This article describes three statistical models for natural language parsing. The models extend methods from probabilistic context-free grammars to lexicalized grammars, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree. Independence assumptions then lead to parameters that encode the X-bar schema, subcategorization, ordering of complements, placement of adjuncts, bigram lexical dependencies, wh-movement, and preferences for close attachment. All of these preferences are expressed by probabilities conditioned on lexical heads. The models are evaluated on the Penn Wall Street Journal Treebank, showing that their accuracy is competitive with other models in the literature. To gain a better understanding of the models, we also give results on different constituent types, as well as a breakdown of precision/recall results in recovering various types of dependencies. We analyze various characteristics of the models through experiments on parsing accuracy, by collecting frequencies of various structures in the treebank, and through linguistically motivated examples. Finally, we compare the models to others that have been applied to parsing the treebank, aiming to give some explanation of the difference in performance of the various models

The last decade has witnessed the emergence of a new breed of human computer interfaces that combines several human language technologies to enable information access and transactional processing using spoken dialogue. In this paper, I discuss my view on the research issues involved in the development of such interfaces, describe the recent work done in this area at the MIT Laboratory for Computer Science, and outline some of the unmet research challenges, including the need to work in real domains, spoken language generation, and portability across domains and languages.

SpeechBuilder is a suite of tools that helps facilitate the creation of mixed-initiative spoken dialogue systems for both novice and experienced developers of human language applications. SpeechBuilder employs intuitive methods of specification to allow developers to create human language interfaces to structured information stored in a relational database, or to control- and transaction-based applications. The goal of this project has been both to robustly accommodate the various scenarios where spoken dialogue systems may be needed, and to provide a stable and reliable infrastructure for design and deployment of applications. SpeechBuilder has been used in various spoken language domains, including a directory of the people working at the MIT Laboratory for Computer Science, an application to control the various physical items in a typical office environment, and a system for real-time weather information access.

In early 1997, our group initiated a project to develop jupiter, a conversational interface that allows users to obtain worldwide weather forecast information over the telephone using spoken dialogue. It has served as the primary research platform for our group on many issues related to human language technology, including telephonebased speech recognition, robust language understanding, language generation, dialogue modelling, and multilingual interfaces. Over a two year period since coming on line in May 1997, jupiter has received, via a toll-free number in North America, over 30,000 calls (totalling over 180,000 utterances), mostly from naive users. The purpose of this paper is to describe our development effort in terms of the underlying human language technologies as well as other system related issues such as utterance rejection and content harvesting. We will also present some evaluation results on the system and its components.

Galaxy-ii is the designated initial common architecture for the DARPA Communicator project in the U.S. Its key feature is the ability to control system integration via a run-time executable scripting language. This paper describes our experience in developing complex systems based on the galaxy-ii framework. Our current system consists of four domains and two languages #English and Mandarin#. Users can interface with the system in both displayful and displayless modes. Users can switch freely among the various domains in a single conversation, and multiple users can access the system in simultaneous conversations. In addition to the hub script that controls liveinteraction with users, wehave also con#gured many other hub scripts that permit various batchmode runs, including the capability to reprocess log #les through improved versions of the system to measure progress. The hub scripting capability has greatly accelerated our pace of system development, and has allowed us to con#gure c...

In developing telephone-based conversational systems, we foresee future systems capable of supporting multiple domains and flexible vocabulary. Users can pursue several topics of interest within a single telephone call, and the system is able to switch transparently among domains within a single dialog. This system is able to detect the presence of any out-of-vocabulary (OOV) words, and automatically hypothesizes each of their pronunciation, spelling and meaning. These can be confirmed with the user and the new words are subsequently incorporated into the recognizer lexicon for future use. This thesis

This thesis focuses on the automatic acquisition of language structure and the subsequent use of the learned language structure to improve the performance of a speech recognition system. First, we develop a grammar inference process which is able to learn a grammar describing a large set of training sentences. The process of acquiring this grammar is one of generalization so that the resulting grammar predicts likely sentences beyond those contained in the training set. From the grammar we construct a novel probabilistic language model called the phrase class n-gram model (pcng), which is a natural generalization of the word class n-gram model [11] to phrase classes. This model utilizes the grammar in such a way that it maintains full coverage of any test set while at the same time reducing the complexity, or number of parameters, of the resulting predictive model. Positive results are shown in terms of perplexity of the acquired phrase class n-gram models and in terms of reduction of ...

We describe the first sentence understanding system that is completely based on learned methods both for understanding individual sentences, and determinig their meaning in the context of preceding sentences. We describe the models used for each of three stages in the understanding: semantic parsing, semantic classification, and discourse modeling. When we ran this system on the last test (December, 1994) of the ARPA Air Travel Information System (ATIS) task, we achieved 14.5% error rate. The error rate for those sentences that are context-independent (class A) was 9.5%.

We describe and experimentally evaluate a system, FeasPar, that learns parsing spontaneous speech. To train and run FeasPar (Feature Structure Parser), only limited handmodeled knowledge is required. The FeasPar architecture consists of neural networks and a search. The networks spilt the incoming sentence into chunks, which are labeled with feature values and chunk relations. Then, the search finds the most probable and consistent feature structure. FeasPar is trained...

In this thesis, I designed and implemented SLS-Lite, a utility for allowing non-experts to build and run spoken language systems. This involved the creation of both a web interface for the developer and a set of programs to support the construction and execution of the required internal systems. We concentrated on simplifying the task of configuring the language understanding components of a spoken language system. Any application-specific functionality required could be provided by the developer in a simple, CGI-based back-end. By learning the required grammar from a set of simple concepts and sentence examples provided by the developer, we were able to build a system where non-experts could build grammars and speech systems. Developers could also easily specify hierarchy in domains where a more complex grammar was appropriate. We demonstrated SLS-Lite by building several domains ourselves, and allowing others to build their own. These included domains for controlling the appliances i...