Thorsten Brants

An Annotation Scheme for Free Word Order Languages

We describe an annotation scheme and a tool developed for creating linguistically annotated corpora for non-configurational languages. Since the requirements for such a formalism differ from those posited for configurational languages, several features have been added, influencing the architecture of the scheme. The resulting scheme reflects a stratificational notion of language, and makes only minimal assumptions about the interrelation of the particular representational strata.

A System for new event detection

We present a new method and system for performing the New Event Detection task, i.e., in one or multiple streams of news stories, all stories on a previously unseen (new) event are marked. The method is based on an incremental TF-IDF model. Our extensions include: generation of source-specific models, similarity score normalization based on document-specific averages, similarity score normalization based on source-pair specific averages, term reweighting based on inverse event frequencies, and segmentation of the documents. We also report on extensions that did not improve results. The system performs very well on TDT3 and TDT4 test data and scored second in the TDT-2002 evaluation.

Topic-based document segmentation with probabilistic latent semantic analysis

This paper presents a new method for topic-based document segmentation, i.e., the identification of boundaries between parts of a document that bear on different topics. The method combines the use of the Probabilistic Latent Semantic Analysis (PLSA) model with the method of selecting segmentation points based on the similarity values between pairs of adjacent blocks. The use of PLSA allows for a better representation of sparse information in a text block, such as a sentence or a sequence of sentences. Furthermore, segmentation performance is improved by combining different instantiations of the same model, either using different random initializations or different numbers of latent classes. Results on commonly available data sets are significantly better than those of other state-of-the-art systems.

The LinGO Redwoods treebank motivation and preliminary applications

The LinGO Redwoods initiative is a seed activity in the design and development of a new type of treebank. While several medium- to large-scale treebanks exist for English (and for other major languages), pre-existing publicly available resources exhibit the following limitations: (i) annotation is mono-stratal, either encoding topological (phrase structure) or tectogrammatical (dependency) information, (ii) the depth of linguistic information recorded is comparatively shallow, (iii) the design and format of linguistic representation in the treebank hard-wires a small, predefined range of ways in which information can be extracted from the treebank, and (iv) representations in existing treebanks are static and over the (often year- or decade-long) evolution of a large-scale treebank tend to fall behind the development of the field. LinGO Redwoods aims at the development of a novel treebanking methodology, rich in nature and dynamic both in the ways linguistic data can be retrieved from the treebank in varying granularity and in the constant evolution and regular updating of the treebank itself. Since October 2001, the project is working to build the foundations for this new type of treebank, to develop a basic set of tools for treebank construction and maintenance, and to construct an initial set of 10,000 annotated trees to be distributed together with the tools under an open-source license.

Wide-Coverage Probabilistic Sentence Processing

This paper describes a fully implemented, broad-coverage model of human syntactic processing. The model uses probabilistic parsing techniques, which combine phrase structure, lexical category, and limited subcategory probabilities with an incremental, left-to-right “pruning” mechanism based on cascaded Markov models. The parameters of the system are established through a uniform training algorithm, which determines maximum-likelihood estimates from a parsed corpus. The probabilistic parsing mechanism enables the system to achieve good accuracy on typical, “garden-variety” language (i.e., when tested on corpora). Furthermore, the incremental probabilistic ranking of the preferred analyses during parsing also naturally explains observed human behavior for a range of garden-path structures. We do not make strong psychological claims about the specific probabilistic mechanism discussed here, which is limited by a number of practical considerations. Rather, we argue incremental probabilistic parsing models are, in general, extremely well suited to explaining this dual nature—generally good and occasionally pathological—of human linguistic performance.

Syntactic Annotation of a German Newspaper Corpus

We report on the syntactic annotation of a German newspaper corpus. The annotations consist of context-free structures, additionally allowing crossing branches, with labeled nodes (phrases) and edges (grammatical functions). Furthermore, we present a new, interactive semi-automatic annotation process that allows efficient and reliable annotations. The annotation process is sped up by incrementally presenting structures and by automatically highlighting unreliable assignments.

A Context Pattern Induction Method for Named Entity Extraction

We present a novel context pattern induction method for information extraction, specifically named entity extraction. Using this method, we extended several classes of seed entity lists into much larger high-precision lists. Using token membership in these extended lists as additional features, we improved the accuracy of a conditional random field-based named entity tagger. In contrast, features derived from the seed lists decreased extractor accuracy.

Cascaded Markov Models

This paper presents a new approach to partial parsing of context-free structures. The approach is based on Markov Models. Each layer of the resulting structure is represented by its own Markov Model, and output of a lower layer is passed as input to the next higher layer. An empirical evaluation of the method yields very good results for NP/PP chunking of German newspaper texts.

Automation of treebank annotation

This paper describes applications of stochastic and symbolic NLP methods to treebank annotation. In particular we focus on (1) the automation of treebank annotation, (2) the comparison of conflicting annotations for the same sentence and (3) the automatic detection of inconsistencies. These techniques are currently employed for building a German treebank.

Query language modeling for voice search

The paper presents an empirical exploration of google.com query stream language modeling. We describe the normalization of the typed query stream resulting in out-of-vocabulary (OoV) rates below 1% for a one million word vocabulary. We present a comprehensive set of experiments that guided the design decisions for a voice search service. In the process we re-discovered a less known interaction between Kneser-Ney smoothing and entropy pruning, and found empirical evidence that hints at non-stationarity of the query stream, as well as strong dependence on various English locales—USA, Britain and Australia.