Leonhard Hennig


2023

pdf bib
Factuality Detection using Machine Translation – a Use Case for German Clinical Text
Mohammed Bin Sumait | Aleksandra Gabryszak | Leonhard Hennig | Roland A. Roller
Proceedings of the 19th Conference on Natural Language Processing (KONVENS 2023)

pdf bib
MultiTACRED: A Multilingual Version of the TAC Relation Extraction Dataset
Leonhard Hennig | Philippe Thomas | Sebastian Möller
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Relation extraction (RE) is a fundamental task in information extraction, whose extension to multilingual settings has been hindered by the lack of supervised resources comparable in size to large English datasets such as TACRED (Zhang et al., 2017). To address this gap, we introduce the MultiTACRED dataset, covering 12 typologically diverse languages from 9 language families, which is created by machine-translating TACRED instances and automatically projecting their entity annotations. We analyze translation and annotation projection quality, identify error categories, and experimentally evaluate fine-tuned pretrained mono- and multilingual language models in common transfer learning scenarios. Our analyses show that machine translation is a viable strategy to transfer RE instances, with native speakers judging more than 83% of the translated instances to be linguistically and semantically acceptable. We find monolingual RE model performance to be comparable to the English original for many of the target languages, and that multilingual models trained on a combination of English and target language data can outperform their monolingual counterparts. However, we also observe a variety of translation and annotation projection errors, both due to the MT systems and linguistic features of the target languages, such as pronoun-dropping, compounding and inflection, that degrade dataset quality and RE model performance.

pdf bib
Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods
Nils Feldhus | Leonhard Hennig | Maximilian Dustin Nasert | Christopher Ebert | Robert Schwarzenberg | Sebastian Möller
Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE)

Saliency maps can explain a neural model’s predictions by identifying important input features. They are difficult to interpret for laypeople, especially for instances with many features. In order to make them more accessible, we formalize the underexplored task of translating saliency maps into natural language and compare methods that address two key challenges of this approach – what and how to verbalize. In both automatic and human evaluation setups, using token-level attributions from text classification tasks, we compare two novel methods (search-based and instruction-based verbalizations) against conventional feature importance representations (heatmap visualizations and extractive rationales), measuring simulatability, faithfulness, helpfulness and ease of understanding. Instructing GPT-3.5 to generate saliency map verbalizations yields plausible explanations which include associations, abstractive summarization and commonsense reasoning, achieving by far the highest human ratings, but they are not faithfully capturing numeric information and are inconsistent in their interpretation of the task. In comparison, our search-based, model-free verbalization approach efficiently completes templated verbalizations, is faithful by design, but falls short in helpfulness and simulatability. Our results suggest that saliency map verbalization makes feature attribution explanations more comprehensible and less cognitively challenging to humans than conventional representations.

2022

pdf bib
Full-Text Argumentation Mining on Scientific Publications
Arne Binder | Leonhard Hennig | Bhuvanesh Verma
Proceedings of the first Workshop on Information Extraction from Scientific Publications

Scholarly Argumentation Mining (SAM) has recently gained attention due to its potential to help scholars with the rapid growth of published scientific literature. It comprises two subtasks: argumentative discourse unit recognition (ADUR) and argumentative relation extraction (ARE), both of which are challenging since they require e.g. the integration of domain knowledge, the detection of implicit statements, and the disambiguation of argument structure. While previous work focused on dataset construction and baseline methods for specific document sections, such as abstract or results, full-text scholarly argumentation mining has seen little progress. In this work, we introduce a sequential pipeline model combining ADUR and ARE for full-text SAM, and provide a first analysis of the performance of pretrained language models (PLMs) on both subtasks. We establish a new SotA for ADUR on the Sci-Arg corpus, outperforming the previous best reported result by a large margin (+7% F1). We also present the first results for ARE, and thus for the full AM pipeline, on this benchmark dataset. Our detailed error analysis reveals that non-contiguous ADUs as well as the interpretation of discourse connectors pose major challenges and that data annotation needs to be more consistent.

pdf bib
Why only Micro-F1? Class Weighting of Measures for Relation Classification
David Harbecke | Yuxuan Chen | Leonhard Hennig | Christoph Alt
Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP

Relation classification models are conventionally evaluated using only a single measure, e.g., micro-F1, macro-F1 or AUC. In this work, we analyze weighting schemes, such as micro and macro, for imbalanced datasets. We introduce a framework for weighting schemes, where existing schemes are extremes, and two new intermediate schemes. We show that reporting results of different weighting schemes better highlights strengths and weaknesses of a model.

pdf bib
Multilingual Relation Classification via Efficient and Effective Prompting
Yuxuan Chen | David Harbecke | Leonhard Hennig
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Prompting pre-trained language models has achieved impressive performance on various NLP tasks, especially in low data regimes. Despite the success of prompting in monolingual settings, applying prompt-based methods in multilingual scenarios has been limited to a narrow set of tasks, due to the high cost of handcrafting multilingual prompts. In this paper, we present the first work on prompt-based multilingual relation classification (RC), by introducing an efficient and effective method that constructs prompts from relation triples and involves only minimal translation for the class labels. We evaluate its performance in fully supervised, few-shot and zero-shot scenarios, and analyze its effectiveness across 14 languages, prompt variants, and English-task training in cross-lingual settings. We find that in both fully supervised and few-shot scenarios, our prompt method beats competitive baselines: fine-tuning XLM-R_EM and null prompts. It also outperforms the random baseline by a large margin in zero-shot experiments. Our method requires little in-language knowledge and can be used as a strong baseline for similar multilingual classification tasks.

pdf bib
A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity Recognition
Yuxuan Chen | Jonas Mikkelsen | Arne Binder | Christoph Alt | Leonhard Hennig
Proceedings of the 7th Workshop on Representation Learning for NLP

Pre-trained language models (PLM) are effective components of few-shot named entity recognition (NER) approaches when augmented with continued pre-training on task-specific out-of-domain data or fine-tuning on in-domain data. However, their performance in low-resource scenarios, where such data is not available, remains an open question. We introduce an encoder evaluation framework, and use it to systematically compare the performance of state-of-the-art pre-trained representations on the task of low-resource NER. We analyze a wide range of encoders pre-trained with different strategies, model architectures, intermediate-task fine-tuning, and contrastive learning. Our experimental results across ten benchmark NER datasets in English and German show that encoder performance varies significantly, suggesting that the choice of encoder for a specific low-resource scenario needs to be carefully evaluated.

2021

pdf bib
MobIE: A German Dataset for Named Entity Recognition, Entity Linking and Relation Extraction in the Mobility Domain
Leonhard Hennig | Phuc Tran Truong | Aleksandra Gabryszak
Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021)

2020

pdf bib
Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning
Hanchu Zhang | Leonhard Hennig | Christoph Alt | Changjian Hu | Yao Meng | Chao Wang
Proceedings of the 3rd Workshop on e-Commerce and NLP

In this work, we introduce a bootstrapped, iterative NER model that integrates a PU learning algorithm for recognizing named entities in a low-resource setting. Our approach combines dictionary-based labeling with syntactically-informed label expansion to efficiently enrich the seed dictionaries. Experimental results on a dataset of manually annotated e-commerce product descriptions demonstrate the effectiveness of the proposed framework.

pdf bib
Defx at SemEval-2020 Task 6: Joint Extraction of Concepts and Relations for Definition Extraction
Marc Hübner | Christoph Alt | Robert Schwarzenberg | Leonhard Hennig
Proceedings of the Fourteenth Workshop on Semantic Evaluation

Definition Extraction systems are a valuable knowledge source for both humans and algorithms. In this paper we describe our submissions to the DeftEval shared task (SemEval-2020 Task 6), which is evaluated on an English textbook corpus. We provide a detailed explanation of our system for the joint extraction of definition concepts and the relations among them. Furthermore we provide an ablation study of our model variations and describe the results of an error analysis.

pdf bib
Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling
Dmitrii Aksenov | Julian Moreno-Schneider | Peter Bourgonje | Robert Schwarzenberg | Leonhard Hennig | Georg Rehm
Proceedings of the Twelfth Language Resources and Evaluation Conference

