We present DOPA METER, a tool suite for the metrical investigation of written language, that provides diagnostic means for its division into discourse categories, such as registers, genres, and style. The quantitative basis of our system are 120 metrics covering a wide range of lexical, syntactic, and semantic features relevant for language profiling. The scores can be summarized, compared, and aggregated using visualization tools that can be tailored according to the users’ needs. We also showcase an application scenario for DOPA METER.

The exploding amount of user-generated content has spurred NLP research to deal with documents from various digital communication formats (tweets, chats, emails, etc.). Using these texts as language resources implies complying with legal data privacy regulations. To protect the personal data of individuals and preclude their identification, we employ pseudonymization. More precisely, we identify those text spans that carry information revealing an individual’s identity (e.g., names of persons, locations, phone numbers, or dates) and subsequently substitute them with synthetically generated surrogates. Based on CodE Alltag, a German-language email corpus, we address two tasks. The first task is to evaluate various architectures for the automatic recognition of privacy-sensitive entities in raw data. The second task examines the applicability of pseudonymized data as training data for such systems since models learned on original data cannot be published for reasons of privacy protection. As outputs of both tasks, we, first, generate a new pseudonymized version of CodE Alltag compliant with the legal requirements of the General Data Protection Regulation (GDPR). Second, we make accessible a tagger for recognizing privacy-sensitive information in German emails and similar text genres, which is trained on already pseudonymized data.

Despite remarkable advances in the development of language resources over the recent years, there is still a shortage of annotated, publicly available corpora covering (German) medical language. With the initial release of the German Guideline Program in Oncology NLP Corpus (GGPONC), we have demonstrated how such corpora can be built upon clinical guidelines, a widely available resource in many natural languages with a reasonable coverage of medical terminology. In this work, we describe a major new release for GGPONC. The corpus has been substantially extended in size and re-annotated with a new annotation scheme based on SNOMED CT top level hierarchies, reaching high inter-annotator agreement (γ=.94). Moreover, we annotated elliptical coordinated noun phrases and their resolutions, a common language phenomenon in (not only German) scientific documents. We also trained BERT-based named entity recognition models on this new data set, which achieve high performance on short, coarse-grained entity spans (F1=.89), while the rate of boundary errors increases for long entity spans. GGPONC is freely available through a data use agreement. The trained named entity recognition models, as well as the detailed annotation guide, are also made publicly available.

To track different levels of formality in written discourse, we introduce a novel type of lexicon for the German language, with entries ordered by their degree of (in)formality. We start with a set of words extracted from traditional lexicographic resources, extend it by sentence-based similarity computations, and let crowdworkers assess the enlarged set of lexical items on a continuous informal-formal scale as a gold standard for evaluation. We submit this lexicon to an intrinsic evaluation related to the best regression models and their effect on predicting formality scores and complement our investigation by an extrinsic evaluation of formality on a German-language email corpus.

Research in emotion analysis is scattered across different label formats (e.g., polarity types, basic emotion categories, and affective dimensions), linguistic levels (word vs. sentence vs. discourse), and, of course, (few well-resourced but much more under-resourced) natural languages and text genres (e.g., product reviews, tweets, news). The resulting heterogeneity makes data and software developed under these conflicting constraints hard to compare and challenging to integrate. To resolve this unsatisfactory state of affairs we here propose a training scheme that learns a shared latent representation of emotion independent from different label formats, natural languages, and even disparate model architectures. Experiments on a wide range of datasets indicate that this approach yields the desired interoperability without penalizing prediction quality. Code and data are archived under DOI 10.5281/zenodo.5466068.

The lack of publicly accessible text corpora is a major obstacle for progress in natural language processing. For medical applications, unfortunately, all language communities other than English are low-resourced. In this work, we present GGPONC (German Guideline Program in Oncology NLP Corpus), a freely dis tributable German language corpus based on clinical practice guidelines for oncology. This corpus is one of the largest ever built from German medical documents. Unlike clinical documents, clinical guidelines do not contain any patient-related information and can therefore be used without data protection restrictions. Moreover, GGPONC is the first corpus for the German language covering diverse conditions in a large medical subfield and provides a variety of metadata, such as literature references and evidence levels. By applying and evaluating existing medical information extraction pipelines for German text, we are able to draw comparisons for the use of medical language to other corpora, medical and non-medical ones.

