We present a new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less, and 89.5% for sentences of length 100 and less when trained and tested on the previously established [5,9,10,15,17] "stan- dard" sections of the Wall Street Journal tree- bank. This represents a 13% decrease in error rate over the best single-parser results on this corpus [9]. The major technical innova- tion is the use of a "maximum-entropy-inspired" model for conditioning and smoothing that let us successfully to test and combine many different conditioning events. We also present some partial results showing the effects of different conditioning information, including a surprising 2% improvement due to guessing the lexical head's pre-terminal before guessing the lexical head.

this paper, we will describe a simple rule-based approach to automated learning of linguistic knowledge. This approach has been shown for a number of tasks to capture information in a clearer and more direct fashion without a compromise in performance. We present a detailed case study of this learning method applied to part of speech tagging

This paper presents a statistical model which trains from a corpus annotated with Part-OfSpeech tags and assigns them to previously unseen text with state-of-the-art accuracy(96.6%). The model can be classified as a Maximum Entropy model and simultaneously uses many contextual "features" to predict the POS tag. Furthermore, this paper demonstrates the use of specialized features to model difficult tagging decisions, discusses the corpus consistency problems discovered during the implementation of these features, and proposes a training strategy that mitigates these problems.

We describe new algorithms for training tagging models, as an alternative to maximum-entropy models or conditional random fields (CRFs). The algorithms rely on Viterbi decoding of training examples, combined with simple additive updates. We describe theory justifying the algorithms through a modification of the proof of convergence of the perceptron algorithm for classification problems. We give experimental results on part-of-speech tagging and base noun phrase chunking, in both cases showing improvements over results for a maximum-entropy tagger.

We describe a parsing system based upon a language model for English that is, in turn, based upon assigning probabilities to possible parses for a sentence. This model is used in a parsing system by finding the parse for the sentence with the highest probability. This system outperforms previous schemes. As this is the third in a series of parsers by different authors that are similar enough to invite detailed comparisons but different enough to give rise to different levels of performance, we also report on some experiments designed to identify what aspects of these systems best explain their relative performance. Introduction We present a statistical parser that induces its grammar and probabilities from a hand-parsed corpus (a tree-bank). Parsers induced from corpora are of interest both as simply exercises in machine learning and also because they are often the best parsers obtainable by any method. That is, if one desires a parser that produces trees in the tree-bank ...

This article presents a measure of semantic similarityinanis-a taxonomy based on the notion of shared information content. Experimental evaluation against a benchmark set of human similarity judgments demonstrates that the measure performs better than the traditional edge-counting approach. The article presents algorithms that take advantage of taxonomic similarity in resolving syntactic and semantic ambiguity, along with experimental results demonstrating their e#ectiveness. 1. Introduction Evaluating semantic relatedness using network representations is a problem with a long history in arti#cial intelligence and psychology, dating back to the spreading activation approach of Quillian #1968# and Collins and Loftus #1975#. Semantic similarity represents a special case of semantic relatedness: for example, cars and gasoline would seem to be more closely related than, say, cars and bicycles, but the latter pair are certainly more similar. Rada et al. #Rada, Mili, Bicknell, & Blett...

Trigrams'n'Tags (TnT) is an efficient statistical part-of-speech tagger. Contrary to claims found elsewhere in the literature, we argue that a tagger based on Markov models performs at least as well as other current approaches, including the Maximum Entropy framework. A recent comparison has even shown that TnT performs significantly better for the tested corpora. We describe the basic model of TnT, the techniques used for smoothing and for handling unknown words. Furthermore, we present evaluations on two corpora.

The Proposition Bank project takes a practical approach to semantic representation, adding a layer of predicate-argument information, or semantic role labels, to the syntactic structures of the Penn Treebank. The resulting resource can be thought of as shallow, in that it does not represent coreference, quantification, and many other higher-order phenomena, but also broad, in that it covers every instance of every verb in the corpus and allows representative statistics to be calculated. We discuss the criteria used to define the sets of semantic roles used in the annotation process and to analyze the frequency of syntactic/semantic alternations in the corpus. We describe an automatic system for semantic role tagging trained on the corpus and discuss the effect on its performance of various types of information, including a comparison of full syntactic parsing with a flat representation and the contribution of the empty ‘‘trace’ ’ categories of the treebank.

Many corpus-based natural language processing systems rely on text corpora that have been manually annotated with syntactic or semantic tags. In particular, all previous dictionary construction systems for information extraction have used an annotated training corpus or some form of annotated input. We have developed a system called AutoSlog-TS that creates dictionaries of extraction patterns using only untagged text. AutoSlog-TS is based on the AutoSlog system, which generated extraction patterns using annotated text and a set of heuristic rules. By adapting AutoSlog and combining it with statistical techniques, we eliminated its dependency on tagged text. In experiments with the MUC-4 terrorism domain, AutoSlogTS created a dictionary of extraction patterns that performed comparably to a dictionary created by AutoSlog, using only preclassified texts as input. Motivation The vast amount of text becoming available on-line offers new possibilities for conquering the knowledgeengineerin...

The Penn Treebank has recently implemented a new syntactic annotation scheme, designed to highlight aspects of predicate-argument structure. This paper discusses the implementation of crucial aspects of this new annotation scheme. It incorporates a more consistent treatment of a wide range of grammatical phenomena, provides a set of coindexed null elements in what can be thought of as "underlying " position for phenomena such as wh-movement, passive, and the subjects of infinitival constructions, provides some non-context free annotational mechanism to allow the structure of discontinuous constituents to be easily recovered, and allows for a clear, concise tagging system for some semantic roles. 1. INTRODUCTION During the first phase of the The Penn Treebank project [10], ending in December 1992, 4.5 million words of text were tagged for part-of-speech, with about two-thirds of this material also annotated with a skeletal syntactic bracketing. All of this material has been hand corre...