no code implementations • SemEval (NAACL) 2022 • Hyunju Song, Steven Bethard
This paper presents the approaches and systems of the UA-KO team for the Korean portion of SemEval-2022 Task 11 on Multilingual Complex Named Entity Recognition. We fine-tuned Korean and multilingual BERT and RoBERTA models, conducted experiments on data augmentation, ensembles, and task-adaptive pretraining.
no code implementations • EMNLP (LAW, DMR) 2021 • Peiwen Su, Steven Bethard
While annotating normalized times in food security documents, we found that the semantically compositional annotation for time normalization (SCATE) scheme required several near-duplicate annotations to get the correct semantics for expressions like Nov. 7th to 11th 2021.
no code implementations • EMNLP (ALW) 2020 • Kadir Bulut Ozler, Kate Kenski, Steve Rains, Yotam Shmargad, Kevin Coe, Steven Bethard
Incivility is a problem on social media, and it comes in many forms (name-calling, vulgarity, threats, etc.)
1 code implementation • NAACL (BioNLP) 2021 • Dongfang Xu, Steven Bethard
We propose a vector-space model for concept normalization, where mentions and concepts are encoded via transformer networks that are trained via a triplet objective with online hard triplet mining.
no code implementations • NAACL (BioNLP) 2021 • Chen Lin, Timothy Miller, Dmitriy Dligach, Steven Bethard, Guergana Savova
We propose a methodology to produce a model focused on the clinical domain: continued pretraining of a model with a broad representation of biomedical terminology (PubMedBERT) on a clinical corpus along with a novel entity-centric masking strategy to infuse domain knowledge in the learning process.
no code implementations • EMNLP (Louhi) 2020 • Kristin Wright-Bettner, Chen Lin, Timothy Miller, Steven Bethard, Dmitriy Dligach, Martha Palmer, James H. Martin, Guergana Savova
We present refinements over existing temporal relation annotations in the Electronic Medical Record clinical narrative.
1 code implementation • ACL 2022 • Xin Su, Yiyun Zhao, Steven Bethard
Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free domain adaptation.
no code implementations • CoNLL (EMNLP) 2021 • Yiyun Zhao, Jian Gang Ngui, Lucy Hall Hartley, Steven Bethard
Pretrained transformer-based language models achieve state-of-the-art performance in many NLP tasks, but it is an open question whether the knowledge acquired by the models during pretraining resembles the linguistic knowledge of humans.
no code implementations • NAACL (ClinicalNLP) 2022 • Dmitriy Dligach, Steven Bethard, Timothy Miller, Guergana Savova
Sequence-to-sequence models are appealing because they allow both encoder and decoder to be shared across many tasks by formulating those tasks as text-to-text problems.
no code implementations • NAACL (ClinicalNLP) 2022 • Lijing Wang, Timothy Miller, Steven Bethard, Guergana Savova
In this paper, we investigate ensemble methods for fine-tuning transformer-based pretrained models for clinical natural language processing tasks, specifically temporal relation extraction from the clinical narrative.
no code implementations • NAACL (HCINLP) 2022 • Mihai Surdeanu, John Hungerford, Yee Seng Chan, Jessica MacBride, Benjamin Gyori, Andrew Zupon, Zheng Tang, Haoling Qiu, Bonan Min, Yan Zverev, Caitlin Hilverman, Max Thomas, Walter Andrews, Keith Alcock, Zeyu Zhang, Michael Reynolds, Steven Bethard, Rebecca Sharp, Egoitz Laparra
An existing domain taxonomy for normalizing content is often assumed when discussing approaches to information extraction, yet often in real-world scenarios there is none. When one does exist, as the information needs shift, it must be continually extended.
no code implementations • NAACL (CLPsych) 2022 • John Culnan, Damian Romero Diaz, Steven Bethard
This paper presents transformer-based models created for the CLPsych 2022 shared task.
no code implementations • EACL (AdaptNLP) 2021 • Timothy Miller, Egoitz Laparra, Steven Bethard
Advances in transfer learning and domain adaptation have raised hopes that once-challenging NLP tasks are ready to be put to use for sophisticated information extraction needs.
