60 code implementations • IJCNLP 2019 • Nils Reimers, Iryna Gurevych
However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10, 000 sentences requires about 50 million inference computations (~65 hours) with BERT.
Ranked #5 on Linear-Probe Classification on SentEval
11 code implementations • EMNLP 2020 • Nils Reimers, Iryna Gurevych
The training is based on the idea that a translated sentence should be mapped to the same location in the vector space as the original sentence.
1 code implementation • NAACL 2021 • Nandan Thakur, Nils Reimers, Johannes Daxenberger, Iryna Gurevych
Bi-encoders, on the other hand, require substantial training data and fine-tuning over the target task to achieve competitive performance.
7 code implementations • 14 Apr 2021 • Kexin Wang, Nils Reimers, Iryna Gurevych
Learning sentence embeddings often requires a large amount of labeled data.
Ranked #1 on Re-Ranking on AskUbuntu
8 code implementations • EMNLP 2020 • Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, Aishwarya Kamath, Ivan Vulić, Sebastian Ruder, Kyunghyun Cho, Iryna Gurevych
We propose AdapterHub, a framework that allows dynamic "stitching-in" of pre-trained adapters for different tasks and languages.
1 code implementation • 18 Nov 2023 • Clifton Poth, Hannah Sterz, Indraneil Paul, Sukannya Purkayastha, Leon Engländer, Timo Imhof, Ivan Vulić, Sebastian Ruder, Iryna Gurevych, Jonas Pfeiffer
We introduce Adapters, an open-source library that unifies parameter-efficient and modular transfer learning in large language models.
3 code implementations • EACL 2021 • Jonas Pfeiffer, Aishwarya Kamath, Andreas Rücklé, Kyunghyun Cho, Iryna Gurevych
We show that by separating the two stages, i. e., knowledge extraction and knowledge composition, the classifier can effectively exploit the representations learned from multiple tasks in a non-destructive manner.
3 code implementations • EMNLP 2020 • Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, Sebastian Ruder
The main goal behind state-of-the-art pre-trained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or few-shot cross-lingual transfer.
Ranked #5 on Cross-Lingual Transfer on XCOPA (using extra training data)
1 code implementation • EMNLP 2021 • Andreas Rücklé, Gregor Geigle, Max Glockner, Tilman Beck, Jonas Pfeiffer, Nils Reimers, Iryna Gurevych
Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements.
6 code implementations • 21 Jul 2017 • Nils Reimers, Iryna Gurevych
Selecting optimal parameters for a neural network architecture can often make the difference between mediocre and state-of-the-art performance.
2 code implementations • 17 Apr 2021 • Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, Iryna Gurevych
To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval.
Ranked #1 on Argument Retrieval on ArguAna (BEIR)
1 code implementation • 26 Mar 2018 • Nils Reimers, Iryna Gurevych
In this publication, we show that there is a high risk that a statistical significance in this type of evaluation is not due to a superior learning approach.
5 code implementations • EMNLP 2017 • Nils Reimers, Iryna Gurevych
In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches.
1 code implementation • COLING 2018 • Jan-Christoph Klie, Michael Bugert, Beto Boullosa, Richard Eckart de Castilho, Iryna Gurevych
We introduce INCEpTION, a new annotation platform for tasks including interactive and semantic annotation (e. g., concept linking, fact linking, knowledge base population, semantic frame annotation).
1 code implementation • 5 Apr 2019 • Nils Reimers, Iryna Gurevych
We evaluate different methods that combine the three vectors from the language model in order to achieve the best possible performance in downstream NLP tasks.
5 code implementations • NAACL 2022 • Kexin Wang, Nandan Thakur, Nils Reimers, Iryna Gurevych
This limits the usage of dense retrieval approaches to only a few domains with large training datasets.
Ranked #9 on Zero-shot Text Search on BEIR
1 code implementation • EMNLP 2017 • Daniil Sorokin, Iryna Gurevych
We demonstrate that for sentence-level relation extraction it is beneficial to consider other relations in the sentential context while predicting the target relation.
Ranked #1 on Relation Extraction on Wikipedia-Wikidata relations
2 code implementations • ACL 2017 • Steffen Eger, Johannes Daxenberger, Iryna Gurevych
Contrary to models that operate on the argument component level, we find that framing AM as dependency parsing leads to subpar performance results.
3 code implementations • EMNLP (NLP4ConvAI) 2021 • Leonardo F. R. Ribeiro, Martin Schmitt, Hinrich Schütze, Iryna Gurevych
We show that the PLMs BART and T5 achieve new state-of-the-art results and that task-adaptive pretraining strategies improve their performance even further.
Ranked #1 on KG-to-Text Generation on WebNLG (All)
1 code implementation • 4 Mar 2018 • Andreas Rücklé, Steffen Eger, Maxime Peyrard, Iryna Gurevych
Here, we generalize the concept of average word embeddings to power mean word embeddings.
1 code implementation • COLING 2018 • Daniil Sorokin, Iryna Gurevych
The most approaches to Knowledge Base Question Answering are based on semantic parsing.
Ranked #1 on Knowledge Base Question Answering on WebQSP-WD
1 code implementation • 22 Mar 2021 • Gregor Geigle, Jonas Pfeiffer, Nils Reimers, Ivan Vulić, Iryna Gurevych
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image.
1 code implementation • 29 Jan 2020 • Leonardo F. R. Ribeiro, Yue Zhang, Claire Gardent, Iryna Gurevych
Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations.
Ranked #1 on Graph-to-Sequence on WebNLG
2 code implementations • ACL 2019 • Nils Reimers, Benjamin Schiller, Tilman Beck, Johannes Daxenberger, Christian Stab, Iryna Gurevych
We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search.
3 code implementations • NAACL 2018 • Ivan Habernal, Henning Wachsmuth, Iryna Gurevych, Benno Stein
On this basis, we present a new challenging task, the argument reasoning comprehension task.