We explore to what extent knowledge about the pre-trained language model that is used is beneficial for the task of abstractive summarization. To this end, we experiment with conditioning the encoder and decoder of a Transformer-based neural model on the BERT language model. In addition, we propose a new method of BERT-windowing, which allows chunk-wise processing of texts longer than the BERT window size. We also explore how locality modeling, i.e., the explicit restriction of calculations to the local context, can affect the summarization ability of the Transformer. This is done by introducing 2-dimensional convolutional self-attention into the first layers of the encoder. The results of our models are compared to a baseline and the state-of-the-art models on the CNN/Daily Mail dataset. We additionally train our model on the SwissText dataset to demonstrate usability on German. Both models outperform the baseline in ROUGE scores on two datasets and show its superiority in a manual qualitative analysis.

pdf bib
Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction
Christoph Alt | Aleksandra Gabryszak | Leonhard Hennig
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Despite the recent progress, little is known about the features captured by state-of-the-art neural relation extraction (RE) models. Common methods encode the source sentence, conditioned on the entity mentions, before classifying the relation. However, the complexity of the task makes it difficult to understand how encoder architecture and supporting linguistic knowledge affect the features learned by the encoder. We introduce 14 probing tasks targeting linguistic properties relevant to RE, and we use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets, TACRED and SemEval 2010 Task 8. We find that the bias induced by the architecture and the inclusion of linguistic features are clearly expressed in the probing task performance. For example, adding contextualized word representations greatly increases performance on probing tasks with a focus on named entity and part-of-speech information, and yields better results in RE. In contrast, entity masking improves RE, but considerably lowers performance on entity type related probing tasks.

pdf bib
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task
Christoph Alt | Aleksandra Gabryszak | Leonhard Hennig
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

TACRED is one of the largest, most widely used crowdsourced datasets in Relation Extraction (RE). But, even with recent advances in unsupervised pre-training and knowledge enhanced neural RE, models still show a high error rate. In this paper, we investigate the questions: Have we reached a performance ceiling or is there still room for improvement? And how do crowd annotations, dataset, and models contribute to this error rate? To answer these questions, we first validate the most challenging 5K examples in the development and test sets using trained annotators. We find that label errors account for 8% absolute F1 test error, and that more than 50% of the examples need to be relabeled. On the relabeled test set the average F1 score of a large baseline model set improves from 62.1 to 70.1. After validation, we analyze misclassifications on the challenging instances, categorize them into linguistically motivated error groups, and verify the resulting error hypotheses on three state-of-the-art RE models. We show that two groups of ambiguous relations are responsible for most of the remaining errors and that models may adopt shallow heuristics on the dataset when entities are not masked.

2019

pdf bib
Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction
Christoph Alt | Marc Hübner | Leonhard Hennig
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Distantly supervised relation extraction is widely used to extract relational facts from text, but suffers from noisy labels. Current relation extraction methods try to alleviate the noise by multi-instance learning and by providing supporting linguistic and contextual information to more efficiently guide the relation classification. While achieving state-of-the-art results, we observed these models to be biased towards recognizing a limited set of relations with high precision, while ignoring those in the long tail. To address this gap, we utilize a pre-trained language model, the OpenAI Generative Pre-trained Transformer (GPT) (Radford et al., 2018). The GPT and similar models have been shown to capture semantic and syntactic features, and also a notable amount of “common-sense” knowledge, which we hypothesize are important features for recognizing a more diverse set of relations. By extending the GPT to the distantly supervised setting, and fine-tuning it on the NYT10 dataset, we show that it predicts a larger set of distinct relation types with high confidence. Manual and automated evaluation of our model shows that it achieves a state-of-the-art AUC score of 0.422 on the NYT10 dataset, and performs especially well at higher recall levels.

pdf bib
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers
Robert Schwarzenberg | Marc Hübner | David Harbecke | Christoph Alt | Leonhard Hennig
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)

Representations in the hidden layers of Deep Neural Networks (DNN) are often hard to interpret since it is difficult to project them into an interpretable domain. Graph Convolutional Networks (GCN) allow this projection, but existing explainability methods do not exploit this fact, i.e. do not focus their explanations on intermediate states. In this work, we present a novel method that traces and visualizes features that contribute to a classification decision in the visible and hidden layers of a GCN. Our method exposes hidden cross-layer dynamics in the input graph structure. We experimentally demonstrate that it yields meaningful layerwise explanations for a GCN sentence classifier.

2018

pdf bib
Learning Comment Controversy Prediction in Web Discussions Using Incidentally Supervised Multi-Task CNNs
Nils Rethmeier | Marc Hübner | Leonhard Hennig
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

Comments on web news contain controversies that manifest as inter-group agreement-conflicts. Tracking such rapidly evolving controversy could ease conflict resolution or journalist-user interaction. However, this presupposes controversy online-prediction that scales to diverse domains using incidental supervision signals instead of manual labeling. To more deeply interpret comment-controversy model decisions we frame prediction as binary classification and evaluate baselines and multi-task CNNs that use an auxiliary news-genre-encoder. Finally, we use ablation and interpretability methods to determine the impacts of topic, discourse and sentiment indicators, contextual vs. global word influence, as well as genre-keywords vs. per-genre-controversy keywords – to find that the models learn plausible controversy features using only incidentally supervised signals.

pdf bib
A German Corpus for Fine-Grained Named Entity Recognition and Relation Extraction of Traffic and Industry Events
Martin Schiersch | Veselina Mironova | Maximilian Schmitt | Philippe Thomas | Aleksandra Gabryszak | Leonhard Hennig
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
A Corpus Study and Annotation Schema for Named Entity Recognition and Relation Extraction of Business Products
Saskia Schön | Veselina Mironova | Aleksandra Gabryszak | Leonhard Hennig
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2017

pdf bib
Streaming Text Analytics for Real-Time Event Recognition
Philippe Thomas | Johannes Kirschnick | Leonhard Hennig | Renlong Ai | Sven Schmeier | Holmer Hemsen | Feiyu Xu | Hans Uszkoreit
Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017

A huge body of continuously growing written knowledge is available on the web in the form of social media posts, RSS feeds, and news articles. Real-time information extraction from such high velocity, high volume text streams requires scalable, distributed natural language processing pipelines. We introduce such a system for fine-grained event recognition within the big data framework Flink, and demonstrate its capabilities for extracting and geo-locating mobility- and industry-related events from heterogeneous text sources. Performance analyses conducted on several large datasets show that our system achieves high throughput and maintains low latency, which is crucial when events need to be detected and acted upon in real-time. We also present promising experimental results for the event extraction component of our system, which recognizes a novel set of event types. The demo system is available at http://dfki.de/sd4m-sta-demo/.

pdf bib
Common Round: Application of Language Technologies to Large-Scale Web Debates
Hans Uszkoreit | Aleksandra Gabryszak | Leonhard Hennig | Jörg Steffen | Renlong Ai | Stephan Busemann | Jon Dehdari | Josef van Genabith | Georg Heigold | Nils Rethmeier | Raphael Rubino | Sven Schmeier | Philippe Thomas | He Wang | Feiyu Xu
Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics

Web debates play an important role in enabling broad participation of constituencies in social, political and economic decision-taking. However, it is challenging to organize, structure, and navigate a vast number of diverse argumentations and comments collected from many participants over a long time period. In this paper we demonstrate Common Round, a next generation platform for large-scale web debates, which provides functions for eliciting the semantic content and structures from the contributions of participants. In particular, Common Round applies language technologies for the extraction of semantic essence from textual input, aggregation of the formulated opinions and arguments. The platform also provides a cross-lingual access to debates using machine translation.