1 code implementation • WNUT (ACL) 2021 • Amanda Bertsch, Steven Bethard
On Wikipedia, an online crowdsourced encyclopedia, volunteers enforce the encyclopedia’s editorial policies.
no code implementations • 14 Nov 2023 • Xin Su, Tiep Le, Steven Bethard, Phillip Howard
An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external unstructured knowledge.
no code implementations • 30 Oct 2023 • Xin Su, Phillip Howard, Nagib Hakim, Steven Bethard
Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents.
1 code implementation • 18 May 2023 • Zeyu Zhang, Steven Bethard
Geocoding is the task of converting location mentions in text into structured data that encodes the geospatial semantics.
1 code implementation • 28 Apr 2023 • Zhengzhong Liang, Zeyu Zhang, Steven Bethard, Mihai Surdeanu
Languages models have been successfully applied to a variety of reasoning tasks in NLP, yet the language models still suffer from compositional generalization.
no code implementations • 24 Oct 2022 • Steven Bethard
This opinion piece argues that there are some safe uses for random seeds: as part of the hyperparameter search to select a good model, creating an ensemble of several models, or measuring the sensitivity of the training algorithm to the random seed hyperparameter.
no code implementations • 7 May 2022 • Zhengzhong Liang, Tushar Khot, Steven Bethard, Mihai Surdeanu, Ashish Sabharwal
Considerable progress has been made recently in open-domain question answering (QA) problems, which require Information Retrieval (IR) and Reading Comprehension (RC).
no code implementations • SemEval (NAACL) 2022 • Nazia Tasnim, Md. Istiak Hossain Shihab, Asif Shahriyar Sushmit, Steven Bethard, Farig Sadeque
Many areas, such as the biological and healthcare domain, artistic works, and organization names, have nested, overlapping, discontinuous entity mentions that may even be syntactically or semantically ambiguous in practice.
1 code implementation • SEMEVAL 2021 • Egoitz Laparra, Xin Su, Yiyun Zhao, {\"O}zlem Uzuner, Timothy Miller, Steven Bethard
Participants are then tested on data representing a new (target) domain.
no code implementations • SEMEVAL 2021 • Xin Su, Yiyun Zhao, Steven Bethard
This paper describes our systems for negation detection and time expression recognition in SemEval 2021 Task 10, Source-Free Domain Adaptation for Semantic Processing.
no code implementations • NAACL 2021 • Zhengzhong Liang, Steven Bethard, Mihai Surdeanu
Moreover, models trained on simpler tasks tend to fail when directly tested on more complex problems.
no code implementations • NAACL 2021 • Vikas Yadav, Steven Bethard, Mihai Surdeanu
We specifically emphasize on the importance of retrieving evidence jointly by showing several comparative analyses to other methods that retrieve and rerank evidence sentences individually.
2 code implementations • COLING 2020 • Egoitz Laparra, Steven Bethard
But creating a dataset for this complex geoparsing task is difficult and, if done manually, would require a huge amount of effort to annotate the geographical shapes of not only the geolocation described but also the reference toponyms.
no code implementations • SEMEVAL 2020 • Moonsung Kim, Steven Bethard
In this paper, we describe our approaches and systems for the SemEval-2020 Task 11 on propaganda technique detection.
no code implementations • ACL 2020 • Yiyun Zhao, Steven Bethard
We apply this methodology to test BERT and RoBERTa on a hypothesis that some attention heads will consistently attend from a word in negation scope to the negation cue.
no code implementations • WS 2020 • Chen Lin, Timothy Miller, Dmitriy Dligach, Farig Sadeque, Steven Bethard, Guergana Savova
Recently BERT has achieved a state-of-the-art performance in temporal relation extraction from clinical Electronic Medical Records text.
no code implementations • WS 2020 • Samuel Gonz{\'a}lez-L{\'o}pez, Steven Bethard, Aurelio Lopez-Lopez
In undergraduate theses, a good methodology section should describe the series of steps that were followed in performing the research.
no code implementations • ACL 2020 • Dongfang Xu, Zeyu Zhang, Steven Bethard
Concept normalization, the task of linking textual mentions of concepts to concepts in an ontology, is challenging because ontologies are large.