1 code implementation • ACL 2022 • Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva, Max Eichler, Gregor Geigle, Clifton Poth, Hannah Sterz, Haritz Puerto, Leonardo F. R. Ribeiro, Jonas Pfeiffer, Nils Reimers, Gözde Gül Şahin, Iryna Gurevych
Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e. g., extractive, abstractive), require different model architectures (e. g., generative, discriminative), and setups (e. g., with or without retrieval).
1 code implementation • 19 Aug 2022 • Rachneet Sachdeva, Haritz Puerto, Tim Baumgärtner, Sewin Tariverdian, Hao Zhang, Kexin Wang, Hossain Shaikh Saadi, Leonardo F. R. Ribeiro, Iryna Gurevych
In this paper, we introduce SQuARE v2, the new version of SQuARE, to provide an explainability infrastructure for comparing models based on methods such as saliency maps and graph-based explanations.
1 code implementation • 31 Mar 2023 • Haritz Puerto, Tim Baumgärtner, Rachneet Sachdeva, Haishuo Fang, Hao Zhang, Sewin Tariverdian, Kexin Wang, Iryna Gurevych
To ease research in multi-agent models, we extend UKP-SQuARE, an online platform for QA research, to support three families of multi-agent systems: i) agent selection, ii) early-fusion of agents, and iii) late-fusion of agents.
1 code implementation • 31 May 2023 • Haishuo Fang, Haritz Puerto, Iryna Gurevych
To evaluate the effectiveness of UKP-SQuARE in teaching scenarios, we adopted it in a postgraduate NLP course and surveyed the students after the course.
2 code implementations • 24 May 2023 • Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Chenxi Whitehouse, Osama Mohammed Afzal, Tarek Mahmoud, Toru Sasaki, Thomas Arnold, Alham Fikri Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov
These results show that the problem is far from solved and that there is a lot of room for improvement.
1 code implementation • 12 Aug 2022 • Ivan Habernal, Daniel Faber, Nicola Recchia, Sebastian Bretthauer, Iryna Gurevych, Indra Spiecker genannt Döhmann, Christoph Burchard
Identifying, classifying, and analyzing arguments in legal discourse has been a prominent area of research since the inception of the argument mining field.
1 code implementation • SEMEVAL 2018 • Daniil Sorokin, Iryna Gurevych
We use the Wikidata knowledge base and available question answering datasets to create benchmarks for entity linking on question answering data.
Ranked #2 on Entity Linking on WebQSP-WD
1 code implementation • 15 Nov 2023 • Yuxia Wang, Revanth Gangi Reddy, Zain Muhammad Mujahid, Arnav Arora, Aleksandr Rubashevskii, Jiahui Geng, Osama Mohammed Afzal, Liangming Pan, Nadav Borenstein, Aditya Pillai, Isabelle Augenstein, Iryna Gurevych, Preslav Nakov
The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs.
1 code implementation • LREC 2016 • Ivan Habernal, Omnia Zayed, Iryna Gurevych
Large Web corpora containing full documents with permissive licenses are crucial for many NLP tasks.
7 code implementations • 13 Jun 2018 • Andreas Hanselowski, Avinesh PVS, Benjamin Schiller, Felix Caspelherr, Debanjan Chaudhuri, Christian M. Meyer, Iryna Gurevych
To date, there is no in-depth analysis paper to critically discuss FNC-1's experimental setup, reproduce the results, and draw conclusions for next-generation stance classification methods.
1 code implementation • WS 2018 • Andreas Hanselowski, Hao Zhang, Zile Li, Daniil Sorokin, Benjamin Schiller, Claudia Schulz, Iryna Gurevych
The Fact Extraction and VERification (FEVER) shared task was launched to support the development of systems able to verify claims by extracting supporting or refuting facts from raw text.
2 code implementations • NAACL 2022 • Leonardo F. R. Ribeiro, Mengwen Liu, Iryna Gurevych, Markus Dreyer, Mohit Bansal
Despite recent improvements in abstractive summarization, most current approaches generate summaries that are not factually consistent with the source document, severely restricting their trust and usage in real-world applications.
1 code implementation • 5 Jun 2022 • Jan-Christoph Klie, Bonnie Webber, Iryna Gurevych
While researchers show that their approaches work well on their newly introduced datasets, they rarely compare their methods to previous work or on the same datasets.
2 code implementations • IJCNLP 2019 • Florian Böhm, Yang Gao, Christian M. Meyer, Ori Shapira, Ido Dagan, Iryna Gurevych
Human evaluation experiments show that, compared to the state-of-the-art supervised-learning systems and ROUGE-as-rewards RL summarisation systems, the RL systems using our learned rewards during training generate summarieswith higher human ratings.
1 code implementation • 6 Jan 2020 • Benjamin Schiller, Johannes Daxenberger, Iryna Gurevych
Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim and has become a key component in applications like fake news detection, claim validation, and argument search.
1 code implementation • NAACL 2018 • Claudia Schulz, Steffen Eger, Johannes Daxenberger, Tobias Kahse, Iryna Gurevych
We investigate whether and where multi-task learning (MTL) can improve performance on NLP problems related to argumentation mining (AM), in particular argument component identification.
1 code implementation • WS 2017 • Rachel Wities, Vered Shwartz, Gabriel Stanovsky, Meni Adler, Ori Shapira, Shyam Upadhyay, Dan Roth, Eugenio Martinez Camara, Iryna Gurevych, Ido Dagan
We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open text-based manner.
1 code implementation • SEMEVAL 2017 • Steffen Eger, Erik-Lân Do Dinh, Ilia Kuznetsov, Masoud Kiaeeha, Iryna Gurevych
From these approaches, we created an ensemble of differently hyper-parameterized systems, achieving a micro-F1-score of 0. 63 on the test data.
1 code implementation • 19 Jul 2023 • Nandan Thakur, Kexin Wang, Iryna Gurevych, Jimmy Lin
In this work, we provide SPRINT, a unified Python toolkit based on Pyserini and Lucene, supporting a common interface for evaluating neural sparse retrieval.