2016

pdf bib
Relation- and Phrase-level Linking of FrameNet with Sar-graphs
Aleksandra Gabryszak | Sebastian Krause | Leonhard Hennig | Feiyu Xu | Hans Uszkoreit
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

Recent research shows the importance of linking linguistic knowledge resources for the creation of large-scale linguistic data. We describe our approach for combining two English resources, FrameNet and sar-graphs, and illustrate the benefits of the linked data in a relation extraction setting. While FrameNet consists of schematic representations of situations, linked to lexemes and their valency patterns, sar-graphs are knowledge resources that connect semantic relations from factual knowledge graphs to the linguistic phrases used to express instances of these relations. We analyze the conceptual similarities and differences of both resources and propose to link sar-graphs and FrameNet on the levels of relations/frames as well as phrases. The former alignment involves a manual ontology mapping step, which allows us to extend sar-graphs with new phrase patterns from FrameNet. The phrase-level linking, on the other hand, is fully automatic. We investigate the quality of the automatically constructed links and identify two main classes of errors.

pdf bib
TEG-REP: A corpus of Textual Entailment Graphs based on Relation Extraction Patterns
Kathrin Eichler | Feiyu Xu | Hans Uszkoreit | Leonhard Hennig | Sebastian Krause
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

The task of relation extraction is to recognize and extract relations between entities or concepts in texts. Dependency parse trees have become a popular source for discovering extraction patterns, which encode the grammatical relations among the phrases that jointly express relation instances. State-of-the-art weakly supervised approaches to relation extraction typically extract thousands of unique patterns only potentially expressing the target relation. Among these patterns, some are semantically equivalent, but differ in their morphological, lexical-semantic or syntactic form. Some express a relation that entails the target relation. We propose a new approach to structuring extraction patterns by utilizing entailment graphs, hierarchical structures representing entailment relations, and present a novel resource of gold-standard entailment graphs based on a set of patterns automatically acquired using distant supervision. We describe the methodology used for creating the dataset and present statistics of the resource as well as an analysis of inference types underlying the entailment decisions.

pdf bib
Real-Time Discovery and Geospatial Visualization of Mobility and Industry Events from Large-Scale, Heterogeneous Data Streams
Leonhard Hennig | Philippe Thomas | Renlong Ai | Johannes Kirschnick | He Wang | Jakob Pannier | Nora Zimmermann | Sven Schmeier | Feiyu Xu | Jan Ostwald | Hans Uszkoreit
Proceedings of ACL-2016 System Demonstrations

2015

pdf bib
Multi-Objective Optimization for the Joint Disambiguation of Nouns and Named Entities
Dirk Weissenborn | Leonhard Hennig | Feiyu Xu | Hans Uszkoreit
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

pdf bib
A Web-based Collaborative Evaluation Tool for Automatically Learned Relation Extraction Patterns
Leonhard Hennig | Hong Li | Sebastian Krause | Feiyu Xu | Hans Uszkoreit
Proceedings of ACL-IJCNLP 2015 System Demonstrations

pdf bib
Sar-graphs: A Linked Linguistic Knowledge Resource Connecting Facts with Language
Sebastian Krause | Leonhard Hennig | Aleksandra Gabryszak | Feiyu Xu | Hans Uszkoreit
Proceedings of the 4th Workshop on Linked Data in Linguistics: Resources and Applications

2012

pdf bib
GerNED: A German Corpus for Named Entity Disambiguation
Danuta Ploch | Leonhard Hennig | Angelina Duka | Ernesto William De Luca | Sahin Albayrak
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)

Determining the real-world referents for name mentions of persons, organizations and other named entities in texts has become an important task in many information retrieval scenarios and is referred to as Named Entity Disambiguation (NED). While comprehensive datasets support the development and evaluation of NED approaches for English, there are no public datasets to assess NED systems for other languages, such as German. This paper describes the construction of an NED dataset based on a large corpus of German news articles. The dataset is closely modeled on the datasets used for the Knowledge Base Population tasks of the Text Analysis Conference, and contains gold standard annotations for the NED tasks of Entity Linking, NIL Detection and NIL Clustering. We also present first experimental results on the new dataset for each of these tasks in order to establish a baseline for future research efforts.

2010

pdf bib
Learning Summary Content Units with Topic Modeling
Leonhard Hennig | Ernesto William De Luca | Sahin Albayrak
Coling 2010: Posters

2009

pdf bib
Topic-based Multi-Document Summarization with Probabilistic Latent Semantic Analysis
Leonhard Hennig
Proceedings of the International Conference RANLP-2009