Search Results for author:
Found 93 papers, 15 papers with code
UA-KO at SemEval-2022 Task 11: Data Augmentation and Ensembles for Korean Named Entity Recognition
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.
Simplifying annotation of intersections in time normalization annotation: exploring syntactic and semantic validation
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.
Fine-tuning for multi-domain and multi-label uncivil language detection
Incivility is a problem on social media, and it comes in many forms (name-calling, vulgarity, threats, etc.)
Triplet-Trained Vector Space and Sieve-Based Search Improve Biomedical Concept Normalization
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.
EntityBERT: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain
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.
Defining and Learning Refined Temporal Relations in the Clinical Narrative
We present refinements over existing temporal relation annotations in the Electronic Medical Record clinical narrative.
A Comparison of Strategies for Source-Free Domain Adaptation
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.
Do pretrained transformers infer telicity like humans?
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.
Exploring Text Representations for Generative Temporal Relation Extraction
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.
Ensemble-based Fine-Tuning Strategy for Temporal Relation Extraction from the Clinical Narrative
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.
Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction
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.
Exploring transformers and time lag features for predicting changes in mood over time
This paper presents transformer-based models created for the CLPsych 2022 shared task.
Domain adaptation in practice: Lessons from a real-world information extraction pipeline
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.
Detection of Puffery on the English Wikipedia
On Wikipedia, an online crowdsourced encyclopedia, volunteers enforce the encyclopedia’s editorial policies.
Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning
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.
Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering
Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents.
Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution
Geocoding is the task of converting location mentions in text into structured data that encodes the geospatial semantics.
Explainable Verbal Reasoner Plus (EVR+): A Natural Language Reasoning Framework that Supports Diverse Compositional Reasoning
Languages models have been successfully applied to a variety of reasoning tasks in NLP, yet the language models still suffer from compositional generalization.
We need to talk about random seeds
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.
Better Retrieval May Not Lead to Better Question Answering
Considerable progress has been made recently in open-domain question answering (QA) problems, which require Information Retrieval (IR) and Reading Comprehension (RC).
TEAM-Atreides at SemEval-2022 Task 11: On leveraging data augmentation and ensemble to recognize complex Named Entities in Bangla
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.
SemEval-2021 Task 10: Source-Free Domain Adaptation for Semantic Processing
Participants are then tested on data representing a new (target) domain.
The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation
This paper describes our systems for negation detection and time expression recognition in SemEval 2021 Task 10, Source-Free Domain Adaptation for Semantic Processing.
Explainable Multi-hop Verbal Reasoning Through Internal Monologue
Moreover, models trained on simpler tasks tend to fail when directly tested on more complex problems.
If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering
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.
A Dataset and Evaluation Framework for Complex Geographical Description Parsing
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.
TTUI at SemEval-2020 Task 11: Propaganda Detection with Transfer Learning and Ensembles
In this paper, we describe our approaches and systems for the SemEval-2020 Task 11 on propaganda technique detection.
How does BERT's attention change when you fine-tune? An analysis methodology and a case study in negation scope
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.
A BERT-based One-Pass Multi-Task Model for Clinical Temporal Relation Extraction
Recently BERT has achieved a state-of-the-art performance in temporal relation extraction from clinical Electronic Medical Records text.
Assisting Undergraduate Students in Writing Spanish Methodology Sections
In undergraduate theses, a good methodology section should describe the series of steps that were followed in performing the research.
A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization
Concept normalization, the task of linking textual mentions of concepts to concepts in an ontology, is challenging because ontologies are large.
Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering
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.
Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering
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).
A Survey on Recent Advances in Named Entity Recognition from Deep Learning models
Named Entity Recognition (NER) is a key component in NLP systems for question answering, information retrieval, relation extraction, etc.
Predicting engagement in online social networks: Challenges and opportunities
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.
Alignment over Heterogeneous Embeddings for Question Answering
We propose a simple, fast, and mostly-unsupervised approach for non-factoid question answering (QA) called Alignment over Heterogeneous Embeddings (AHE).
Eidos, INDRA, \& Delphi: From Free Text to Executable Causal Models
Building causal models of complicated phenomena such as food insecurity is currently a slow and labor-intensive manual process.
Incivility Detection in Online Comments
Incivility in public discourse has been a major concern in recent times as it can affect the quality and tenacity of the discourse negatively.
University of Arizona at SemEval-2019 Task 12: Deep-Affix Named Entity Recognition of Geolocation Entities
We present the Named Entity Recognition (NER) and disambiguation model used by the University of Arizona team (UArizona) for the SemEval 2019 task 12.
Inferring missing metadata from environmental policy texts
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.
Pre-trained Contextualized Character Embeddings Lead to Major Improvements in Time Normalization: a Detailed Analysis
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.
Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction
Neural network models are oftentimes restricted by limited labeled instances and resort to advanced architectures and features for cutting edge performance.
SemEval 2018 Task 6: Parsing Time Normalizations
This paper presents the outcomes of the Parsing Time Normalization shared task held within SemEval-2018.
Deep Affix Features Improve Neural Named Entity Recognizers
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.
From Characters to Time Intervals: New Paradigms for Evaluation and Neural Parsing of Time Normalizations
This paper presents the first model for time normalization trained on the SCATE corpus.
Ranked #1 on
Timex normalization
on PNT
SemEval-2017 Task 12: Clinical TempEval
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)?
Unsupervised Domain Adaptation for Clinical Negation Detection
Detecting negated concepts in clinical texts is an important part of NLP information extraction systems.
Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks
Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing.
Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments
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.
Facing the most difficult case of Semantic Role Labeling: A collaboration of word embeddings and co-training
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.
A Semantically Compositional Annotation Scheme for Time Normalization
We present a new annotation scheme for normalizing time expressions, such as {``}three days ago{''}, to computer-readable forms, such as 2016-03-07.
Age and Gender Prediction on Health Forum Data
Health support forums have become a rich source of data that can be used to improve health care outcomes.
ClearTK 2.0: Design Patterns for Machine Learning in UIMA
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.
Clinical TempEval
We describe the Clinical TempEval task which is currently in preparation for the SemEval-2015 evaluation exercise.
Dense Event Ordering with a Multi-Pass Architecture
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
Temporal Annotation in the Clinical Domain
The corpus is available to the community and has been proposed for use in a SemEval 2015 task.
Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence
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.
Annotating Story Timelines as Temporal Dependency Structures
We present an approach to annotating timelines in stories where events are linked together by temporal relations into a temporal dependency tree.
