research
∙
09/16/2023
PDFTriage: Question Answering over Long, Structured Documents
Large Language Models (LLMs) have issues with document question answerin...
share
research
∙
06/18/2023
Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness
Academic literature does not give much guidance on how to build the best...
research
∙
05/20/2023
Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer
In real-world scenarios, labeled samples for dialogue summarization are ...
research
∙
02/23/2023
Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
Effective figure captions are crucial for clear comprehension of scienti...
research
∙
11/27/2022
MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
Document images are a ubiquitous source of data where the text is organi...
research
∙
10/25/2022
Influence Functions for Sequence Tagging Models
Many language tasks (e.g., Named Entity Recognition, Part-of-Speech tagg...
research
∙
10/14/2022
Self-Repetition in Abstractive Neural Summarizers
We provide a quantitative and qualitative analysis of self-repetition in...
research
∙
11/24/2021
Temporal Effects on Pre-trained Models for Language Processing Tasks
Keeping the performance of language technologies optimal as time passes ...
research
∙
02/06/2021
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution
The ability to quantify incivility online, in news and in congressional ...
research
∙
10/07/2020
Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relations
The best evidence concerning comparative treatment effectiveness comes f...
research
∙
05/21/2020
Trialstreamer: Mapping and Browsing Medical Evidence in Real-Time
We introduce Trialstreamer, a living database of clinical trial reports....
research
∙
04/09/2020
Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve
Named Entity Recognition systems achieve remarkable performance on domai...
research
∙
04/08/2020
Entity-Switched Datasets: An Approach to Auditing the In-Domain Robustness of Named Entity Recognition Models
Named entity recognition systems perform well on standard datasets compr...
research
∙
05/19/2019
Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction
Modern NLP systems require high-quality annotated data. In specialized d...
research
∙
10/26/2018
Named Person Coreference in English News
People are often entities of interest in tasks such as search and inform...
research
∙
06/11/2018
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature
We present a corpus of 5,000 richly annotated abstracts of medical artic...
research
∙
04/30/2018
Syntactic Patterns Improve Information Extraction for Medical Search
Medical professionals search the published literature by specifying the ...
research
∙
04/03/2017
Combining Lexical and Syntactic Features for Detecting Content-dense Texts in News
Content-dense news report important factual information about an event i...
research
∙
02/26/2017