research
∙
05/31/2023
From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces
Much of the previous work towards digital agents for graphical user inte...
share
research
∙
02/22/2023
Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
Large-scale multi-modal pre-training models such as CLIP and PaLI exhibi...
research
∙
05/09/2022
Few-shot Mining of Naturally Occurring Inputs and Outputs
Creating labeled natural language training data is expensive and require...
research
∙
04/15/2022
Improving Passage Retrieval with Zero-Shot Question Generation
We propose a simple and effective re-ranking method for improving passag...
research
∙
01/19/2022
CM3: A Causal Masked Multimodal Model of the Internet
We introduce CM3, a family of causally masked generative models trained ...
research
∙
07/14/2021
HTLM: Hyper-Text Pre-Training and Prompting of Language Models
We introduce HTLM, a hyper-text language model trained on a large-scale ...
research
∙
06/09/2021
DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions
Short textual descriptions of entities provide summaries of their key at...
research
∙
06/08/2021
Realistic Evaluation Principles for Cross-document Coreference Resolution
We point out that common evaluation practices for cross-document corefer...
research
∙
06/02/2021
Cross-document Coreference Resolution over Predicted Mentions
Coreference resolution has been mostly investigated within a single docu...
research
∙
02/16/2021
FEWS: Large-Scale, Low-Shot Word Sense Disambiguation with the Dictionary
Current models for Word Sense Disambiguation (WSD) struggle to disambigu...
research
∙
09/23/2020
Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling
Recent evaluation protocols for Cross-document (CD) coreference resoluti...
research
∙
05/01/2020
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
Decisions of complex language understanding models can be rationalized b...
research
∙
04/24/2020
Contextualized Representations Using Textual Encyclopedic Knowledge
We present a method to represent input texts by contextualizing them joi...
research
∙
08/24/2019
BERT for Coreference Resolution: Baselines and Analysis
We apply BERT to coreference resolution, achieving strong improvements o...
research
∙
07/26/2019
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Language model pretraining has led to significant performance gains but ...
research
∙
07/24/2019
SpanBERT: Improving Pre-training by Representing and Predicting Spans
We present SpanBERT, a pre-training method that is designed to better re...
research
∙
10/20/2018
pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
Reasoning about implied relationships (e.g. paraphrastic, common sense, ...
research
∙
05/09/2017