Search Results for author: Hans Uszkoreit

Found 38 papers, 1 papers with code

A Linguistically Motivated Test Suite to Semi-Automatically Evaluate German–English Machine Translation Output

1 code implementation LREC 2022 Vivien Macketanz, Eleftherios Avramidis, Aljoscha Burchardt, He Wang, Renlong Ai, Shushen Manakhimova, Ursula Strohriegel, Sebastian Möller, Hans Uszkoreit

Furthermore, we present various exemplary applications of our test suite that have been implemented in the past years, like contributions to the Conference of Machine Translation, the usage of the test suite and MT outputs for quality estimation, and the expansion of the test suite to the language pair Portuguese–English.

Machine Translation

Linguistic evaluation of German-English Machine Translation using a Test Suite

no code implementations WS 2019 Eleftherios Avramidis, Vivien Macketanz, Ursula Strohriegel, Hans Uszkoreit

We present the results of the application of a grammatical test suite for German$\rightarrow$English MT on the systems submitted at WMT19, with a detailed analysis for 107 phenomena organized in 14 categories.

Machine Translation Translation

Word Embeddings as Features for Supervised Coreference Resolution

no code implementations RANLP 2017 Iliana Simova, Hans Uszkoreit

A common reason for errors in coreference resolution is the lack of semantic information to help determine the compatibility between mentions referring to the same entity.

coreference-resolution Dimensionality Reduction +4

Generating Pattern-Based Entailment Graphs for Relation Extraction

no code implementations SEMEVAL 2017 Kathrin Eichler, Feiyu Xu, Hans Uszkoreit, Sebastian Krause

A common approach is to exploit existing knowledge to learn linguistic patterns expressing the target relation and use these patterns for extracting new relation mentions.

Knowledge Base Population Natural Language Inference +1

The taraX\"U corpus of human-annotated machine translations

no code implementations LREC 2014 Eleftherios Avramidis, Aljoscha Burchardt, Sabine Hunsicker, Maja Popovi{\'c}, Cindy Tscherwinka, David Vilar, Hans Uszkoreit

Human translators are the key to evaluating machine translation (MT) quality and also to addressing the so far unanswered question when and how to use MT in professional translation workflows.

General Classification Machine Translation +1

Information Extraction from German Patient Records via Hybrid Parsing and Relation Extraction Strategies

no code implementations LREC 2014 Hans-Ulrich Krieger, Christian Spurk, Hans Uszkoreit, Feiyu Xu, Yi Zhang, Frank M{\"u}ller, Thomas Tolxdorff

In this paper, we report on first attempts and findings to analyzing German patient records, using a hybrid parsing architecture and a combination of two relation extraction strategies.

Chunking Medical Diagnosis +3

Annotating Relation Mentions in Tabloid Press

no code implementations LREC 2014 Hong Li, Sebastian Krause, Feiyu Xu, Hans Uszkoreit, Robert Hummel, Veselina Mironova

The current corpus is already in active use in our research for evaluation of the relation extraction performance of our automatically learned extraction patterns.

Relation Extraction

Language Resources and Annotation Tools for Cross-Sentence Relation Extraction

no code implementations LREC 2014 Sebastian Krause, Hong Li, Feiyu Xu, Hans Uszkoreit, Robert Hummel, Luise Spielhagen

In this paper, we present a novel combination of two types of language resources dedicated to the detection of relevant relations (RE) such as events or facts across sentence boundaries.

Coreference Resolution Dependency Parsing +1

Cannot find the paper you are looking for? You can Submit a new open access paper.