Papers by Christian Hardmeier

11 papers
ParCorFull: a Parallel Corpus Annotated with Full Coreference (L18-1)

Copied to clipboard

Challenge: Recent research in multilingual coreference and automatic pronoun translation has led to important insights into the problem and some promising results.
Approach: They propose a corpus annotated with full coreference chains that addresses a problem that machine translation and other multilingual natural language processing (NLP) technologies face: translation of coreference across languages.
Outcome: The proposed corpus contains parallel texts for the language pair English-German, two major European languages.
ParCorFull2.0: a Parallel Corpus Annotated with Full Coreference (2022.lrec-1)

Copied to clipboard

Challenge: Existing corpus ParCorFull contains parallel texts for English-German, French and Portuguese . translation of coreference across languages is challenging for MT and other NLP applications .
Approach: They describe a parallel corpus annotated with full coreference chains for multiple languages . they use the existing corpus ParCorFull to study translation of coreference across languages - a challenge for machine translation and NLP .
Outcome: The proposed corpus addresses translation of coreference across languages, a problem still challenging for machine translation and other multilingual natural language processing applications.
A Dataset of Offensive Language in Kosovo Social Media (2022.lrec-1)

Copied to clipboard

Challenge: Social media are a central part of people’s lives but are rife with bullying and offensive language, creating an unsafe environment for their users.
Approach: They propose to use user-generated comments on Facebook and YouTube from selected Kosovo news platforms to annotate offensive language in Albanian.
Outcome: The proposed system improves on Danish but not Albanian, on offensive language recognition and distinguishing targeted and untargeted offence.
Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity (2022.findings-emnlp)

Copied to clipboard

Challenge: Using low-resource languages, we assess the quality of uncertainty estimates from a wide array of approaches, but with more data.
Approach: They train models on sub-sampled datasets in three different languages to assess the confidence of a neural classifier.
Outcome: The proposed models train on sub-sampled datasets in three different languages and show that the quality of uncertainty estimates suffers with more data.
Getting Gender Right in Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: linguistics studies show that the language used by males and females differs in terms of style and syntax.
Approach: They integrate gender information into NMT systems to improve translation quality for multiple language pairs by incorporating gender information to a large dataset.
Outcome: The proposed system significantly improves translation quality for some language pairs.
Automatic Reference-Based Evaluation of Pronoun Translation Misses the Point (D18-1)

Copied to clipboard

Challenge: a range of issues limit the performance of the automated metrics.
Approach: They propose to use semi-automatic metrics and test suites instead of fully automatic metrics for pronoun translation.
Outcome: The proposed metrics improve translation accuracy by comparing them against a manually annotated dataset . the proposed metrics are semi-automatic and test suites in place of fully automatic metrics.
Exploiting Cross-Lingual Hints to Discover Event Pronouns (2020.lrec-1)

Copied to clipboard

Challenge: Non-nominal co-reference is much less studied than nominal coreference because of the lack of annotated corpora.
Approach: They propose to use parallel multilingual corpora to create artificially labeled data for the classification of three different readings of the English pronoun ‘it’: entity, event or pleonastic.
Outcome: The proposed method can be used to classify three different readings of the English pronoun ‘it’ from their translation in several languages.
Experimental Standards for Deep Learning in Natural Language Processing Research (2022.findings-emnlp)

Copied to clipboard

Challenge: a lack of common experimental standards remains an open challenge to the field at large .
Approach: They propose to distill discussions on experimental standards into a single, widely-applicable methodology.
Outcome: Using best practices, we can strengthen experimental evidence, improve reproducibility and enable scientific progress.
Code Like Humans: A Multi-Agent Solution for Medical Coding (2025.findings-emnlp)

Copied to clipboard

Challenge: In medical coding, experts map unstructured clinical notes to alphanumeric codes for diagnoses and procedures.
Approach: They introduce ‘Code Like Humans’: a new agentic framework for medical coding with large language models that implements official coding guidelines for human experts.
Outcome: The proposed framework implements official coding guidelines for human experts and can support the full ICD-10 coding system (+70K labels).
Parallel Data Helps Neural Entity Coreference Resolution (2023.findings-acl)

Copied to clipboard

Challenge: Current neural coreference models are trained on monolingual annotated data but annotating such coreference information is expensive and challenging.
Approach: They propose a simple yet effective model to exploit coreference knowledge from parallel data.
Outcome: The proposed model improves on the OntoNotes 5.0 English dataset by 1.74 percentage points . it is based on an unsupervised module learning coreference from annotations .
Multimodal Extraction and Recognition of Arabic Implicit Discourse Relations (2025.coling-main)

Copied to clipboard

Challenge: Identifying implicit discourse relations in written text is challenging, but it is also crucial to understand them in spoken discourse.
Approach: They propose a method for implicit discourse relation identification that uses audio and text data to extract semantically equivalent pairs of implicit and explicit discourse markers.
Outcome: The proposed method outperforms audio-based models but can be augmented by combining text and audio features.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations