Alan Akbik


2024

pdf bib
Parameter-Efficient Fine-Tuning: Is There An Optimal Subset of Parameters to Tune?
Max Ploner | Alan Akbik
Findings of the Association for Computational Linguistics: EACL 2024

The ever-growing size of pretrained language models (PLM) presents a significant challenge for efficiently fine-tuning and deploying these models for diverse sets of tasks within memory-constrained environments.In light of this, recent research has illuminated the possibility of selectively updating only a small subset of a model’s parameters during the fine-tuning process.Since no new parameters or modules are added, these methods retain the inference speed of the original model and come at no additional computational cost. However, an open question pertains to which subset of parameters should best be tuned to maximize task performance and generalizability. To investigate, this paper presents comprehensive experiments covering a large spectrum of subset selection strategies. We comparatively evaluate their impact on model performance as well as the resulting model’s capability to generalize to different tasks.Surprisingly, we find that the gains achieved in performance by elaborate selection strategies are, at best, marginal when compared to the outcomes obtained by tuning a random selection of parameter subsets. Our experiments also indicate that selection-based tuning impairs generalizability to new tasks.

pdf bib
Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition
Jonas Golde | Felix Hamborg | Alan Akbik
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Few-shot named entity recognition (NER) detects named entities within text using only a few annotated examples. One promising line of research is to leverage natural language descriptions of each entity type: the common label PER might, for example, be verbalized as ”person entity.” In an initial label interpretation learning phase, the model learns to interpret such verbalized descriptions of entity types. In a subsequent few-shot tagset extension phase, this model is then given a description of a previously unseen entity type (such as ”music album”) and optionally a few training examples to perform few-shot NER for this type. In this paper, we systematically explore the impact of a strong semantic prior to interpret verbalizations of new entity types by massively scaling up the number and granularity of entity types used for label interpretation learning. To this end, we leverage an entity linking benchmark to create a dataset with orders of magnitude of more distinct entity types and descriptions as currently used datasets. We find that this increased signal yields strong results in zero- and few-shot NER in in-domain, cross-domain, and even cross-lingual settings. Our findings indicate significant potential for improving few-shot NER through heuristical data-based optimization.

2023

pdf bib
CleanCoNLL: A Nearly Noise-Free Named Entity Recognition Dataset
Susanna Rücker | Alan Akbik
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

The CoNLL-03 corpus is arguably the most well-known and utilized benchmark dataset for named entity recognition (NER). However, prior works found significant numbers of annotation errors, incompleteness, and inconsistencies in the data. This poses challenges to objectively comparing NER approaches and analyzing their errors, as current state-of-the-art models achieve F1-scores that are comparable to or even exceed the estimated noise level in CoNLL-03. To address this issue, we present a comprehensive relabeling effort assisted by automatic consistency checking that corrects 7.0% of all labels in the English CoNLL-03. Our effort adds a layer of entity linking annotation both for better explainability of NER labels and as additional safeguard of annotation quality. Our experimental evaluation finds not only that state-of-the-art approaches reach significantly higher F1-scores (97.1%) on our data, but crucially that the share of correct predictions falsely counted as errors due to annotation noise drops from 47% to 6%. This indicates that our resource is well suited to analyze the remaining errors made by state-of-the-art models, and that the theoretical upper bound even on high resource, coarse-grained NER is not yet reached. To facilitate such analysis, we make CleanCoNLL publicly available to the research community.

pdf bib
Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs
Jonas Golde | Patrick Haller | Felix Hamborg | Julian Risch | Alan Akbik
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-intensive. Current research addresses this bottleneck by exploring a novel paradigm called zero-shot learning via dataset generation. Here, a powerful LLM is prompted with a task description to generate labeled data that can be used to train a downstream NLP model. For instance, an LLM might be prompted to “generate 500 movie reviews with positive overall sentiment, and another 500 with negative sentiment.” The generated data could then be used to train a binary sentiment classifier, effectively leveraging an LLM as a teacher to a smaller student model. With this demo, we introduce Fabricator, an open-source Python toolkit for dataset generation. Fabricator implements common dataset generation workflows, supports a wide range of downstream NLP tasks (such as text classification, question answering, and entity recognition), and is integrated with well-known libraries to facilitate quick experimentation. With Fabricator, we aim to support researchers in conducting reproducible dataset generation experiments using LLMs and help practitioners apply this approach to train models for downstream tasks.

