interaction paradigm. The ATIS task involves providing air travel information to a user in the context of a interactive dialogue. Under the AT&T interaction paradigm, informa- tion retrieved from a travel …...

The DARPA Spoken Language effort has profited greatly from its emphasis on tasks and common evaluation metrics. Common, standardized evaluation procedures have helped the community to focus research effort, to measure progress, and to encourage com- munication among participating sites. The task and the evaluation metrics, however, must be consistent …...

As the DARPA spoken language community moves to- wards developing useful systems for interactive problem solv- ing, we must explore alternative evaluation procedures that measure whether these systems aid people in solving problems within the task domain. In this paper, we describe several experiments exploring new evaluation procedures. To look …...

We have analyzed three factors affecting user satisfaction and system performance using an SLS implemented in the ATIS domain. We have found that: (I) trade-offs between speed and accuracy have different implications for user sat- isfaction; (2) recognition performance improves over time, at least in part because of a reduction …...

This paper describes a recently collected spoken language cor- pus for the ATIS (Air Travel Information System) domain. This data collection effort has been co-ordinated by MAD- COW (Multi-site ATIS Data COllection Working group). We summarize the motivation for this effort, the goals, the imple- mentation of a multi-site data …...

Analysis of a corpus of queries to a statistical database has shown considerable variation in the location and order of modifiers in complex noun phrases. Never- theless, restrictions can be defined on nominal mod- ification because of certain correspondences between nominal modifiers and the role they fulfill in a statisti- …...

Most of tile research on parsing natnral [allguages has beetl concerned with I",nglish, or wil, h other languages nlOrl)hologically similar Io English. Parsing agglntinat.ive word st, ructures ha.s altracted relatively little attcnl;ion most probal~ly becanse agghlfinatiw? lallgllages COlll~aill word s/ructtlres of considerable complexity, and parsing WOrdS ill Stlch languages I'(?(llliros …...

In this paper global patterns of thematic text organization me considered within the framework of a distributed model of text understmlding, ttased on file parsing resuhs of prior lext cohe- sioll analysis, specialized text grammar modules deternfine whether SOllle well-defined text lllltCro organization palteln is cOlll])ulabte flOlll the available text …...

This paper proposes a generation method for feature-structured)ased unification grammars. As comlx~red with fixed ~rity term notation, fea- ture structure notation is more tlexible for repre- senting knowledge needed to generate idiom~ttic structures as well as genem~l constructions. The method enables feature strncture retrieval via nmltiple indices. The indexing mechanism, …...