Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

Threddy: An Interactive System for Personalized Thread-based Exploration and Organization of Scientific Literature

Hyeonsu B. KangJoseph Chee ChangYongsung KimAniket Kittur
2022
UIST

Reviewing the literature to understand relevant threads of past work is a critical part of research and vehicle for learning. However, as the scientific literature grows the challenges for users to… 

SciFact-Open: Towards open-domain scientific claim verification

David WaddenKyle LoBailey KuehlHannaneh Hajishirzi
2022
EMNLP 2022

While research on scientific claim verification has led to the development of powerful systems that appear to approach human performance, these approaches have yet to be tested in a realistic… 

A Dataset of Alt Texts from HCI Publications

Sanjana ChintalapatiJonathan BraggLucy Lu Wang
2022
ASSETS

Figures in scientifc publications contain important information and results, and alt text is needed for blind and low vision readers to engage with their content. We conduct a study to characterize… 

Multi-Scale Contrastive Co-Training for Event Temporal Relation Extraction

Hao-Ren YaoLuke BreitfellerAakanksha NaikCarolyn Rosé
2022
arXiv.org

Extracting temporal relationships between pairs of events in texts is a crucial yet challenging problem for natural language understanding. Depending on the distance between the events, models must… 

Few-Shot Self-Rationalization with Natural Language Prompts

Ana MarasovićIz BeltagyDoug DowneyMatthew E. Peters
2022
Findings of NAACL

Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These models are, however,… 

Literature-Augmented Clinical Outcome Prediction

Aakanksha NaikS. ParasaSergey FeldmanTom Hope
2022
Findings of NAACL

We present BEEP (Biomedical Evidence-Enhanced Predictions), a novel approach for clinical outcome prediction that retrieves patient-specific medical literature and incorporates it into predictive… 

Long Context Question Answering via Supervised Contrastive Learning

Avi CaciularuIdo DaganJacob GoldbergerArman Cohan
2022
NAACL

Long-context question answering (QA) tasks require reasoning over a long document or multiple documents. Addressing these tasks often benefits from identifying a set of evidence spans (e.g.,… 

MultiVerS: Improving scientific claim verification with weak supervision and full-document context

David WaddenKyle LoLucy Lu WangHannaneh Hajishirzi
2022
Findings of NAACL

The scientific claim verification task requires an NLP system to label scientific documents which Support or Refute an input claim, and to select evidentiary sentences (or rationales) justifying… 

Paragraph-based Transformer Pre-training for Multi-Sentence Inference

Luca Di LielloSiddhant GargLuca SoldainiAlessandro Moschitti
2022
NAACL

Inference tasks such as answer sentence selection (AS2) or fact verification are typically solved by fine-tuning transformer-based models as individual sentence-pair classifiers. Recent studies show… 

Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities

Zejiang ShenKyle LoLauren YuDoug Downey
2022
arXiv

With the advent of large language models, methods for abstractive summarization have made great strides, creating potential for use in applications to aid knowledge workers processing unwieldy…