Ulf Leser


BEEDS: Large-Scale Biomedical Event Extraction using Distant Supervision and Question Answering
Xing David Wang | Ulf Leser | Leon Weber
Proceedings of the 21st Workshop on Biomedical Language Processing

Automatic extraction of event structures from text is a promising way to extract important facts from the evergrowing amount of biomedical literature. We propose BEEDS, a new approach on how to mine event structures from PubMed based on a question-answering paradigm. Using a three-step pipeline comprising a document retriever, a document reader, and an entity normalizer, BEEDS is able to fully automatically extract event triples involving a query protein or gene and to store this information directly in a knowledge base. BEEDS applies a transformer-based architecture for event extraction and uses distant supervision to augment the scarce training data in event mining. In a knowledge base population setting, it outperforms a strong baseline in finding post-translational modification events consisting of enzyme-substrate-site triples while achieving competitive results in extracting binary relations consisting of protein-protein and protein-site interactions.


Extend, don’t rebuild: Phrasing conditional graph modification as autoregressive sequence labelling
Leon Weber | Jannes Münchmeyer | Samuele Garda | Ulf Leser
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Deriving and modifying graphs from natural language text has become a versatile basis technology for information extraction with applications in many subfields, such as semantic parsing or knowledge graph construction. A recent work used this technique for modifying scene graphs (He et al. 2020), by first encoding the original graph and then generating the modified one based on this encoding. In this work, we show that we can considerably increase performance on this problem by phrasing it as graph extension instead of graph generation. We propose the first model for the resulting graph extension problem based on autoregressive sequence labelling. On three scene graph modification data sets, this formulation leads to improvements in accuracy over the state-of-the-art between 13 and 24 percentage points. Furthermore, we introduce a novel data set from the biomedical domain which has much larger linguistic variability and more complex graphs than the scene graph modification data sets. For this data set, the state-of-the art fails to generalize, while our model can produce meaningful predictions.

WBI at MEDIQA 2021: Summarizing Consumer Health Questions with Generative Transformers
Mario Sänger | Leon Weber | Ulf Leser
Proceedings of the 20th Workshop on Biomedical Language Processing

This paper describes our contribution for the MEDIQA-2021 Task 1 question summarization competition. We model the task as conditional generation problem. Our concrete pipeline performs a finetuning of the large pretrained generative transformers PEGASUS (Zhang et al.,2020a) and BART (Lewis et al.,2020). We used the resulting models as strong baselines and experimented with (i) integrating structured knowledge via entity embeddings, (ii) ensembling multiple generative models with the generator-discriminator framework and (iii) disentangling summarization and interrogative prediction to achieve further improvements.Our best performing model, a fine-tuned vanilla PEGASUS, reached the second place in the competition with an ROUGE-2-F1 score of 15.99. We observed that all of our additional measures hurt performance (up to 5.2 pp) on the official test set. In course of a post-hoc experimental analysis which uses a larger validation set results indicate slight performance improvements through the proposed extensions. However, further analysis is need to provide stronger evidence.

Early Detection of Sexual Predators in Chats
Matthias Vogt | Ulf Leser | Alan Akbik
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

An important risk that children face today is online grooming, where a so-called sexual predator establishes an emotional connection with a minor online with the objective of sexual abuse. Prior work has sought to automatically identify grooming chats, but only after an incidence has already happened in the context of legal prosecution. In this work, we instead investigate this problem from the point of view of prevention. We define and study the task of early sexual predator detection (eSPD) in chats, where the goal is to analyze a running chat from its beginning and predict grooming attempts as early and as accurately as possible. We survey existing datasets and their limitations regarding eSPD, and create a new dataset called PANC for more realistic evaluations. We present strong baselines built on BERT that also reach state-of-the-art results for conventional SPD. Finally, we consider coping with limited computational resources, as real-life applications require eSPD on mobile devices.


Biomedical Event Extraction as Multi-turn Question Answering
Xing David Wang | Leon Weber | Ulf Leser
Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis

Biomedical event extraction from natural text is a challenging task as it searches for complex and often nested structures describing specific relationships between multiple molecular entities, such as genes, proteins, or cellular components. It usually is implemented by a complex pipeline of individual tools to solve the different relation extraction subtasks. We present an alternative approach where the detection of relationships between entities is described uniformly as questions, which are iteratively answered by a question answering (QA) system based on the domain-specific language model SciBERT. This model outperforms two strong baselines in two biomedical event extraction corpora in a Knowledge Base Population setting, and also achieves competitive performance in BioNLP challenge evaluation settings.


NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
Leon Weber | Pasquale Minervini | Jannes Münchmeyer | Ulf Leser | Tim Rocktäschel
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Rule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge. However, such systems are difficult to apply to problems involving natural language, due to its large linguistic variability. In contrast, neural models can cope very well with ambiguity by learning distributed representations of words and their composition from data, but lead to models that are difficult to interpret. In this paper, we describe a model combining neural networks with logic programming in a novel manner for solving multi-hop reasoning tasks over natural language. Specifically, we propose to use an Prolog prover which we extend to utilize a similarity function over pretrained sentence encoders. We fine-tune the representations for the similarity function via backpropagation. This leads to a system that can apply rule-based reasoning to natural language, and induce domain-specific natural language rules from training data. We evaluate the proposed system on two different question answering tasks, showing that it outperforms two baselines – BiDAF (Seo et al., 2016a) and FastQA( Weissenborn et al., 2017) on a subset of the WikiHop corpus and achieves competitive results on the MedHop data set (Welbl et al., 2017).


Identifying Key Sentences for Precision Oncology Using Semi-Supervised Learning
Jurica Ševa | Martin Wackerbauer | Ulf Leser
Proceedings of the BioNLP 2018 workshop

We present a machine learning pipeline that identifies key sentences in abstracts of oncological articles to aid evidence-based medicine. This problem is characterized by the lack of gold standard datasets, data imbalance and thematic differences between available silver standard corpora. Additionally, available training and target data differs with regard to their domain (professional summaries vs. sentences in abstracts). This makes supervised machine learning inapplicable. We propose the use of two semi-supervised machine learning approaches: To mitigate difficulties arising from heterogeneous data sources, overcome data imbalance and create reliable training data we propose using transductive learning from positive and unlabelled data (PU Learning). For obtaining a realistic classification model, we propose the use of abstracts summarised in relevant sentences as unlabelled examples through Self-Training. The best model achieves 84% accuracy and 0.84 F1 score on our dataset


SCARE ― The Sentiment Corpus of App Reviews with Fine-grained Annotations in German
Mario Sänger | Ulf Leser | Steffen Kemmerer | Peter Adolphs | Roman Klinger
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

The automatic analysis of texts containing opinions of users about, e.g., products or political views has gained attention within the last decades. However, previous work on the task of analyzing user reviews about mobile applications in app stores is limited. Publicly available corpora do not exist, such that a comparison of different methods and models is difficult. We fill this gap by contributing the Sentiment Corpus of App Reviews (SCARE), which contains fine-grained annotations of application aspects, subjective (evaluative) phrases and relations between both. This corpus consists of 1,760 annotated application reviews from the Google Play Store with 2,487 aspects and 3,959 subjective phrases. We describe the process and methodology how the corpus was created. The Fleiss Kappa between four annotators reveals an agreement of 0.72. We provide a strong baseline with a linear-chain conditional random field and word-embedding features with a performance of 0.62 for aspect detection and 0.63 for the extraction of subjective phrases. The corpus is available to the research community to support the development of sentiment analysis methods on mobile application reviews.


WBI-NER: The impact of domain-specific features on the performance of identifying and classifying mentions of drugs
Tim Rocktäschel | Torsten Huber | Michael Weidlich | Ulf Leser
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)

WBI-DDI: Drug-Drug Interaction Extraction using Majority Voting
Philippe Thomas | Mariana Neves | Tim Rocktäschel | Ulf Leser
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)


pdf bib
Not all links are equal: Exploiting Dependency Types for the Extraction of Protein-Protein Interactions from Text
Philippe Thomas | Stefan Pietschmann | Illés Solt | Domonkos Tikk | Ulf Leser
Proceedings of BioNLP 2011 Workshop

Learning Protein–Protein Interaction Extraction using Distant Supervision
Philippe Thomas | Illés Solt | Roman Klinger | Ulf Leser
Proceedings of Workshop on Robust Unsupervised and Semisupervised Methods in Natural Language Processing


Molecular event extraction from Link Grammar parse trees
Jörg Hakenberg | Illés Solt | Domonkos Tikk | Luis Tari | Astrid Rheinländer | Nguyen Quang Long | Graciela Gonzalez | Ulf Leser
Proceedings of the BioNLP 2009 Workshop Companion Volume for Shared Task