1 code implementation • ACL 2020 • Vikas Yadav, Steven Bethard, Mihai Surdeanu
Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method.
no code implementations • IJCNLP 2019 • Vikas Yadav, Steven Bethard, Mihai Surdeanu
We show that the sentences selected by our method improve the performance of a state-of-the-art supervised QA model on two multi-hop QA datasets: AI2's Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC).
1 code implementation • COLING 2018 • Vikas Yadav, Steven Bethard
Named Entity Recognition (NER) is a key component in NLP systems for question answering, information retrieval, relation extraction, etc.
no code implementations • 11 Jul 2019 • Farig Sadeque, Steven Bethard
We classified these works based on our task definitions, and explored the machine learning models that have been used for any kind of participation prediction.
1 code implementation • NAACL 2019 • Vikas Yadav, Steven Bethard, Mihai Surdeanu
We propose a simple, fast, and mostly-unsupervised approach for non-factoid question answering (QA) called Alignment over Heterogeneous Embeddings (AHE).
1 code implementation • NAACL 2019 • Rebecca Sharp, Adarsh Pyarelal, Benjamin Gyori, Keith Alcock, Egoitz Laparra, Marco A. Valenzuela-Esc{\'a}rcega, Ajay Nagesh, Vikas Yadav, John Bachman, Zheng Tang, Heather Lent, Fan Luo, Mithun Paul, Steven Bethard, Kobus Barnard, Clayton Morrison, Mihai Surdeanu
Building causal models of complicated phenomena such as food insecurity is currently a slow and labor-intensive manual process.
no code implementations • SEMEVAL 2019 • Farig Sadeque, Stephen Rains, Yotam Shmargad, Kate Kenski, Kevin Coe, Steven Bethard
Incivility in public discourse has been a major concern in recent times as it can affect the quality and tenacity of the discourse negatively.
no code implementations • SEMEVAL 2019 • Vikas Yadav, Egoitz Laparra, Ti-Tai Wang, Mihai Surdeanu, Steven Bethard
We present the Named Entity Recognition (NER) and disambiguation model used by the University of Arizona team (UArizona) for the SemEval 2019 task 12.
no code implementations • WS 2019 • Chen Lin, Timothy Miller, Dmitriy Dligach, Steven Bethard, Guergana Savova
Classic methods for clinical temporal relation extraction focus on relational candidates within a sentence.
no code implementations • WS 2019 • Steven Bethard, Egoitz Laparra, Sophia Wang, Yiyun Zhao, Ragheb Al-Ghezi, Aaron Lien, Laura L{\'o}pez-Hoffman
The National Environmental Policy Act (NEPA) provides a trove of data on how environmental policy decisions have been made in the United States over the last 50 years.
no code implementations • SEMEVAL 2019 • Dongfang Xu, Egoitz Laparra, Steven Bethard
Recent studies have shown that pre-trained contextual word embeddings, which assign the same word different vectors in different contexts, improve performance in many tasks.
no code implementations • WS 2018 • Chen Lin, Timothy Miller, Dmitriy Dligach, Hadi Amiri, Steven Bethard, Guergana Savova
Neural network models are oftentimes restricted by limited labeled instances and resort to advanced architectures and features for cutting edge performance.
no code implementations • SEMEVAL 2018 • Egoitz Laparra, Dongfang Xu, Ahmed Elsayed, Steven Bethard, Martha Palmer
This paper presents the outcomes of the Parsing Time Normalization shared task held within SemEval-2018.