1 code implementation • ICLR 2020 • Shweta Mahajan, Iryna Gurevych, Stefan Roth
Therefore, we propose a novel semi-supervised framework, which models shared information between domains and domain-specific information separately.
1 code implementation • EMNLP 2021 • Clifton Poth, Jonas Pfeiffer, Andreas Rücklé, Iryna Gurevych
Our best methods achieve an average Regret@3 of less than 1% across all target tasks, demonstrating that we are able to efficiently identify the best datasets for intermediate training.
1 code implementation • ACL 2020 • Jan-Christoph Klie, Richard Eckart de Castilho, Iryna Gurevych
Entity linking (EL) is concerned with disambiguating entity mentions in a text against knowledge bases (KB).
1 code implementation • Findings (EMNLP) 2021 • Kexin Wang, Nils Reimers, Iryna Gurevych
Learning sentence embeddings often requires a large amount of labeled data.
1 code implementation • 4 Sep 2023 • Sheng Lu, Irina Bigoulaeva, Rachneet Sachdeva, Harish Tayyar Madabushi, Iryna Gurevych
Large language models have exhibited emergent abilities, demonstrating exceptional performance across diverse tasks for which they were not explicitly trained, including those that require complex reasoning abilities.
1 code implementation • EMNLP 2021 • Leonardo F. R. Ribeiro, Yue Zhang, Iryna Gurevych
Pretrained language models (PLM) have recently advanced graph-to-text generation, where the input graph is linearized into a sequence and fed into the PLM to obtain its representation.
Ranked #1 on Data-to-Text Generation on AMR3.0
1 code implementation • COLING 2018 • Andreas Hanselowski, Avinesh PVS, Benjamin Schiller, Felix Caspelherr, Debanjan Chaudhuri, Christian M. Meyer, Iryna Gurevych
To date, there is no in-depth analysis paper to critically discuss FNC-1{'}s experimental setup, reproduce the results, and draw conclusions for next-generation stance classification methods.
1 code implementation • NAACL 2021 • Benjamin Schiller, Johannes Daxenberger, Iryna Gurevych
In this work, we train a language model for argument generation that can be controlled on a fine-grained level to generate sentence-level arguments for a given topic, stance, and aspect.
1 code implementation • 23 May 2023 • Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
While automatic dialogue tutors hold great potential in making education personalized and more accessible, research on such systems has been hampered by a lack of sufficiently large and high-quality datasets.
1 code implementation • EMNLP 2018 • Steffen Eger, Paul Youssef, Iryna Gurevych
Activation functions play a crucial role in neural networks because they are the nonlinearities which have been attributed to the success story of deep learning.
1 code implementation • 7 Mar 2019 • Steffen Eger, Chao Li, Florian Netzer, Iryna Gurevych
By extrapolation, we predict that these topics will remain lead problems/approaches in their fields in the short- and mid-term.
1 code implementation • ACL 2021 • Phillip Rust, Jonas Pfeiffer, Ivan Vulić, Sebastian Ruder, Iryna Gurevych
In this work, we provide a systematic and comprehensive empirical comparison of pretrained multilingual language models versus their monolingual counterparts with regard to their monolingual task performance.
1 code implementation • 17 Feb 2023 • Luke Bates, Iryna Gurevych
Few-shot text classification systems have impressive capabilities but are infeasible to deploy and use reliably due to their dependence on prompting and billion-parameter language models.
1 code implementation • IJCNLP 2019 • Edwin Simpson, Iryna Gurevych
Current methods for sequence tagging, a core task in NLP, are data hungry, which motivates the use of crowdsourcing as a cheap way to obtain labelled data.
1 code implementation • NAACL 2019 • Steffen Eger, Gözde Gül Şahin, Andreas Rücklé, Ji-Ung Lee, Claudia Schulz, Mohsen Mesgar, Krishnkant Swarnkar, Edwin Simpson, Iryna Gurevych
Visual modifications to text are often used to obfuscate offensive comments in social media (e. g., "! d10t") or as a writing style ("1337" in "leet speak"), among other scenarios.
1 code implementation • NAACL 2019 • Yang Gao, Steffen Eger, Ilia Kuznetsov, Iryna Gurevych, Yusuke Miyao
We then focus on the role of the rebuttal phase, and propose a novel task to predict after-rebuttal (i. e., final) scores from initial reviews and author responses.
1 code implementation • EMNLP 2020 • Prasetya Ajie Utama, Nafise Sadat Moosavi, Iryna Gurevych
Recently proposed debiasing methods are shown to be effective in mitigating this tendency.
1 code implementation • 27 Feb 2024 • Yuesong Shen, Nico Daheim, Bai Cong, Peter Nickl, Gian Maria Marconi, Clement Bazan, Rio Yokota, Iryna Gurevych, Daniel Cremers, Mohammad Emtiyaz Khan, Thomas Möllenhoff
We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks.
1 code implementation • Findings (ACL) 2022 • Jonas Pfeiffer, Gregor Geigle, Aishwarya Kamath, Jan-Martin O. Steitz, Stefan Roth, Ivan Vulić, Iryna Gurevych
In this work, we address this gap and provide xGQA, a new multilingual evaluation benchmark for the visual question answering task.
1 code implementation • NAACL 2022 • Nafise Sadat Moosavi, Quentin Delfosse, Kristian Kersting, Iryna Gurevych
The resulting adapters (a) contain about 50% of the learning parameters of the standard adapter and are therefore more efficient at training and inference, and require less storage space, and (b) achieve considerably higher performances in low-data settings.
1 code implementation • WS 2018 • Yevgeniy Puzikov, Iryna Gurevych
E2E NLG Challenge is a shared task on generating restaurant descriptions from sets of key-value pairs.
Ranked #11 on Data-to-Text Generation on E2E NLG Challenge
1 code implementation • ACL 2020 • Prasetya Ajie Utama, Nafise Sadat Moosavi, Iryna Gurevych
Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution.
