Papers by Guenter Neumann
Wikinflection Corpus: A (Better) Multilingual, Morpheme-Annotated Inflectional Corpus (2020.lrec-1)
Copied to clipboard
| Challenge: | Inflectional corpora with annotated morpheme boundaries are scarce in the NLP community . a generated, multilingual inflectional lexicon with morphological features is not as good as UniMorph's . |
| Approach: | They evaluate a multilingual inflectional corpus with morpheme boundaries from the English Wiktionary and the UniMorph project's inflection corpus. |
| Outcome: | The generated Wikinflection corpus is not as good as UniMorph's, but extracts significant amount of words from the intersection of the two corpora. |
Team DOMLIN: Exploiting Evidence Enhancement for the FEVER Shared Task (D19-66)
Copied to clipboard
| Challenge: | Existing methods of fact checking are based on the assignment of a truth value to a given (factual) statement, and therefore it is desirable to have access to the evidence used to reach an assignment. |
| Approach: | They propose a two-staged sentence selection strategy to account for examples in the dataset where evidence is not only conditioned on the claim, but also on previously retrieved evidence. |
| Outcome: | The proposed system beats the top performing systems of the first FEVER challenge which act as a baseline, beating 64.21% of the top-performing systems. |
MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Relation extraction in the biomedical domain is challenging due to the lack of labeled data and high annotation costs. |
| Approach: | They propose to use distant supervision to pair knowledge graph relationships with raw texts to tackle the scarcity of annotated data and to validate their results. |
| Outcome: | The proposed benchmarks are more accurate and consistent with existing benchmarks and show that there is no train-test leakage. |
T2NER: Transformers based Transfer Learning Framework for Named Entity Recognition (2021.eacl-demos)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is an important task in information extraction due to large variations in entity names and flexibility in how entities are mentioned. |
| Approach: | They propose a Transformers based Transfer Learning framework for Named Entity Recognition (T2NER) that integrates transformer models with the state-of-the-art in NLP and provides a unified platform for transfer learning. |
| Outcome: | The proposed framework bridges the gap between the state-of-the-art in transformer models and the state of the art in NER with deep transformer models. |
AutoEQA: Auto-Encoding Questions for Extractive Question Answering (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Extractive question answering models are reliant on annotations of answer-spans in the corresponding passages. |
| Approach: | They propose a method that auto-encodes a question and generates corresponding questions from it. |
| Outcome: | The proposed method performs well in a zero-shot setting and can provide an additional loss to boost performance for extractive question answering (EQA). |