The massive digitization efforts related to historical newspapers over the past decades have focused on mass media sources and ordinary people as their primary recipients. Much less attention has been paid to newspapers published for a more specialized audience, e.g., those aiming at scholarly or cultural exchange within intellectual communities much narrower in scope, such as newspapers devoted to music criticism, arts or philosophy. Only some few of these specialized newspapers have been digitized up until now, but they are usually not well curated in terms of digitization quality, data formatting, completeness, redundancy (de-duplication), supply of metadata, and, hence, searchability. This paper describes our approach to eliminate these drawbacks for a major German-language newspaper resource of the Romantic Age, the Allgemeine Musikalische Zeitung (General Music Gazette). We here focus on a workflow that copes with a posteriori digitization problems, inconsistent OCRing and index building for searchability. In addition, we provide a user-friendly graphic interface to empower content-centric access to this (and other) digital resource(s) adopting open-source software for the purpose of Web presentation.

The vast amount of social communication distributed over various electronic media channels (tweets, blogs, emails, etc.), so-called user-generated content (UGC), creates entirely new opportunities for today’s NLP research. Yet, data privacy concerns implied by the unauthorized use of these text streams as a data resource are often neglected. In an attempt to reconciliate the diverging needs of unconstrained raw data use and preservation of data privacy in digital communication, we here investigate the automatic recognition of privacy-sensitive stretches of text in UGC and provide an algorithmic solution for the protection of personal data via pseudonymization. Our focus is directed at the de-identification of emails where personally identifying information does not only refer to the sender but also to those people, locations, dates, and other identifiers mentioned in greetings, boilerplates and the content-carrying body of emails. We evaluate several de-identification procedures and systems on two hitherto non-anonymized German-language email corpora (CodE AlltagS+d and CodE AlltagXL), and generate fully pseudonymized versions for both (CodE Alltag 2.0) in which personally identifying information of all social actors addressed in these mails has been camouflaged (to the greatest extent possible).

Genes and proteins constitute the fundamental entities of molecular genetics. We here introduce ProGene (formerly called FSU-PRGE), a corpus that reflects our efforts to cope with this important class of named entities within the framework of a long-lasting large-scale annotation campaign at the Jena University Language & Information Engineering (JULIE) Lab. We assembled the entire corpus from 11 subcorpora covering various biological domains to achieve an overall subdomain-independent corpus. It consists of 3,308 MEDLINE abstracts with over 36k sentences and more than 960k tokens annotated with nearly 60k named entity mentions. Two annotators strove for carefully assigning entity mentions to classes of genes/proteins as well as families/groups, complexes, variants and enumerations of those where genes and proteins are represented by a single class. The main purpose of the corpus is to provide a large body of consistent and reliable annotations for supervised training and evaluation of machine learning algorithms in this relevant domain. Furthermore, we provide an evaluation of two state-of-the-art baseline systems — BioBert and flair — on the ProGene corpus. We make the evaluation datasets and the trained models available to encourage comparable evaluations of new methods in the future.

Emotion lexicons describe the affective meaning of words and thus constitute a centerpiece for advanced sentiment and emotion analysis. Yet, manually curated lexicons are only available for a handful of languages, leaving most languages of the world without such a precious resource for downstream applications. Even worse, their coverage is often limited both in terms of the lexical units they contain and the emotional variables they feature. In order to break this bottleneck, we here introduce a methodology for creating almost arbitrarily large emotion lexicons for any target language. Our approach requires nothing but a source language emotion lexicon, a bilingual word translation model, and a target language embedding model. Fulfilling these requirements for 91 languages, we are able to generate representationally rich high-coverage lexicons comprising eight emotional variables with more than 100k lexical entries each. We evaluated the automatically generated lexicons against human judgment from 26 datasets, spanning 12 typologically diverse languages, and found that our approach produces results in line with state-of-the-art monolingual approaches to lexicon creation and even surpasses human reliability for some languages and variables. Code and data are available at https://github.com/JULIELab/MEmoLon archived under DOI 10.5281/zenodo.3779901.

We examine the affective content of central bank press statements using emotion analysis. Our focus is on two major international players, the European Central Bank (ECB) and the US Federal Reserve Bank (Fed), covering a time span from 1998 through 2019. We reveal characteristic patterns in the emotional dimensions of valence, arousal, and dominance and find—despite the commonly established attitude that emotional wording in central bank communication should be avoided—a correlation between the state of the economy and particularly the dominance dimension in the press releases under scrutiny and, overall, an impact of the president in office.