1 code implementation • SEMEVAL 2018 • Vikas Yadav, Rebecca Sharp, Steven Bethard
We propose a practical model for named entity recognition (NER) that combines word and character-level information with a specific learned representation of the prefixes and suffixes of the word.
1 code implementation • TACL 2018 • Egoitz Laparra, Dongfang Xu, Steven Bethard
This paper presents the first model for time normalization trained on the SCATE corpus.
Ranked #1 on Timex normalization on PNT
no code implementations • SEMEVAL 2017 • Steven Bethard, Guergana Savova, Martha Palmer, James Pustejovsky
Clinical TempEval 2017 aimed to answer the question: how well do systems trained on annotated timelines for one medical condition (colon cancer) perform in predicting timelines on another medical condition (brain cancer)?
no code implementations • WS 2017 • Timothy Miller, Steven Bethard, Hadi Amiri, Guergana Savova
Detecting negated concepts in clinical texts is an important part of NLP information extraction systems.
no code implementations • WS 2017 • Chen Lin, Timothy Miller, Dmitriy Dligach, Steven Bethard, Guergana Savova
Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing.
no code implementations • IJCNLP 2017 • Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens
Implicit semantic role labeling (iSRL) is the task of predicting the semantic roles of a predicate that do not appear as explicit arguments, but rather regard common sense knowledge or are mentioned earlier in the discourse.
no code implementations • EACL 2017 • Dmitriy Dligach, Timothy Miller, Chen Lin, Steven Bethard, Guergana Savova
We experiment with neural architectures for temporal relation extraction and establish a new state-of-the-art for several scenarios.
no code implementations • COLING 2016 • Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens
We present a successful collaboration of word embeddings and co-training to tackle in the most difficult test case of semantic role labeling: predicting out-of-domain and unseen semantic frames.
1 code implementation • LREC 2016 • Steven Bethard, Jonathan Parker
We present a new annotation scheme for normalizing time expressions, such as {``}three days ago{''}, to computer-readable forms, such as 2016-03-07.
no code implementations • LREC 2016 • Prasha Shrestha, Nicolas Rey-Villamizar, Farig Sadeque, Ted Pedersen, Steven Bethard, Thamar Solorio
Health support forums have become a rich source of data that can be used to improve health care outcomes.
no code implementations • LREC 2014 • Steven Bethard, Philip Ogren, Lee Becker
ClearTK adds machine learning functionality to the UIMA framework, providing wrappers to popular machine learning libraries, a rich feature extraction library that works across different classifiers, and utilities for applying and evaluating machine learning models.
no code implementations • 19 Mar 2014 • Steven Bethard, Leon Derczynski, James Pustejovsky, Marc Verhagen
We describe the Clinical TempEval task which is currently in preparation for the SemEval-2015 evaluation exercise.
no code implementations • TACL 2014 • Nathanael Chambers, Taylor Cassidy, Bill McDowell, Steven Bethard
We experiment on the densest event graphs to date and show a 14{\%} gain over state-of-the-art.
Ranked #2 on Temporal Information Extraction on TimeBank
no code implementations • TACL 2014 • William F. Styler IV, Steven Bethard, Sean Finan, Martha Palmer, Sameer Pradhan, Piet C de Groen, Brad Erickson, Timothy Miller, Chen Lin, Guergana Savova, James Pustejovsky
The corpus is available to the community and has been proposed for use in a SemEval 2015 task.
no code implementations • TACL 2014 • Md. Arafat Sultan, Steven Bethard, Tamara Sumner
We present a simple, easy-to-replicate monolingual aligner that demonstrates state-of-the-art performance while relying on almost no supervision and a very small number of external resources.
no code implementations • LREC 2012 • Steven Bethard, Oleks Kolomiyets, R, Marie-Francine Moens
We present an approach to annotating timelines in stories where events are linked together by temporal relations into a temporal dependency tree.