1 code implementation • 30 Mar 2023 • Nico Daheim, Nouha Dziri, Mrinmaya Sachan, Iryna Gurevych, Edoardo M. Ponti
We evaluate our method -- using different variants of Flan-T5 as a backbone language model -- on multiple datasets for information-seeking dialogue generation and compare our method with state-of-the-art techniques for faithfulness, such as CTRL, Quark, DExperts, and Noisy Channel reranking.
3 code implementations • CL 2020 • Gözde Gül Şahin, Clara Vania, Ilia Kuznetsov, Iryna Gurevych
We present a reusable methodology for creation and evaluation of such tests in a multilingual setting.
1 code implementation • IJCNLP 2019 • Leonardo F. R. Ribeiro, Claire Gardent, Iryna Gurevych
Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges.
Ranked #11 on AMR-to-Text Generation on LDC2017T10
1 code implementation • 3 Dec 2021 • Haritz Puerto, Gözde Gül Şahin, Iryna Gurevych
The recent explosion of question answering (QA) datasets and models has increased the interest in the generalization of models across multiple domains and formats by either training on multiple datasets or by combining multiple models.
1 code implementation • 22 Apr 2019 • Dietrich Trautmann, Johannes Daxenberger, Christian Stab, Hinrich Schütze, Iryna Gurevych
In this work, we argue that the task should be performed on a more fine-grained level of sequence labeling.
2 code implementations • 23 May 2023 • Kexin Wang, Nils Reimers, Iryna Gurevych
This drives us to build a benchmark for this task including multiple datasets from heterogeneous domains.
1 code implementation • EMNLP (DeeLIO) 2020 • Anne Lauscher, Olga Majewska, Leonardo F. R. Ribeiro, Iryna Gurevych, Nikolai Rozanov, Goran Glavaš
Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowledge from external resources into these models.
1 code implementation • COLING 2018 • Steffen Eger, Johannes Daxenberger, Christian Stab, Iryna Gurevych
Argumentation mining (AM) requires the identification of complex discourse structures and has lately been applied with success monolingually.
1 code implementation • ACL 2020 • Mohsen Mesgar, Sebastian Bücker, Iryna Gurevych
Recent dialogue coherence models use the coherence features designed for monologue texts, e. g. nominal entities, to represent utterances and then explicitly augment them with dialogue-relevant features, e. g., dialogue act labels.
1 code implementation • EMNLP 2020 • Andreas Rücklé, Jonas Pfeiffer, Iryna Gurevych
We investigate the model performances on nine benchmarks of answer selection and question similarity tasks, and show that all 140 models transfer surprisingly well, where the large majority of models substantially outperforms common IR baselines.
2 code implementations • 1 Apr 2021 • Max Glockner, Ieva Staliūnaitė, James Thorne, Gisela Vallejo, Andreas Vlachos, Iryna Gurevych
Automated fact-checking systems verify claims against evidence to predict their veracity.
1 code implementation • 24 Feb 2023 • Dennis Zyska, Nils Dycke, Jan Buchmann, Ilia Kuznetsov, Iryna Gurevych
Recent years have seen impressive progress in AI-assisted writing, yet the developments in AI-assisted reading are lacking.
1 code implementation • NAACL 2018 • Ivan Habernal, Henning Wachsmuth, Iryna Gurevych, Benno Stein
Arguing without committing a fallacy is one of the main requirements of an ideal debate.
1 code implementation • EMNLP 2017 • Johannes Daxenberger, Steffen Eger, Ivan Habernal, Christian Stab, Iryna Gurevych
Argument mining has become a popular research area in NLP.
1 code implementation • EMNLP 2018 • Yang Gao, Christian M. Meyer, Iryna Gurevych
The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries.
1 code implementation • EMNLP 2018 • Daniil Sorokin, Iryna Gurevych
Most approaches to Knowledge Base Question Answering are based on semantic parsing.
1 code implementation • TACL 2018 • Edwin Simpson, Iryna Gurevych
We introduce a scalable Bayesian preference learning method for identifying convincing arguments in the absence of gold-standard rat- ings or rankings.
1 code implementation • EMNLP 2017 • Tobias Falke, Iryna Gurevych
Concept maps can be used to concisely represent important information and bring structure into large document collections.
1 code implementation • WS 2017 • Michael Bugert, Yevgeniy Puzikov, Andreas R{\"u}ckl{\'e}, Judith Eckle-Kohler, Teresa Martin, Eugenio Mart{\'\i}nez-C{\'a}mara, Daniil Sorokin, Maxime Peyrard, Iryna Gurevych
The Story Cloze test is a recent effort in providing a common test scenario for text understanding systems.
1 code implementation • ACL 2019 • Edwin Simpson, Erik-L{\^a}n Do Dinh, Tristan Miller, Iryna Gurevych
The inability to quantify key aspects of creative language is a frequent obstacle to natural language understanding.
1 code implementation • 4 Dec 2019 • Edwin Simpson, Iryna Gurevych
As previous solutions based on Gaussian processes do not scale to large numbers of users, items or pairwise labels, we propose a stochastic variational inference approach that limits computational and memory costs.
1 code implementation • 14 Apr 2021 • Gregor Geigle, Nils Reimers, Andreas Rücklé, Iryna Gurevych
We argue that there exist a wide range of specialized QA agents in literature.
1 code implementation • ACL 2022 • Tilman Beck, Bela Bohlender, Christina Viehmann, Vincent Hane, Yanik Adamson, Jaber Khuri, Jonas Brossmann, Jonas Pfeiffer, Iryna Gurevych
The open-access dissemination of pretrained language models through online repositories has led to a democratization of state-of-the-art natural language processing (NLP) research.
1 code implementation • 19 Oct 2022 • Tim Baumgärtner, Leonardo F. R. Ribeiro, Nils Reimers, Iryna Gurevych
Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets.
1 code implementation • EMNLP 2017 • Ivan Habernal, Raffael Hannemann, Christian Pollak, Christopher Klamm, Patrick Pauli, Iryna Gurevych
An important skill in critical thinking and argumentation is the ability to spot and recognize fallacies.
1 code implementation • 16 Apr 2021 • Nafise Sadat Moosavi, Andreas Rücklé, Dan Roth, Iryna Gurevych
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions.
1 code implementation • ACL 2021 • Kevin Stowe, Tuhin Chakrabarty, Nanyun Peng, Smaranda Muresan, Iryna Gurevych
Guided by conceptual metaphor theory, we propose to control the generation process by encoding conceptual mappings between cognitive domains to generate meaningful metaphoric expressions.
1 code implementation • EMNLP 2021 • Prasetya Ajie Utama, Nafise Sadat Moosavi, Victor Sanh, Iryna Gurevych
Recent prompt-based approaches allow pretrained language models to achieve strong performances on few-shot finetuning by reformulating downstream tasks as a language modeling problem.
1 code implementation • ACL 2022 • Kevin Stowe, Prasetya Utama, Iryna Gurevych
Natural language inference (NLI) has been widely used as a task to train and evaluate models for language understanding.
1 code implementation • WS 2018 • Teresa Botschen, Daniil Sorokin, Iryna Gurevych
Common-sense argumentative reasoning is a challenging task that requires holistic understanding of the argumentation where external knowledge about the world is hypothesized to play a key role.
1 code implementation • CL (ACL) 2021 • Michael Bugert, Nils Reimers, Iryna Gurevych
This raises strong concerns on their generalizability -- a must-have for downstream applications where the magnitude of domains or event mentions is likely to exceed those found in a curated corpus.
1 code implementation • AKBC 2021 • Michael Bugert, Iryna Gurevych
Cross-document event coreference resolution (CDCR) is the task of identifying which event mentions refer to the same events throughout a collection of documents.
1 code implementation • 12 Nov 2022 • Nils Dycke, Ilia Kuznetsov, Iryna Gurevych
Peer review constitutes a core component of scholarly publishing; yet it demands substantial expertise and training, and is susceptible to errors and biases.
1 code implementation • 19 Dec 2022 • Haau-Sing Li, Mohsen Mesgar, André F. T. Martins, Iryna Gurevych
We hypothesize that the under-specification of a natural language description can be resolved by asking clarification questions.
1 code implementation • 1 Nov 2023 • Yongxin Huang, Kexin Wang, Sourav Dutta, Raj Nath Patel, Goran Glavaš, Iryna Gurevych
As a solution, we propose AdaSent, which decouples SEPT from DAPT by training a SEPT adapter on the base PLM.
1 code implementation • ACL 2020 • Ji-Ung Lee, Christian M. Meyer, Iryna Gurevych
Existing approaches to active learning maximize the system performance by sampling unlabeled instances for annotation that yield the most efficient training.
1 code implementation • 22 Apr 2022 • Ilia Kuznetsov, Jan Buchmann, Max Eichler, Iryna Gurevych
While existing NLP studies focus on the analysis of individual texts, editorial assistance often requires modeling interactions between pairs of texts -- yet general frameworks and datasets to support this scenario are missing.
1 code implementation • NAACL 2022 • Prasetya Ajie Utama, Joshua Bambrick, Nafise Sadat Moosavi, Iryna Gurevych
In this work, we show that NLI models can be effective for this task when the training data is augmented with high-quality task-oriented examples.
Abstractive Text Summarization Natural Language Inference +1
1 code implementation • 25 Oct 2022 • Max Glockner, Yufang Hou, Iryna Gurevych
In our analysis, we show that, by design, existing NLP task definitions for fact-checking cannot refute misinformation as professional fact-checkers do for the majority of claims.
1 code implementation • 3 Nov 2022 • Tilman Beck, Andreas Waldis, Iryna Gurevych
Stance detection deals with identifying an author's stance towards a target.
2 code implementations • CONLL 2019 • Andreas Hanselowski, Christian Stab, Claudia Schulz, Zile Li, Iryna Gurevych
Automated fact-checking based on machine learning is a promising approach to identify false information distributed on the web.
2 code implementations • 30 Aug 2022 • Haishuo Fang, Ji-Ung Lee, Nafise Sadat Moosavi, Iryna Gurevych
In contrast to conventional, predefined activation functions, RAFs can adaptively learn optimal activation functions during training according to input data.
1 code implementation • 19 Feb 2024 • Justus-Jonas Erker, Florian Mai, Nils Reimers, Gerasimos Spanakis, Iryna Gurevych
Search-based dialog models typically re-encode the dialog history at every turn, incurring high cost.
1 code implementation • COLING 2018 • Ilia Kuznetsov, Iryna Gurevych
We examine the effect of lemmatization and POS typing on word embedding performance in a novel resource-based evaluation scenario, as well as on standard similarity benchmarks.
1 code implementation • IJCNLP 2019 • Andreas Rücklé, Nafise Sadat Moosavi, Iryna Gurevych
We show that our proposed approaches are more effective in many cases because they can utilize larger amounts of unlabeled data from cQA forums.
1 code implementation • CONLL 2020 • Steffen Eger, Johannes Daxenberger, Iryna Gurevych
We then probe embeddings in a multilingual setup with design choices that lie in a 'stable region', as we identify for English, and find that results on English do not transfer to other languages.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Max Glockner, Ivan Habernal, Iryna Gurevych
We propose a differentiable training-framework to create models which output faithful rationales on a sentence level, by solely applying supervision on the target task.
1 code implementation • EMNLP 2021 • Leonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang, Iryna Gurevych
Recent work on multilingual AMR-to-text generation has exclusively focused on data augmentation strategies that utilize silver AMR.
2 code implementations • 14 Feb 2022 • Federico Ruggeri, Mohsen Mesgar, Iryna Gurevych
The applications of conversational agents for scientific disciplines (as expert domains) are understudied due to the lack of dialogue data to train such agents.
Ranked #1 on Fact Selection on ArgSciChat
1 code implementation • 24 Jan 2023 • Jakub Macina, Nico Daheim, Lingzhi Wang, Tanmay Sinha, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
Designing dialog tutors has been challenging as it involves modeling the diverse and complex pedagogical strategies employed by human tutors.
1 code implementation • 18 Jan 2024 • Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych
Reasoning is a fundamental component of language understanding.
1 code implementation • WS 2016 • Pedro Bispo Santos, Lisa Beinborn, Iryna Gurevych
We explore a domain-agnostic approach for analyzing speech with the goal of opinion prediction.
1 code implementation • COLING 2016 • Darina Benikova, Margot Mieskes, Christian M. Meyer, Iryna Gurevych
Coherent extracts are a novel type of summary combining the advantages of manually created abstractive summaries, which are fluent but difficult to evaluate, and low-quality automatically created extractive summaries, which lack coherence and structure.
1 code implementation • IJCNLP 2019 • Max Eichler, Gözde Gül Şahin, Iryna Gurevych
We present LINSPECTOR WEB, an open source multilingual inspector to analyze word representations.
1 code implementation • 30 Jul 2019 • Yang Gao, Christian M. Meyer, Mohsen Mesgar, Iryna Gurevych
The predominant RL paradigm for summarisation learns a cross-input policy, which requires considerable time, data and parameter tuning due to the huge search spaces and the delayed rewards.
1 code implementation • ACL 2021 • Mingzhu Wu, Nafise Sadat Moosavi, Dan Roth, Iryna Gurevych
We propose a methodology for creating MRC datasets that better reflect the challenges of coreference reasoning and use it to create a sample evaluation set.
1 code implementation • CoNLL (EMNLP) 2021 • Kevin Stowe, Nils Beck, Iryna Gurevych
Metaphor generation is a difficult task, and has seen tremendous improvement with the advent of deep pretrained models.
1 code implementation • Findings (EMNLP) 2021 • Mohsen Mesgar, Leonardo F. R. Ribeiro, Iryna Gurevych
Entity grids and entity graphs are two frameworks for modeling local coherence.
1 code implementation • 11 Nov 2023 • Luke Bates, Peter Ebert Christensen, Preslav Nakov, Iryna Gurevych
Here, to aid understanding of memes, we release a knowledge base of memes and information found on www. knowyourmeme. com, which we call the Know Your Meme Knowledge Base (KYMKB), composed of more than 54, 000 images.
1 code implementation • 6 Mar 2024 • Indraneil Paul, Goran Glavaš, Iryna Gurevych
In particular, most mainstream Code-LMs have been pre-trained on source code files alone.
1 code implementation • NAACL 2019 • Tristan Miller, Maria Sukhareva, Iryna Gurevych
The study of argumentation and the development of argument mining tools depends on the availability of annotated data, which is challenging to obtain in sufficient quantity and quality.
1 code implementation • 22 Nov 2019 • Edwin Simpson, Yang Gao, Iryna Gurevych
For many NLP applications, such as question answering and summarisation, the goal is to select the best solution from a large space of candidates to meet a particular user's needs.
2 code implementations • EMNLP 2021 • Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, Sebastian Ruder
The ultimate challenge is dealing with under-resourced languages not covered at all by the models and written in scripts unseen during pretraining.
1 code implementation • CL (ACL) 2022 • Ji-Ung Lee, Jan-Christoph Klie, Iryna Gurevych
Annotation studies often require annotators to familiarize themselves with the task, its annotation scheme, and the data domain.
1 code implementation • 16 Aug 2022 • Lorenz Stangier, Ji-Ung Lee, Yuxi Wang, Marvin Müller, Nicholas Frick, Joachim Metternich, Iryna Gurevych
We evaluate TexPrax in a user-study with German factory employees who ask their colleagues for solutions on problems that arise during their daily work.
1 code implementation • 19 Dec 2022 • Martin Funkquist, Ilia Kuznetsov, Yufang Hou, Iryna Gurevych
To address this challenge, we propose CiteBench: a benchmark for citation text generation that unifies multiple diverse datasets and enables standardized evaluation of citation text generation models across task designs and domains.
1 code implementation • 14 Sep 2023 • Rachneet Sachdeva, Martin Tutek, Iryna Gurevych
In recent years, large language models (LLMs) have shown remarkable capabilities at scale, particularly at generating text conditioned on a prompt.
1 code implementation • 15 Sep 2023 • Chen Cecilia Liu, Fajri Koto, Timothy Baldwin, Iryna Gurevych
Large language models (LLMs) are highly adept at question answering and reasoning tasks, but when reasoning in a situational context, human expectations vary depending on the relevant cultural common ground.
1 code implementation • 18 Oct 2023 • Sheng Lu, Shan Chen, Yingya Li, Danielle Bitterman, Guergana Savova, Iryna Gurevych
In-context learning (ICL) is a new learning paradigm that has gained popularity along with the development of large language models.
1 code implementation • COLING 2018 • Erik-L{\^a}n Do Dinh, Steffen Eger, Iryna Gurevych
In this paper we investigate multi-task learning for related non-literal language phenomena.
1 code implementation • 24 May 2023 • Tianyu Yang, Thy Thy Tran, Iryna Gurevych
These models also suffer from posterior collapse, i. e., the decoder tends to ignore latent variables and directly access information captured in the encoder through the cross-attention mechanism.
1 code implementation • 13 Sep 2023 • Tilman Beck, Hendrik Schuff, Anne Lauscher, Iryna Gurevych
However, the available NLP literature disagrees on the efficacy of this technique - it remains unclear for which tasks and scenarios it can help, and the role of the individual factors in sociodemographic prompting is still unexplored.
1 code implementation • 26 Nov 2018 • Claudia Schulz, Christian M. Meyer, Michael Sailer, Jan Kiesewetter, Elisabeth Bauer, Frank Fischer, Martin R. Fischer, Iryna Gurevych
We aim to enable the large-scale adoption of diagnostic reasoning analysis and feedback by automating the epistemic activity identification.