The stability of word embedding algorithms, i.e., the consistency of the word representations they reveal when trained repeatedly on the same data set, has recently raised concerns. We here compare word embedding algorithms on three corpora of different sizes, and evaluate both their stability and accuracy. We find strong evidence that down-sampling strategies (used as part of their training procedures) are particularly influential for the stability of SVD-PPMI-type embeddings. This finding seems to explain diverging reports on their stability and lead us to a simple modification which provides superior stability as well as accuracy on par with skip-gram embedding

To understand historical texts, we must be aware that language—including the emotional connotation attached to words—changes over time. In this paper, we aim at estimating the emotion which is associated with a given word in former language stages of English and German. Emotion is represented following the popular Valence-Arousal-Dominance (VAD) annotation scheme. While being more expressive than polarity alone, existing word emotion induction methods are typically not suited for addressing it. To overcome this limitation, we present adaptations of two popular algorithms to VAD. To measure their effectiveness in diachronic settings, we present the first gold standard for historical word emotions, which was created by scholars with proficiency in the respective language stages and covers both English and German. In contrast to claims in previous work, our findings indicate that hand-selecting small sets of seed words with supposedly stable emotional meaning is actually harm- rather than helpful.

In this paper, we describe a workflow for the data-driven acquisition and semantic scaling of a lexicon that covers lexical items from the lower end of the German language register—terms typically considered as rough, vulgar or obscene. Since the fine semantic representation of grades of obscenity can only inadequately be captured at the categorical level (e.g., obscene vs. non-obscene, or rough vs. vulgar), our main contribution lies in applying best-worst scaling, a rating methodology that has already been shown to be useful for emotional language, to capture the relative strength of obscenity of lexical items. We describe the empirical foundations for bootstrapping such a low-end lexicon for German by starting from manually supplied lexicographic categorizations of a small seed set of rough and vulgar lexical items and automatically enlarging this set by means of distributional semantics. We then determine the degrees of obscenity for the full set of all acquired lexical items by letting crowdworkers comparatively assess their pejorative grade using best-worst scaling. This semi-automatically enriched lexicon already comprises 3,300 lexical items and incorporates 33,000 vulgarity ratings. Using it as a seed lexicon for fully automatic lexical acquisition, we were able to raise its coverage up to slightly more than 11,000 entries.

Today’s widely used annotation tools were designed for annotating typically short textual mentions of entities or relations, making their interface cumbersome to use for long(er) stretches of text, e.g, sentences running over several lines in a document. They also lack systematic support for hierarchically structured labels, i.e., one label being conceptually more general than another (e.g., anamnesis in relation to family anamnesis). Moreover, as a more fundamental shortcoming of today’s tools, they provide no continuous quality con trol mechanisms for the annotation process, an essential feature to intrinsically support iterative cycles in the development of annotation guidelines. We alleviated these problems by developing WAT-SL 2.0, an open-source web-based annotation tool for long-segment labeling, hierarchically structured label sets and built-ins for quality control.

We deal with the pseudonymization of those stretches of text in emails that might allow to identify real individual persons. This task is decomposed into two steps. First, named entities carrying privacy-sensitive information (e.g., names of persons, locations, phone numbers or dates) are identified, and, second, these privacy-bearing entities are replaced by synthetically generated surrogates (e.g., a person originally named ‘John Doe’ is renamed as ‘Bill Powers’). We describe a system architecture for surrogate generation and evaluate our approach on CodeAlltag, a German email corpus.

Predicting the emotional value of lexical items is a well-known problem in sentiment analysis. While research has focused on polarity for quite a long time, meanwhile this early focus has been shifted to more expressive emotion representation models (such as Basic Emotions or Valence-Arousal-Dominance). This change resulted in a proliferation of heterogeneous formats and, in parallel, often small-sized, non-interoperable resources (lexicons and corpus annotations). In particular, the limitations in size hampered the application of deep learning methods in this area because they typically require large amounts of input data. We here present a solution to get around this language data bottleneck by rephrasing word emotion induction as a multi-task learning problem. In this approach, the prediction of each independent emotion dimension is considered as an individual task and hidden layers are shared between these dimensions. We investigate whether multi-task learning is more advantageous than single-task learning for emotion prediction by comparing our model against a wide range of alternative emotion and polarity induction methods featuring 9 typologically diverse languages and a total of 15 conditions. Our model turns out to outperform each one of them. Against all odds, the proposed deep learning approach yields the largest gain on the smallest data sets, merely composed of one thousand samples.