pdf bib
ZELDA: A Comprehensive Benchmark for Supervised Entity Disambiguation
Marcel Milich | Alan Akbik
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Entity disambiguation (ED) is the task of disambiguating named entity mentions in text to unique entries in a knowledge base. Due to its industrial relevance, as well as current progress in leveraging pre-trained language models, a multitude of ED approaches have been proposed in recent years. However, we observe a severe lack of uniformity across experimental setups in current ED work,rendering a direct comparison of approaches based solely on reported numbers impossible: Current approaches widely differ in the data set used to train, the size of the covered entity vocabulary, and the usage of additional signals such as candidate lists. To address this issue, we present ZELDA , a novel entity disambiguation benchmark that includes a unified training data set, entity vocabulary, candidate lists, as well as challenging evaluation splits covering 8 different domains. We illustrate its design and construction, and present experiments in which we train and compare current state-of-the-art approaches on our benchmark. To encourage greater direct comparability in the entity disambiguation domain, we make our benchmark publicly available to the research community.

2022

pdf bib
Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning
Angelo Ziletti | Alan Akbik | Christoph Berns | Thomas Herold | Marion Legler | Martina Viell
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track

Medical coding (MC) is an essential pre-requisite for reliable data retrieval and reporting. Given a free-text reported term (RT) such as “pain of right thigh to the knee”, the task is to identify the matching lowest-level term (LLT) –in this case “unilateral leg pain”– from a very large and continuously growing repository of standardized medical terms. However, automating this task is challenging due to a large number of LLT codes (as of writing over 80\,000), limited availability of training data for long tail/emerging classes, and the general high accuracy demands of the medical domain.With this paper, we introduce the MC task, discuss its challenges, and present a novel approach called xTARS that combines traditional BERT-based classification with a recent zero/few-shot learning approach (TARS). We present extensive experiments that show that our combined approach outperforms strong baselines, especially in the few-shot regime. The approach is developed and deployed at Bayer, live since November 2021. As we believe our approach potentially promising beyond MC, and to ensure reproducibility, we release the code to the research community.

2021

pdf bib
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.

2020

pdf bib
Task-Aware Representation of Sentences for Generic Text Classification
Kishaloy Halder | Alan Akbik | Josip Krapac | Roland Vollgraf
Proceedings of the 28th International Conference on Computational Linguistics

State-of-the-art approaches for text classification leverage a transformer architecture with a linear layer on top that outputs a class distribution for a given prediction problem. While effective, this approach suffers from conceptual limitations that affect its utility in few-shot or zero-shot transfer learning scenarios. First, the number of classes to predict needs to be pre-defined. In a transfer learning setting, in which new classes are added to an already trained classifier, all information contained in a linear layer is therefore discarded, and a new layer is trained from scratch. Second, this approach only learns the semantics of classes implicitly from training examples, as opposed to leveraging the explicit semantic information provided by the natural language names of the classes. For instance, a classifier trained to predict the topics of news articles might have classes like “business” or “sports” that themselves carry semantic information. Extending a classifier to predict a new class named “politics” with only a handful of training examples would benefit from both leveraging the semantic information in the name of a new class and using the information contained in the already trained linear layer. This paper presents a novel formulation of text classification that addresses these limitations. It imbues the notion of the task at hand into the transformer model itself by factorizing arbitrary classification problems into a generic binary classification problem. We present experiments in few-shot and zero-shot transfer learning that show that our approach significantly outperforms previous approaches on small training data and can even learn to predict new classes with no training examples at all. The implementation of our model is publicly available at: https://github.com/flairNLP/flair.

