Research

PapersDataVideosDemosLeaderboardsSoftwarePodcasts

Research

Papers

Viewing 1-10 of 77 papers

  • Analyzing Compositionality in Visual Question Answering

    Sanjay Subramanian, Sameer Singh, Matt GardnerNeurIPS • ViGIL Workshop • 2020Since the release of the original Visual Question Answering (VQA) dataset, several newer datasets for visual reasoning have been introduced, often with the express intent of requiring systems to perform compositional reasoning. Recently, transformer models pretrained on large amounts of images and… more

  • Break It Down: A Question Understanding Benchmark

    Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner, Yoav Goldberg, Daniel Deutch, Jonathan BerantTACL • 2020Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning Representation (QDMR) for questions. QDMR constitutes the ordered list of steps, expressed through… more

  • A Formal Hierarchy of RNN Architectures

    William. Merrill, Gail Garfinkel Weiss, Yoav Goldberg, Roy Schwartz, Noah A. Smith, Eran YahavACL • 2020We develop a formal hierarchy of the expressive capacity of RNN architectures. The hierarchy is based on two formal properties: space complexity, which measures the RNN's memory, and rational recurrence, defined as whether the recurrent update can be described by a weighted finite-state machine. We… more

  • A Mixture of h-1 Heads is Better than h Heads

    Hao Peng, Roy Schwartz, Dianqi Li, Noah A. SmithACL • 2020Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks. Evidence has shown that they are overparameterized; attention heads can be pruned without significant performance loss. In this work, we instead "reallocate" them… more

  • Don't Stop Pretraining: Adapt Language Models to Domains and Tasks

    Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, Noah A. SmithACL • 2020
    Best Paper Award Honorable Mention
    Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the domain of a target task. We present a study across four… more

  • Improving Transformer Models by Reordering their Sublayers

    Ofir Press, Noah A. Smith, Omer LevyACL • 2020Multilayer transformer networks consist of interleaved self-attention and feedforward sublayers. Could ordering the sublayers in a different pattern lead to better performance? We generate randomly ordered transformers and train them with the language modeling objective. We observe that some of… more

  • Obtaining Faithful Interpretations from Compositional Neural Networks

    Sanjay Subramanian, Ben Bogin, Nitish Gupta, Tomer Wolfson, Sameer Singh, Jonathan Berant, Matt Gardner ACL • 2020Neural module networks (NMNs) are a popular approach for modeling compositionality: they achieve high accuracy when applied to problems in language and vision, while reflecting the compositional structure of the problem in the network architecture. However, prior work implicitly assumed that the… more

  • QuASE: Question-Answer Driven Sentence Encoding.

    Hangfeng He, Qiang Ning, Dan RothACL • 2020Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, {\em can we use QAMR (Michael et al., 2017) to improve named entity recognition?} We… more

  • Recollection versus Imagination: Exploring Human Memory and Cognition via Neural Language Models

    Maarten Sap, Eric Horvitz, Yejin Choi, Noah A. Smith, James W. Pennebaker ACL • 2020We investigate the use of NLP as a measure of the cognitive processes involved in storytelling, contrasting imagination and recollection of events. To facilitate this, we collect and release HIPPOCORPUS, a dataset of 7,000 stories about imagined and recalled events. We introduce a measure of… more

  • Social Bias Frames: Reasoning about Social and Power Implications of Language

    Maarten Sap, Saadia Gabriel, Lianhui Qin, Dan Jurafsky, Noah A. Smith, Yejin ChoiACL • 2020Language has the power to reinforce stereotypes and project social biases onto others. At the core of the challenge is that it is rarely what is stated explicitly, but all the implied meanings that frame people's judgements about others. For example, given a seemingly innocuous statement "we… more