Emotion Representation Mapping (ERM) has the goal to convert existing emotion ratings from one representation format into another one, e.g., mapping Valence-Arousal-Dominance annotations for words or sentences into Ekman’s Basic Emotions and vice versa. ERM can thus not only be considered as an alternative to Word Emotion Induction (WEI) techniques for automatic emotion lexicon construction but may also help mitigate problems that come from the proliferation of emotion representation formats in recent years. We propose a new neural network approach to ERM that not only outperforms the previous state-of-the-art. Equally important, we present a refined evaluation methodology and gather strong evidence that our model yields results which are (almost) as reliable as human annotations, even in cross-lingual settings. Based on these results we generate new emotion ratings for 13 typologically diverse languages and claim that they have near-gold quality, at least.

We here introduce a substantially extended version of JeSemE, an interactive website for visually exploring computationally derived time-variant information on word meanings and lexical emotions assembled from five large diachronic text corpora. JeSemE is designed for scholars in the (digital) humanities as an alternative to consulting manually compiled, printed dictionaries for such information (if available at all). This tool uniquely combines state-of-the-art distributional semantics with a nuanced model of human emotions, two information streams we deem beneficial for a data-driven interpretation of texts in the humanities.

We introduce JOCo, a novel text corpus for NLP analytics in the field of economics, business and management. This corpus is composed of corporate annual and social responsibility reports of the top 30 US, UK and German companies in the major (DJIA, FTSE 100, DAX), middle-sized (S&P 500, FTSE 250, MDAX) and technology (NASDAQ, FTSE AIM 100, TECDAX) stock indices, respectively. Altogether, this adds up to 5,000 reports from 270 companies headquartered in three of the world’s most important economies. The corpus spans a time frame from 2000 up to 2015 and contains, in total, 282M tokens. We also feature JOCo in a small-scale experiment to demonstrate its potential for NLP-fueled studies in economics, business and management research.

We describe EmoBank, a corpus of 10k English sentences balancing multiple genres, which we annotated with dimensional emotion metadata in the Valence-Arousal-Dominance (VAD) representation format. EmoBank excels with a bi-perspectival and bi-representational design. On the one hand, we distinguish between writer’s and reader’s emotions, on the other hand, a subset of the corpus complements dimensional VAD annotations with categorical ones based on Basic Emotions. We find evidence for the supremacy of the reader’s perspective in terms of IAA and rating intensity, and achieve close-to-human performance when mapping between dimensional and categorical formats.

We here examine how different perspectives of understanding written discourse, like the reader’s, the writer’s or the text’s point of view, affect the quality of emotion annotations. We conducted a series of annotation experiments on two corpora, a popular movie review corpus and a genre- and domain-balanced corpus of standard English. We found statistical evidence that the writer’s perspective yields superior annotation quality overall. However, the quality one perspective yields compared to the other(s) seems to depend on the domain the utterance originates from. Our data further suggest that the popular movie review data set suffers from an atypical bimodal distribution which may decrease model performance when used as a training resource.

We here describe a novel methodology for measuring affective language in historical text by expanding an affective lexicon and jointly adapting it to prior language stages. We automatically construct a lexicon for word-emotion association of 18th and 19th century German which is then validated against expert ratings. Subsequently, this resource is used to identify distinct emotional patterns and trace long-term emotional trends in different genres of writing spanning several centuries.

We introduce JCoRe 2.0, the relaunch of a UIMA-based open software repository for full-scale natural language processing originating from the Jena University Language & Information Engineering (JULIE) Lab. In an attempt to put the new release of JCoRe on firm software engineering ground, we uploaded it to GitHub, a social coding platform, with an underlying source code versioning system and various means to support collaboration for software development and code modification management. In order to automate the builds of complex NLP pipelines and properly represent and track dependencies of the underlying Java code, we incorporated Maven as part of our software configuration management efforts. In the meantime, we have deployed our artifacts on Maven Central, as well. JCoRe 2.0 offers a broad range of text analytics functionality (mostly) for English-language scientific abstracts and full-text articles, especially from the life sciences domain.

We introduce CODE ALLTAG, a text corpus composed of German-language e-mails. It is divided into two partitions: the first of these portions, CODE ALLTAG_XL, consists of a bulk-size collection drawn from an openly accessible e-mail archive (roughly 1.5M e-mails), whereas the second portion, CODE ALLTAG_S+d, is much smaller in size (less than thousand e-mails), yet excels with demographic data from each author of an e-mail. CODE ALLTAG, thus, currently constitutes the largest E-Mail corpus ever built. In this paper, we describe, for both parts, the solicitation process for gathering e-mails, present descriptive statistical properties of the corpus, and, for CODE ALLTAG_S+d, reveal a compilation of demographic features of the donors of e-mails.

We assess the reliability and accuracy of (neural) word embeddings for both modern and historical English and German. Our research provides deeper insights into the empirically justified choice of optimal training methods and parameters. The overall low reliability we observe, nevertheless, casts doubt on the suitability of word neighborhoods in embedding spaces as a basis for qualitative conclusions on synchronic and diachronic lexico-semantic matters, an issue currently high up in the agenda of Digital Humanities.

The coverage of multilingual biomedical resources is high for the English language, yet sparse for non-English languages―an observation which holds for seemingly well-resourced, yet still dramatically low-resourced ones such as Spanish, French or German but even more so for really under-resourced ones such as Dutch. We here present experimental results for automatically annotating parallel corpora and simultaneously acquiring new biomedical terminology for these under-resourced non-English languages on the basis of two types of language resources, namely parallel corpora (i.e. full translation equivalents at the document unit level) and (admittedly deficient) multilingual biomedical terminologies, with English as their anchor language. We automatically annotate these parallel corpora with biomedical named entities by an ensemble of named entity taggers and harmonize non-identical annotations the outcome of which is a so-called silver standard corpus. We conclude with an empirical assessment of this approach to automatically identify both known and new terms in multilingual corpora.

Confidential corpora from the medical, enterprise, security or intelligence domains often contain sensitive raw data which lead to severe restrictions as far as the public accessibility and distribution of such language resources are concerned. The enforcement of strict mechanisms of data protection consitutes a serious barrier for progress in language technology (products) in such domains, since these data are extremely rare or even unavailable for scientists and developers not directly involved in the creation and maintenance of such resources. In order to by-pass this problem, we here propose to distribute trained language models which were derived from such resources as a substitute for the original confidential raw data which remain hidden to the outside world. As an example, we exploit the access-protected German-language medical FRAMED corpus from which we generate and distribute models for sentence splitting, tokenization and POS tagging based on software taken from OPENNLP, NLTK and JCORE, our own UIMA-based text analytics pipeline.

We here discuss a methodology for dealing with the annotation of semantically hard to delineate, i.e., sloppy, named entity types. To illustrate sloppiness of entities, we treat an example from the medical domain, namely pathological phenomena. Based on our experience with iterative guideline refinement we propose to carefully characterize the thematic scope of the annotation by positive and negative coding lists and allow for alternative, short vs. long mention span annotations. Short spans account for canonical entity mentions (e.g., standardized disease names), while long spans cover descriptive text snippets which contain entity-specific elaborations (e.g., anatomical locations, observational details, etc.). Using this stratified approach, evidence for increasing annotation performance is provided by kappa-based inter-annotator agreement measurements over several, iterative annotation rounds using continuously refined guidelines. The latter reflects the increasing understanding of the sloppy entity class both from the perspective of guideline writers and users (annotators). Given our data, we have gathered evidence that we can deal with sloppiness in a controlled manner and expect inter-annotator agreement values around 80% for PathoJen, the pathological phenomena corpus currently under development in our lab.

A number of gold standard corpora for named entity recognition are available to the public. However, the existing gold standard corpora are limited in size and semantic entity types. These usually lead to implementation of trained solutions (1) for a limited number of semantic entity types and (2) lacking in generalization capability. In order to overcome these problems, the CALBC project has aimed to automatically generate large scale corpora annotated with multiple semantic entity types in a community-wide manner based on the consensus of different named entity solutions. The generated corpus is called the silver standard corpus since the corpus generation process does not involve any manual curation. In this publication, we announce the release of the final CALBC corpora which include the silver standard corpus in different versions and several gold standard corpora for the further usage of the biomedical text mining community. The gold standard corpora are utilised to benchmark the methods used in the silver standard corpora generation process and released in a shared format. All the corpora are released in a shared format and accessible at www.calbc.eu.

Despite the large variety of corpora in the biomedical domain their annotations differ in many respects, e.g., the coverage of different, highly specialized knowledge domains, varying degrees of granularity of targeted relations, the specificity of linguistic anchoring of relations and named entities in documents, etc. We here present GeneReg (Gene Regulation Corpus), the result of an annotation campaign led by the Jena University Language & Information Engineering (JULIE) Lab. The GeneReg corpus consists of 314 abstracts dealing with the regulation of gene expression in the model organism E. coli. Our emphasis in this paper is on the compatibility of the GeneReg corpus with the alternative Genia event corpus and with several in-domain and out-of-domain lexical resources, e.g., the Specialist Lexicon, FrameNet, and WordNet. The links we established from the GeneReg corpus to these external resources will help improve the performance of the automatic relation extraction engine JREx trained and evaluated on GeneReg.