2019

pdf bib
Pooled Contextualized Embeddings for Named Entity Recognition
Alan Akbik | Tanja Bergmann | Roland Vollgraf
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Contextual string embeddings are a recent type of contextualized word embedding that were shown to yield state-of-the-art results when utilized in a range of sequence labeling tasks. They are based on character-level language models which treat text as distributions over characters and are capable of generating embeddings for any string of characters within any textual context. However, such purely character-based approaches struggle to produce meaningful embeddings if a rare string is used in a underspecified context. To address this drawback, we propose a method in which we dynamically aggregate contextualized embeddings of each unique string that we encounter. We then use a pooling operation to distill a ”global” word representation from all contextualized instances. We evaluate these ”pooled contextualized embeddings” on common named entity recognition (NER) tasks such as CoNLL-03 and WNUT and show that our approach significantly improves the state-of-the-art for NER. We make all code and pre-trained models available to the research community for use and reproduction.

pdf bib
FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP
Alan Akbik | Tanja Bergmann | Duncan Blythe | Kashif Rasul | Stefan Schweter | Roland Vollgraf
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)

We present FLAIR, an NLP framework designed to facilitate training and distribution of state-of-the-art sequence labeling, text classification and language models. The core idea of the framework is to present a simple, unified interface for conceptually very different types of word and document embeddings. This effectively hides all embedding-specific engineering complexity and allows researchers to “mix and match” various embeddings with little effort. The framework also implements standard model training and hyperparameter selection routines, as well as a data fetching module that can download publicly available NLP datasets and convert them into data structures for quick set up of experiments. Finally, FLAIR also ships with a “model zoo” of pre-trained models to allow researchers to use state-of-the-art NLP models in their applications. This paper gives an overview of the framework and its functionality. The framework is available on GitHub at https://github.com/zalandoresearch/flair .

2018

pdf bib
Contextual String Embeddings for Sequence Labeling
Alan Akbik | Duncan Blythe | Roland Vollgraf
Proceedings of the 27th International Conference on Computational Linguistics

Recent advances in language modeling using recurrent neural networks have made it viable to model language as distributions over characters. By learning to predict the next character on the basis of previous characters, such models have been shown to automatically internalize linguistic concepts such as words, sentences, subclauses and even sentiment. In this paper, we propose to leverage the internal states of a trained character language model to produce a novel type of word embedding which we refer to as contextual string embeddings. Our proposed embeddings have the distinct properties that they (a) are trained without any explicit notion of words and thus fundamentally model words as sequences of characters, and (b) are contextualized by their surrounding text, meaning that the same word will have different embeddings depending on its contextual use. We conduct a comparative evaluation against previous embeddings and find that our embeddings are highly useful for downstream tasks: across four classic sequence labeling tasks we consistently outperform the previous state-of-the-art. In particular, we significantly outperform previous work on English and German named entity recognition (NER), allowing us to report new state-of-the-art F1-scores on the CoNLL03 shared task. We release all code and pre-trained language models in a simple-to-use framework to the research community, to enable reproduction of these experiments and application of our proposed embeddings to other tasks: https://github.com/zalandoresearch/flair

pdf bib
FEIDEGGER: A Multi-modal Corpus of Fashion Images and Descriptions in German
Leonidas Lefakis | Alan Akbik | Roland Vollgraf
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
ZAP: An Open-Source Multilingual Annotation Projection Framework
Alan Akbik | Roland Vollgraf
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2017

pdf bib
CROWD-IN-THE-LOOP: A Hybrid Approach for Annotating Semantic Roles
Chenguang Wang | Alan Akbik | Laura Chiticariu | Yunyao Li | Fei Xia | Anbang Xu
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Crowdsourcing has proven to be an effective method for generating labeled data for a range of NLP tasks. However, multiple recent attempts of using crowdsourcing to generate gold-labeled training data for semantic role labeling (SRL) reported only modest results, indicating that SRL is perhaps too difficult a task to be effectively crowdsourced. In this paper, we postulate that while producing SRL annotation does require expert involvement in general, a large subset of SRL labeling tasks is in fact appropriate for the crowd. We present a novel workflow in which we employ a classifier to identify difficult annotation tasks and route each task either to experts or crowd workers according to their difficulties. Our experimental evaluation shows that the proposed approach reduces the workload for experts by over two-thirds, and thus significantly reduces the cost of producing SRL annotation at little loss in quality.