1 code implementation • WS 2018 • Steffen Eger, Andreas R{\"u}ckl{\'e}, Iryna Gurevych
We consider unsupervised cross-lingual transfer on two tasks, viz., sentence-level argumentation mining and standard POS tagging.
1 code implementation • COLING 2016 • Christian M. Meyer, Judith Eckle-Kohler, Iryna Gurevych
We introduce the task of detecting cross-lingual marketing blunders, which occur if a trade name resembles an inappropriate or negatively connotated word in a target language.
1 code implementation • 7 Jun 2019 • Yang Gao, Christian M. Meyer, Iryna Gurevych
Interactive NLP is a promising paradigm to close the gap between automatic NLP systems and the human upper bound.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Mingzhu Wu, Nafise Sadat Moosavi, Andreas Rücklé, Iryna Gurevych
Our framework weights each example based on the biases it contains and the strength of those biases in the training data.
1 code implementation • 17 Apr 2021 • Aniket Pramanick, Tilman Beck, Kevin Stowe, Iryna Gurevych
Language use changes over time, and this impacts the effectiveness of NLP systems.
1 code implementation • ACL 2021 • Tilman Beck, Ji-Ung Lee, Christina Viehmann, Marcus Maurer, Oliver Quiring, Iryna Gurevych
This work investigates the use of interactively updated label suggestions to improve upon the efficiency of gathering annotations on the task of opinion mining in German Covid-19 social media data.
1 code implementation • 27 Jan 2022 • Nils Dycke, Ilia Kuznetsov, Iryna Gurevych
The shift towards publicly available text sources has enabled language processing at unprecedented scale, yet leaves under-serviced the domains where public and openly licensed data is scarce.
1 code implementation • 15 Feb 2022 • Chen Liu, Jonas Pfeiffer, Anna Korhonen, Ivan Vulić, Iryna Gurevych
2) We analyze cross-lingual VQA across different question types of varying complexity for different multilingual multimodal Transformers, and identify question types that are the most difficult to improve on.
1 code implementation • 24 Oct 2023 • Dominic Petrak, Nafise Sadat Moosavi, Ye Tian, Nikolai Rozanov, Iryna Gurevych
Learning from free-text human feedback is essential for dialog systems, but annotated data is scarce and usually covers only a small fraction of error types known in conversational AI.
1 code implementation • 7 Nov 2023 • Sukannya Purkayastha, Anne Lauscher, Iryna Gurevych
In this work, we are the first to explore Jiu-Jitsu argumentation for peer review by proposing the novel task of attitude and theme-guided rebuttal generation.
1 code implementation • COLING 2018 • Lisa Beinborn, Teresa Botschen, Iryna Gurevych
This survey discusses how recent developments in multimodal processing facilitate conceptual grounding of language.
1 code implementation • WS 2018 • Gil Rocha, Christian Stab, Henrique Lopes Cardoso, Iryna Gurevych
Argument mining aims to detect and identify argument structures from textual resources.
1 code implementation • NAACL 2019 • Tobias Falke, Iryna Gurevych
Concept map-based multi-document summarization has recently been proposed as a variant of the traditional summarization task with graph-structured summaries.
1 code implementation • LREC 2016 • Tristan Miller, Mohamed Khemakhem, Richard Eckart de Castilho, Iryna Gurevych
Also introduced in this paper is Ubyline, the web application used to produce the sense annotations.
1 code implementation • 3 Aug 2020 • Tristan Miller, Erik-Lân Do Dinh, Edwin Simpson, Iryna Gurevych
Most humour processing systems to date make at best discrete, coarse-grained distinctions between the comical and the conventional, yet such notions are better conceptualized as a broad spectrum.
2 code implementations • 13 May 2022 • Dominic Petrak, Nafise Sadat Moosavi, Iryna Gurevych
In this paper, we propose a new extended pretraining approach called Arithmetic-Based Pretraining that jointly addresses both in one extended pretraining step without requiring architectural changes or pretraining from scratch.
1 code implementation • 31 Oct 2022 • Irina Bigoulaeva, Rachneet Sachdeva, Harish Tayyar Madabushi, Aline Villavicencio, Iryna Gurevych
We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the other.
1 code implementation • 17 Jan 2024 • Dominic Petrak, Thy Thy Tran, Iryna Gurevych
The success of task-oriented and document-grounded dialogue systems depends on users accepting and enjoying using them.
no code implementations • 15 Feb 2018 • Christian Stab, Tristan Miller, Iryna Gurevych
Argument mining is a core technology for automating argument search in large document collections.
no code implementations • GWC 2018 • Xuan-Son Vu, Lucie Flekova, Lili Jiang, Iryna Gurevych
In this paper, we aim to reveal the impact of lexical-semantic resources, used in particular for word sense disambiguation and sense-level semantic categorization, on automatic personality classification task.
no code implementations • CL 2017 • Ivan Habernal, Iryna Gurevych
The goal of argumentation mining, an evolving research field in computational linguistics, is to design methods capable of analyzing people's argumentation.
no code implementations • COLING 2016 • Carsten Schnober, Steffen Eger, Erik-Lân Do Dinh, Iryna Gurevych
We analyze the performance of encoder-decoder neural models and compare them with well-known established methods.
no code implementations • CL 2017 • Christian Stab, Iryna Gurevych
In this article, we present a novel approach for parsing argumentation structures.
no code implementations • 19 Dec 2013 • Jinseok Nam, Jungi Kim, Eneldo Loza Mencía, Iryna Gurevych, Johannes Fürnkranz
Neural networks have recently been proposed for multi-label classification because they are able to capture and model label dependencies in the output layer.
no code implementations • EMNLP 2018 • Christian Stab, Tristan Miller, Benjamin Schiller, Pranav Rai, Iryna Gurevych
Argument mining is a core technology for automating argument search in large document collections.