We describe the re-annotation of selected types of named entities (persons, organizations, locations) from the Muc7 corpus. The focus of this annotation initiative is on recording the time needed for the linguistic process of named entity annotation. Annotation times are measured on two basic annotation units -- sentences vs. complex noun phrases. We gathered evidence that decision times are non-uniformly distributed over the annotation units, while they do not substantially deviate among annotators. This data seems to support the hypothesis that annotation times very much depend on the inherent ""hardness"" of each single annotation decision. We further show how such time-stamped information can be used for empirically grounded studies of selective sampling techniques, such as Active Learning. We directly compare Active Learning costs on the basis of token-based vs. time-based measurements. The data reveals that Active Learning keeps its competitive advantage over random sampling in both scenarios though the difference is less marked for the time metric than for the token metric.

The production of gold standard corpora is time-consuming and costly. We propose an alternative: the ‚silver standard corpus‘ (SSC), a corpus that has been generated by the harmonisation of the annotations that have been delivered from a selection of annotation systems. The systems have to share the type system for the annotations and the harmonisation solution has use a suitable similarity measure for the pair-wise comparison of the annotations. The annotation systems have been evaluated against the harmonised set (630.324 sentences, 15,956,841 tokens). We can demonstrate that the annotation of proteins and genes shows higher diversity across all used annotation solutions leading to a lower agreement against the harmonised set in comparison to the annotations of diseases and species. An analysis of the most frequent annotations from all systems shows that a high agreement amongst systems leads to the selection of terms that are suitable to be kept in the harmonised set. This is the first large-scale approach to generate an annotated corpus from automated annotation systems. Further research is required to understand, how the annotations from different systems have to be combined to produce the best annotation result for a harmonised corpus.

Active learning (AL) is getting more and more popular as a methodology to considerably reduce the annotation effort when building training material for statistical learning methods for various NLP tasks. A crucial issue rarely addressed, however, is when to actually stop the annotation process to profit from the savings in efforts. This question is tightly related to estimating the classifier performance after a certain amount of data has already been annotated. While learning curves are the default means to monitor the progress of the annotation process in terms of classifier performance, this requires a labeled gold standard which - in realistic annotation settings, at least - is often unavailable. We here propose a method for committee-based AL to approximate the progression of the learning curve based on the disagreement among the committee members. This method relies on a separate, unlabeled corpus and is thus well suited for situations where a labeled gold standard is not available or would be too expensive to obtain. Considering named entity recognition as a test case we provide empirical evidence that this approach works well under simulation as well as under real-world annotation conditions.

We provide an overview of corpus building efforts at the Jena University Language & Information Engineering (JULIE) Lab which are focused on life science documents. Special emphasis is laid on semantic annotations in terms of a large amount of biomedical named entities (almost 100 entity types), semantic relations, as well as discourse phenomena, reference relations in particular.

We present the lexico-semantic foundations underlying a multilingual lexicon the entries of which are constituted by so-called subwords. These subwords reflect semantic atomicity constraints in the medical domain which diverge from canonical lexicological understanding in NLP. We focus here on criteria to identify and delimit reasonable subword units, to group them into functionally adequate synonymy classes and relate them by two types of lexical relations. The lexicon we implemented on the basis of these considerations forms the lexical backbone for MorphoSaurus, a cross-language document retrieval engine for the medical domain.

We introduce a light-weight interlingua for a cross-language document retrieval system in the medical domain. It is composed of equivalence classes of semantically primitive, language-specific subwords which are clustered by interlingual and intralingual synonymy. Each subword cluster represents a basic conceptual entity of the language-independent interlingua. Documents, as well as queries, are mapped to this interlingua level on which retrieval operations are performed. Evaluation experiments reveal that this interlingua-based retrieval model outperforms a direct translation approach.

We argue for a performance-based design of natural language grammars and their associated parsers in order to meet the constraints imposed by real-world NLP. Our approach incorporates declarative and procedural knowledge about language and language use within an object-oriented specification framework. We discuss several message-passing protocols for parsing and provide reasons for sacrificing completeness of the parse in favor of efficiency based on a preliminary empirical evaluation.