pdf bib
The Projector: An Interactive Annotation Projection Visualization Tool
Alan Akbik | Roland Vollgraf
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Previous works proposed annotation projection in parallel corpora to inexpensively generate treebanks or propbanks for new languages. In this approach, linguistic annotation is automatically transferred from a resource-rich source language (SL) to translations in a target language (TL). However, annotation projection may be adversely affected by translational divergences between specific language pairs. For this reason, previous work often required careful qualitative analysis of projectability of specific annotation in order to define strategies to address quality and coverage issues. In this demonstration, we present THE PROJECTOR, an interactive GUI designed to assist researchers in such analysis: it allows users to execute and visually inspect annotation projection in a range of different settings. We give an overview of the GUI, discuss use cases and illustrate how the tool can facilitate discussions with the research community.

2016

pdf bib
POLYGLOT: Multilingual Semantic Role Labeling with Unified Labels
Alan Akbik | Yunyao Li
Proceedings of ACL-2016 System Demonstrations

pdf bib
Towards Semi-Automatic Generation of Proposition Banks for Low-Resource Languages
Alan Akbik | Vishwajeet Kumar | Yunyao Li
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
K-SRL: Instance-based Learning for Semantic Role Labeling
Alan Akbik | Yunyao Li
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Semantic role labeling (SRL) is the task of identifying and labeling predicate-argument structures in sentences with semantic frame and role labels. A known challenge in SRL is the large number of low-frequency exceptions in training data, which are highly context-specific and difficult to generalize. To overcome this challenge, we propose the use of instance-based learning that performs no explicit generalization, but rather extrapolates predictions from the most similar instances in the training data. We present a variant of k-nearest neighbors (kNN) classification with composite features to identify nearest neighbors for SRL. We show that high-quality predictions can be derived from a very small number of similar instances. In a comparative evaluation we experimentally demonstrate that our instance-based learning approach significantly outperforms current state-of-the-art systems on both in-domain and out-of-domain data, reaching F1-scores of 89,28% and 79.91% respectively.

pdf bib
Multilingual Aliasing for Auto-Generating Proposition Banks
Alan Akbik | Xinyu Guan | Yunyao Li
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Semantic Role Labeling (SRL) is the task of identifying the predicate-argument structure in sentences with semantic frame and role labels. For the English language, the Proposition Bank provides both a lexicon of all possible semantic frames and large amounts of labeled training data. In order to expand SRL beyond English, previous work investigated automatic approaches based on parallel corpora to automatically generate Proposition Banks for new target languages (TLs). However, this approach heuristically produces the frame lexicon from word alignments, leading to a range of lexicon-level errors and inconsistencies. To address these issues, we propose to manually alias TL verbs to existing English frames. For instance, the German verb drehen may evoke several meanings, including “turn something” and “film something”. Accordingly, we alias the former to the frame TURN.01 and the latter to a group of frames that includes FILM.01 and SHOOT.03. We execute a large-scale manual aliasing effort for three target languages and apply the new lexicons to automatically generate large Proposition Banks for Chinese, French and German with manually curated frames. We present a detailed evaluation in which we find that our proposed approach significantly increases the quality and consistency of the generated Proposition Banks. We release these resources to the research community.

pdf bib
Multilingual Information Extraction with PolyglotIE
Alan Akbik | Laura Chiticariu | Marina Danilevsky | Yonas Kbrom | Yunyao Li | Huaiyu Zhu
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

We present PolyglotIE, a web-based tool for developing extractors that perform Information Extraction (IE) over multilingual data. Our tool has two core features: First, it allows users to develop extractors against a unified abstraction that is shared across a large set of natural languages. This means that an extractor needs only be created once for one language, but will then run on multilingual data without any additional effort or language-specific knowledge on part of the user. Second, it embeds this abstraction as a set of views within a declarative IE system, allowing users to quickly create extractors using a mature IE query language. We present PolyglotIE as a hands-on demo in which users can experiment with creating extractors, execute them on multilingual text and inspect extraction results. Using the UI, we discuss the challenges and potential of using unified, crosslingual semantic abstractions as basis for downstream applications. We demonstrate multilingual IE for 9 languages from 4 different language groups: English, German, French, Spanish, Japanese, Chinese, Arabic, Russian and Hindi.

