Search Results for author:
Found 46 papers, 23 papers with code
Scideator: Human-LLM Scientific Idea Generation Grounded in Research-Paper Facet Recombination
The scientific ideation process often involves blending salient aspects of existing papers to create new ideas.
Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows
The design space covers a designer's objectives and the tactics used to build workflows.
In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making
To synthesize these findings, we propose a simple theory that elucidates the frequent failure of AI explanations to engender appropriate reliance and complementary decision making performance.
The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces
Scholarly publications are key to the transfer of knowledge from scholars to others.
An Interactive UI to Support Sensemaking over Collections of Parallel Texts
Scientists and science journalists, among others, often need to make sense of a large number of papers and how they compare with each other in scope, focus, findings, or any other important factors.
ScatterShot: Interactive In-context Example Curation for Text Transformation
ScatterShot iteratively slices unlabeled data into task-specific patterns, samples informative inputs from underexplored or not-yet-saturated slices in an active learning manner, and helps users label more efficiently with the help of an LLM and the current example set.
The Semantic Scholar Open Data Platform
The volume of scientific output is creating an urgent need for automated tools to help scientists keep up with developments in their field.
FeedLens: Polymorphic Lenses for Personalizing Exploratory Search over Knowledge Graphs
We implement our technique in a novel system, FeedLens, which is built over Semantic Scholar, a production system for navigating the scientific literature KG.
ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts
We present ACCoRD, an end-to-end system tackling the novel task of generating sets of descriptions of scientific concepts.
Few-shot Mining of Naturally Occurring Inputs and Outputs
Creating labeled natural language training data is expensive and requires significant human effort.
A Computational Inflection for Scientific Discovery
We stand at the foot of a significant inflection in the trajectory of scientific discovery.
Exploring How Anomalous Model Input and Output Alerts Affect Decision-Making in Healthcare
An important goal in the field of human-AI interaction is to help users more appropriately trust AI systems' decisions.
From Who You Know to What You Read: Augmenting Scientific Recommendations with Implicit Social Networks
To improve the discovery experience we introduce multiple new methods for \em augmenting recommendations with textual relevance messages that highlight knowledge-graph connections between recommended papers and a user's publication and interaction history.
Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search
Based on our findings, we present PINOCCHIO, a new decoding method that improves the consistency of a transformer-based abstractive summarizer by constraining beam search to avoid hallucinations.
Exploring The Role of Local and Global Explanations in Recommender Systems
However, we note that the two explanation approaches may be better compared in the context of a higher-stakes or more opaque domain.
A Search Engine for Discovery of Scientific Challenges and Directions
To address this problem, we present a novel task of extraction and search of scientific challenges and directions, to facilitate rapid knowledge discovery.
VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups
Experiments are conducted on a newly curated evaluation suite, S2-VLUE, that unifies existing automatically-labeled datasets and includes a new dataset of manual annotations covering diverse papers from 19 scientific disciplines.
GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation
While often assumed a gold standard, effective human evaluation of text generation remains an important, open area for research.
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models
While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only instantiate limited types of perturbations such as paraphrases or word substitutions.
Document-Level Definition Detection in Scholarly Documents: Existing Models, Error Analyses, and Future Directions
Based on this analysis, we develop a new definition detection system, HEDDEx, that utilizes syntactic features, transformer encoders, and heuristic filters, and evaluate it on a standard sentence-level benchmark.
Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols
We introduce ScholarPhi, an augmented reading interface with four novel features: (1) tooltips that surface position-sensitive definitions from elsewhere in a paper, (2) a filter over the paper that "declutters" it to reveal how the term or symbol is used across the paper, (3) automatic equation diagrams that expose multiple definitions in parallel, and (4) an automatically generated glossary of important terms and symbols.
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
However, prior studies observed improvements from explanations only when the AI, alone, outperformed both the human and the best team.
High-Precision Extraction of Emerging Concepts from Scientific Literature
From a corpus of computer science papers on arXiv, we find that our method achieves a Precision@1000 of 99%, compared to 86% for prior work, and a substantially better precision-yield trade-off across the top 15, 000 extractions.
Knowledge Base Construction
Vocal Bursts Intensity Prediction
SciSight: Combining faceted navigation and research group detection for COVID-19 exploratory scientific search
The COVID-19 pandemic has sparked unprecedented mobilization of scientists, generating a deluge of papers that makes it hard for researchers to keep track and explore new directions.
The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America
We report the results of running the pipeline on 16. 3 million pages from the Chronicling America corpus and describe the resulting Newspaper Navigator dataset, the largest dataset of extracted visual content from historic newspapers ever produced.
TLDR: Extreme Summarization of Scientific Documents
We introduce TLDR generation, a new form of extreme summarization, for scientific papers.
Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork
To optimize the team performance for this setting we maximize the team's expected utility, expressed in terms of the quality of the final decision, cost of verifying, and individual accuracies of people and machines.
CORD-19: The COVID-19 Open Research Dataset
The COVID-19 Open Research Dataset (CORD-19) is a growing resource of scientific papers on COVID-19 and related historical coronavirus research.
SPECTER: Document-level Representation Learning using Citation-informed Transformers
We propose SPECTER, a new method to generate document-level embedding of scientific documents based on pretraining a Transformer language model on a powerful signal of document-level relatedness: the citation graph.
Ranked #1 on
Document Classification
on SciDocs (MAG)
LIMEADE: From AI Explanations to Advice Taking
We show our method improves accuracy compared to a rigorous baseline on the image classification domains.
Pretrained Language Models for Sequential Sentence Classification
As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in context of the document.
BERT for Coreference Resolution: Baselines and Analysis
We apply BERT to coreference resolution, achieving strong improvements on the OntoNotes (+3. 9 F1) and GAP (+11. 5 F1) benchmarks.
Ranked #11 on
Coreference Resolution
on CoNLL 2012
(using extra training data)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text.
Ranked #1 on
Question Answering
on NewsQA
(F1 metric)
pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
Reasoning about implied relationships (e. g., paraphrastic, common sense, encyclopedic) between pairs of words is crucial for many cross-sentence inference problems.
Semi-Supervised Event Extraction with Paraphrase Clusters
Supervised event extraction systems are limited in their accuracy due to the lack of available training data.
StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow
In this paper, we investigate a new problem of systematically mining question-code pairs from Stack Overflow (in contrast to heuristically collecting them).
The Challenge of Crafting Intelligible Intelligence
Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand.
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
We present TriviaQA, a challenging reading comprehension dataset containing over 650K question-answer-evidence triples.
A Programming Language With a POMDP Inside
We present POAPS, a novel planning system for defining Partially Observable Markov Decision Processes (POMDPs) that abstracts away from POMDP details for the benefit of non-expert practitioners.
Extreme Extraction: Only One Hour per Relation
Information Extraction (IE) aims to automatically generate a large knowledge base from natural language text, but progress remains slow.
Design Challenges for Entity Linking
Recent research on entity linking (EL) has introduced a plethora of promising techniques, ranging from deep neural networks to joint inference.
