Search Results for author: Ulf Hermjakob

Found 13 papers, 3 papers with code

The eBible Corpus: Data and Model Benchmarks for Bible Translation for Low-Resource Languages

1 code implementation19 Apr 2023 Vesa Akerman, David Baines, Damien Daspit, Ulf Hermjakob, Taeho Jang, Colin Leong, Michael Martin, Joel Mathew, Jonathan Robie, Marcus Schwarting

Efficiently and accurately translating a corpus into a low-resource language remains a challenge, regardless of the strategies employed, whether manual, automated, or a combination of the two.

Benchmarking Machine Translation +2

User Study for Improving Tools for Bible Translation

no code implementations1 Feb 2023 Joel Mathew, Ulf Hermjakob

Technology has increasingly become an integral part of the Bible translation process.

Translation

Translating a Language You Don't Know In the Chinese Room

no code implementations ACL 2018 Ulf Hermjakob, Jonathan May, Michael Pust, Kevin Knight

In a corruption of John Searle{'}s famous AI thought experiment, the Chinese Room (Searle, 1980), we twist its original intent by enabling humans to translate text, e. g. from Uyghur to English, even if they don{'}t have any prior knowledge of the source language.

Domain Adaptation Language Modelling +3

Out-of-the-box Universal Romanization Tool uroman

no code implementations ACL 2018 Ulf Hermjakob, Jonathan May, Kevin Knight

We present uroman, a tool for converting text in myriads of languages and scripts such as Chinese, Arabic and Cyrillic into a common Latin-script representation.

Machine Translation

Extracting Biomolecular Interactions Using Semantic Parsing of Biomedical Text

1 code implementation4 Dec 2015 Sahil Garg, Aram Galstyan, Ulf Hermjakob, Daniel Marcu

We advance the state of the art in biomolecular interaction extraction with three contributions: (i) We show that deep, Abstract Meaning Representations (AMR) significantly improve the accuracy of a biomolecular interaction extraction system when compared to a baseline that relies solely on surface- and syntax-based features; (ii) In contrast with previous approaches that infer relations on a sentence-by-sentence basis, we expand our framework to enable consistent predictions over sets of sentences (documents); (iii) We further modify and expand a graph kernel learning framework to enable concurrent exploitation of automatically induced AMR (semantic) and dependency structure (syntactic) representations.

Semantic Parsing Sentence

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