2015

pdf bib
Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling
Alan Akbik | Laura Chiticariu | Marina Danilevsky | Yunyao Li | Shivakumar Vaithyanathan | Huaiyu Zhu
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
SCHNÄPPER: A Web Toolkit for Exploratory Relation Extraction
Thilo Michael | Alan Akbik
Proceedings of ACL-IJCNLP 2015 System Demonstrations

2014

pdf bib
The Weltmodell: A Data-Driven Commonsense Knowledge Base
Alan Akbik | Thilo Michael
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

We present the Weltmodell, a commonsense knowledge base that was automatically generated from aggregated dependency parse fragments gathered from over 3.5 million English language books. We leverage the magnitude and diversity of this dataset to arrive at close to ten million distinct N-ary commonsense facts using techniques from open-domain Information Extraction (IE). Furthermore, we compute a range of measures of association and distributional similarity on this data. We present the results of our efforts using a browsable web demonstrator and publicly release all generated data for use and discussion by the research community. In this paper, we give an overview of our knowledge acquisition method and representation model, and present our web demonstrator.

pdf bib
Freepal: A Large Collection of Deep Lexico-Syntactic Patterns for Relation Extraction
Johannes Kirschnick | Alan Akbik | Holmer Hemsen
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

The increasing availability and maturity of both scalable computing architectures and deep syntactic parsers is opening up new possibilities for Relation Extraction (RE) on large corpora of natural language text. In this paper, we present Freepal, a resource designed to assist with the creation of relation extractors for more than 5,000 relations defined in the Freebase knowledge base (KB). The resource consists of over 10 million distinct lexico-syntactic patterns extracted from dependency trees, each of which is assigned to one or more Freebase relations with different confidence strengths. We generate the resource by executing a large-scale distant supervision approach on the ClueWeb09 corpus to extract and parse over 260 million sentences labeled with Freebase entities and relations. We make Freepal freely available to the research community, and present a web demonstrator to the dataset, accessible from free-pal.appspot.com.

pdf bib
Proceedings of the First AHA!-Workshop on Information Discovery in Text
Alan Akbik | Larysa Visengeriyeva
Proceedings of the First AHA!-Workshop on Information Discovery in Text

pdf bib
Extracting a Repository of Events and Event References from News Clusters
Silvia Julinda | Christoph Boden | Alan Akbik
Proceedings of the First AHA!-Workshop on Information Discovery in Text

pdf bib
Exploratory Relation Extraction in Large Text Corpora
Alan Akbik | Thilo Michael | Christoph Boden
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

pdf bib
Nerdle: Topic-Specific Question Answering Using Wikia Seeds
Umar Maqsud | Sebastian Arnold | Michael Hülfenhaus | Alan Akbik
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations

2013

pdf bib
Effective Selectional Restrictions for Unsupervised Relation Extraction
Alan Akbik | Larysa Visengeriyeva | Johannes Kirschnick | Alexander Löser
Proceedings of the Sixth International Joint Conference on Natural Language Processing

pdf bib
Propminer: A Workflow for Interactive Information Extraction and Exploration using Dependency Trees
Alan Akbik | Oresti Konomi | Michail Melnikov
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations

2012

pdf bib
Unsupervised Discovery of Relations and Discriminative Extraction Patterns
Alan Akbik | Larysa Visengeriyeva | Priska Herger | Holmer Hemsen | Alexander Löser
Proceedings of COLING 2012

pdf bib
KrakeN: N-ary Facts in Open Information Extraction
Alan Akbik | Alexander Löser
Proceedings of the Joint Workshop on Automatic Knowledge Base Construction and Web-scale Knowledge Extraction (AKBC-WEKEX)