no code implementations • EMNLP 2018 • Beto Boullosa, Richard Eckart de Castilho, Naveen Kumar, Jan-Christoph Klie, Iryna Gurevych
Annotating entity mentions and linking them to a knowledge resource are essential tasks in many domains.
no code implementations • CONLL 2018 • Ilia Kuznetsov, Iryna Gurevych
Thematic role hierarchy is a widely used linguistic tool to describe interactions between semantic roles and their syntactic realizations.
no code implementations • TACL 2018 • Nils Reimers, Nazanin Dehghani, Iryna Gurevych
We use this tree to incrementally infer, in a stepwise manner, at which time frame an event happened.
no code implementations • TACL 2016 • Silvana Hartmann, Judith Eckle-Kohler, Iryna Gurevych
We present a new approach for generating role-labeled training data using Linked Lexical Resources, i. e., integrated lexical resources that combine several resources (e. g., Word-Net, FrameNet, Wiktionary) by linking them on the sense or on the role level.
no code implementations • ACL 2017 • Henning Wachsmuth, Nona Naderi, Ivan Habernal, Yufang Hou, Graeme Hirst, Iryna Gurevych, Benno Stein
Argumentation quality is viewed differently in argumentation theory and in practical assessment approaches.
no code implementations • ACL 2017 • Gabriel Stanovsky, Judith Eckle-Kohler, Yevgeniy Puzikov, Ido Dagan, Iryna Gurevych
Previous models for the assessment of commitment towards a predicate in a sentence (also known as factuality prediction) were trained and tested against a specific annotated dataset, subsequently limiting the generality of their results.
no code implementations • EACL 2017 • Silvana Hartmann, Ilia Kuznetsov, Teresa Martin, Iryna Gurevych
We create a novel test set for FrameNet SRL based on user-generated web text and find that the major bottleneck for out-of-domain FrameNet SRL is the frame identification step.
no code implementations • EACL 2017 • Sallam Abualhaija, Tristan Miller, Judith Eckle-Kohler, Iryna Gurevych, Karl-Heinz Zimmermann
In this paper, we propose using metaheuristics{---}in particular, simulated annealing and the new D-Bees algorithm{---}to solve word sense disambiguation as an optimization problem within a knowledge-based lexical substitution system.
no code implementations • EACL 2017 • Christian Stab, Iryna Gurevych
In this paper, we propose a new task for assessing the quality of natural language arguments.
no code implementations • EACL 2017 • Beto Boullosa, Richard Eckart de Castilho, Alex Geyken, er, Lothar Lemnitzer, Iryna Gurevych
This paper describes an application system aimed to help lexicographers in the extraction of example sentences for a given headword based on its different senses.
no code implementations • NAACL 2018 • Teresa Botschen, Iryna Gurevych, Jan-Christoph Klie, Hatem Mousselly-Sergieh, Stefan Roth
Our analysis shows that for the German data, textual representations are still competitive with multimodal ones.
no code implementations • NAACL 2018 • Maxime Peyrard, Iryna Gurevych
Supervised summarization systems usually rely on supervision at the sentence or n-gram level provided by automatic metrics like ROUGE, which act as noisy proxies for human judgments.
no code implementations • NAACL 2018 • Christian Stab, Johannes Daxenberger, Chris Stahlhut, Tristan Miller, Benjamin Schiller, Christopher Tauchmann, Steffen Eger, Iryna Gurevych
Argument mining is a core technology for enabling argument search in large corpora.
no code implementations • SEMEVAL 2018 • Ivan Habernal, Henning Wachsmuth, Iryna Gurevych, Benno Stein
A natural language argument is composed of a claim as well as reasons given as premises for the claim.
no code implementations • SEMEVAL 2018 • Hatem Mousselly-Sergieh, Teresa Botschen, Iryna Gurevych, Stefan Roth
Current methods for knowledge graph (KG) representation learning focus solely on the structure of the KG and do not exploit any kind of external information, such as visual and linguistic information corresponding to the KG entities.
no code implementations • SEMEVAL 2017 • Tristan Miller, Christian Hempelmann, Iryna Gurevych
A pun is a form of wordplay in which a word suggests two or more meanings by exploiting polysemy, homonymy, or phonological similarity to another word, for an intended humorous or rhetorical effect.
no code implementations • EMNLP 2017 • Tobias Falke, Iryna Gurevych
Many techniques to automatically extract different types of graphs, showing for example entities or concepts and different relationships between them, have been suggested.
no code implementations • WS 2018 • Yevgeniy Puzikov, Iryna Gurevych
Surface Realization Shared Task 2018 is a workshop on generating sentences from lemmatized sets of dependency triples.
no code implementations • COLING 2018 • Erik-L{\^a}n Do Dinh, Steffen Eger, Iryna Gurevych
In this paper, we tackle four different tasks of non-literal language classification: token and construction level metaphor detection, classification of idiomatic use of infinitive-verb compounds, and classification of non-literal particle verbs.
no code implementations • WS 2017 • Silvana Hartmann, {\'E}va M{\'u}jdricza-Maydt, Ilia Kuznetsov, Iryna Gurevych, Anette Frank
We present the first experiment-based study that explicitly contrasts the three major semantic role labeling frameworks.
no code implementations • WS 2017 • Maria Sukhareva, Francesco Fuscagni, Johannes Daxenberger, Susanne G{\"o}rke, Doris Prechel, Iryna Gurevych
To our knowledge, this is the first attempt of statistical POS tagging of a cuneiform language.
no code implementations • WS 2017 • Teresa Botschen, Hatem Mousselly-Sergieh, Iryna Gurevych
Automatic completion of frame-to-frame (F2F) relations in the FrameNet (FN) hierarchy has received little attention, although they incorporate meta-level commonsense knowledge and are used in downstream approaches.
no code implementations • WS 2017 • Maxime Peyrard, Teresa Botschen, Iryna Gurevych
The evaluation of summaries is a challenging but crucial task of the summarization field.
no code implementations • WS 2017 • Iryna Gurevych
Can we reliably annotate convincingness of an argument?