Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 41-50 of 553 papers
Neural Extractive Search
Shaul Ravfogel, Hillel Taub-Tabib, Yoav GoldbergACL • Demo Track • 2021 Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called “extractive search”, in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search… morePAWLS: PDF Annotation With Labels and Structure
Mark Neumann, Zejiang Shen, Sam SkjonsbergDemo • ACL • 2021 Adobe’s Portable Document Format (PDF) is a popular way of distributing view-only documents with a rich visual markup. This presents a challenge to NLP practitioners who wish to use the information contained within PDF documents for training models or data… morePIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World
Rowan Zellers, Ari Holtzman, Matthew E. Peters, R. Mottaghi, Aniruddha Kembhavi, A. Farhadi, Yejin ChoiACL • 2021 We propose PIGLeT: a model that learns physical commonsense knowledge through interaction, and then uses this knowledge to ground language. We factorize PIGLeT into a physical dynamics model, and a separate language model. Our dynamics model learns not just… morePromoting Graph Awareness in Linearized Graph-to-Text Generation
Alexander M. Hoyle, Ana Marasović, Noah A. SmithFindings of ACL • 2021 Generating text from structured inputs, such as meaning representations or RDF triples, has often involved the use of specialized graphencoding neural networks. However, recent applications of pretrained transformers to linearizations of graph inputs have… moreQuestion Decomposition with Dependency Graphs
Matan Hasson, Jonathan BerantACL-IJCNLP • 15th Workshop on Structured Prediction for NLP • 2021 QDMR is a meaning representation for complex questions, which decomposes questions into a sequence of atomic steps. While stateof-the-art QDMR parsers use the common sequence-to-sequence (seq2seq) approach, a QDMR structure fundamentally describes labeled… moreShortformer: Better Language Modeling using Shorter Inputs
Ofir Press, Noah A. Smith, M. LewisACL • 2021 We explore the benefits of decreasing the input length of transformers. First, we show that initially training the model on short subsequences, before moving on to longer ones, both reduces overall training time and, surprisingly, gives a large improvement in… moreProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
Oyvind Tafjord, B. D. Mishra, P. ClarkFindings of ACL • 2021 Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate implications of a theory… moreBreak, Perturb, Build: Automatic Perturbation of Reasoning Paths through Question Decomposition
Mor Geva, Tomer Wolfson, Jonathan BerantarXiv • 2021 Recent efforts to create challenge benchmarks that test the abilities of natural language understanding models have largely depended on human annotations. In this work, we introduce the “Break, Perturb, Build” (BPB) framework for automatic reasoning-oriented… moreFLEX: Unifying Evaluation for Few-Shot NLP
Jonathan Bragg, Arman Cohan, Kyle Lo, Iz BeltagyarXiv • 2021 Few-shot NLP research is highly active, yet conducted in disjoint research threads with evaluation suites that lack challenging-yet-realistic testing setups and fail to employ careful experimental design. Consequently, the community does not know which… moreTurning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills
Ori Yoran, Alon Talmor, Jonathan BerantarXiv • 2021 Models pre-trained with a language modeling objective possess ample world knowledge and language skills, but are known to struggle in tasks that require reasoning. In this work, we propose to leverage semi-structured tables, and automatically generate at… more