Papers

Learn more about AI2's Lasting Impact Award
Viewing 31-40 of 835 papers
  • Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning

    Oyvind Tafjord, Bhavana Dalvi Mishra, Peter ClarkEMNLP2022 Our goal is a question-answering (QA) system that can show how its answers are implied by its own internal beliefs via a systematic chain of reasoning . Such a capability would allow better understanding of why a model produced the answer it did. Our approach…
  • GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation

    Daniel Khashabi, Gabriel Stanovsky, Jonathan Bragg, Nicholas Lourie, Jungo Kasai, Yejin Choi, Noah A. Smith, Daniel S. WeldEMNLP2022 While often assumed a gold standard, effective human evaluation of text generation remains an important, open area for research. We revisit this problem with a focus on pro-ducing consistent evaluations that are reproducible —over time and across different…
  • How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers

    Michael Hassid, Hao Peng, Daniel Rotem, Jungo Kasai, Ivan Montero, Noah Smith, Roy SchwartzEMNLP Findings2022 The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as important as…
  • In-Context Learning for Few-Shot Dialogue State Tracking

    Yushi Hu, Chia-Hsuan Lee, Tianbao Xie, Tao Yu, Noah A. Smith, Mari OstendorfEMNLP Findings2022 Collecting and annotating task-oriented dialogues is time-consuming and costly. Thus, zero and few shot learning for dialogue tasks presents an exciting opportunity. In this work, we propose an in-context (IC) learning framework for zero-shot and few-shot…
  • Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning

    Xiangyu Peng, Siyan Li, Sarah Wiegreffe, Mark O. RiedlFindings of EMNLP2022 Transformer-based language model approaches to automated story generation currently provide state-of-the-art results. However, they still suffer from plot incoherence when generating narratives over time, and critically lack basic commonsense reasoning…
  • Knowledge Transfer from Answer Ranking to Answer Generation

    Matteo Gabburo, Rik Koncel-Kedziorski, Siddhant Garg, Luca Soldaini, Alessandro MoschittiEMNLP2022 Recent studies show that Question Answering (QA) based on Answer Sentence Selection (AS2) can be improved by generating an improved answer from the top-k ranked answer sentences (termed GenQA). This allows for synthesizing the information from multiple…
  • Lexical Generalization Improves with Larger Models and Longer Training

    Elron Bandel, Yoav Goldberg, Yanai ElazarFinding of EMNLP2022 While fine-tuned language models perform well on many tasks, they were also shown to rely on superficial surface features such as lexical overlap. Excessive utilization of such heuristics can lead to failure on challenging inputs. We analyze the use of lexical…
  • Modeling Context With Linear Attention for Scalable Document-Level Translation

    Zhaofeng Wu, Hao Peng, Nikolaos Pappas, Noah A. SmithFindings of EMNLP 2022 Document-level machine translation leverages inter-sentence dependencies to produce more coherent and consistent translations. However, these models, predominantly based on transformers, are difficult to scale to long documents as their attention layers have…
  • On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization

    Shruti Palaskar, Akshita Bhagia, Yonatan Bisk, Florian Metze, A. Black, Ana MarasovićFindings of EMNLP2022 Integrating vision and language has gained no-table attention following the success of pretrained language models. Despite that, a fraction of emerging multimodal models is suitable for text generation conditioned on images. This minority is typically…
  • Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

    Luca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro MoschittiEMNLP2022 An important task for designing QA systems is answer sentence selection (AS2): select-ing the sentence containing (or constituting) the answer to a question from a set of re-trieved relevant documents. In this paper, we propose three novel sentence-level…