Raphael Tang, Linqing Liu, Akshat Pandey, Zhiying Jiang, Gefei Yang, Karun Kumar, Pontus Stenetorp, Jimmy Lin, Ferhan Ture. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Recently, flat-minima optimizers, which seek to find parameters in low-loss neighborhoods, have been shown to improve a neural network's generalization performance over stochastic and adaptive gradient-based optimizers. Two methods have received significant attention due to their scalability: 1. Stochastic Weight Averaging (SWA), and 2. Sharpness-Aware Minimization (SAM). However, there has been limited investigation into their properties and no systematic benchmarking of them across different domains. We fill this gap here by comparing the loss surfaces of the models trained with each method and through broad benchmarking across computer vision, natural language processing, and graph representation learning tasks. We discover several surprising findings from these results, which we hope will help researchers further improve deep learning optimizers, and practitioners identify the right optimizer for their problem.

Abstract Open-domain Question Answering models that directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared with conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models fall short of the accuracy of retrieve-and-read systems, as substantially less knowledge is covered by the available QA-pairs relative to text corpora like Wikipedia. To facilitate improved QA-pair models, we introduce Probably Asked Questions (PAQ), a very large resource of 65M automatically generated QA-pairs. We introduce a new QA-pair retriever, RePAQ, to complement PAQ. We find that PAQ preempts and caches test questions, enabling RePAQ to match the accuracy of recent retrieve-and-read models, whilst being significantly faster. Using PAQ, we train CBQA models which outperform comparable baselines by 5%, but trail RePAQ by over 15%, indicating the effectiveness of explicit retrieval. RePAQ can be configured for size (under 500MB) or speed (over 1K questions per second) while retaining high accuracy. Lastly, we demonstrate RePAQ’s strength at selective QA, abstaining from answering when it is likely to be incorrect. This enables RePAQ to “back-off” to a more expensive state-of-the-art model, leading to a combined system which is both more accurate and 2x faster than the state-of-the-art model alone.

We propose a Multi-task learning approach for Abstractive Text Summarization (MATS), motivated by the fact that humans have no difficulty performing such task because they have the capabilities of multiple domains. Specifically, MATS consists of three components: (i) a text categorization model that learns rich category-specific text representations using a bi-LSTM encoder; (ii) a syntax labeling model that learns to improve the syntax-aware LSTM decoder; and (iii) an abstractive text summarization model that shares its encoder and decoder with the text categorization and the syntax labeling tasks, respectively. In particular, the abstractive text summarization model enjoys significant benefit from the additional text categorization and syntax knowledge. Our experimental results show that MATS outperforms the competitors.1

Linqing Liu, Wei Yang, Jinfeng Rao, Raphael Tang, Jimmy Lin. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Jinfeng Rao, Linqing Liu, Yi Tay, Wei Yang, Peng Shi, Jimmy Lin. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

BACKGROUND: The biological network is highly dynamic. Functional relations between genes can be activated or deactivated depending on the biological conditions. On the genome-scale network, subnetworks that gain or lose local expression consistency may shed light on the regulatory mechanisms related to the changing biological conditions, such as disease status or tissue developmental stages. RESULTS: In this study, we develop a new method to select genes and modules on the existing biological network, in which local expression consistency changes significantly between clinical conditions. The method is called DNLC: Differential Network Local Consistency. In simulations, our algorithm detected artificially created local consistency changes effectively. We applied the method on two publicly available datasets, and the method detected novel genes and network modules that were biologically plausible. CONCLUSIONS: The new method is effective in finding modules in which the gene expression consistency change between clinical conditions. It is a useful tool that complements traditional differential expression analyses to make discoveries from gene expression data. The R package is available at https://cran.r-project.org/web/packages/DNLC.

In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an agent of reinforcement learning, which takes the raw text as input and predicts the abstractive summarization. We also build a discriminator which attempts to distinguish the generated summary from the ground truth summary. Extensive experiments demonstrate that our model achieves competitive ROUGE scores with the state-of-the-art methods on CNN/Daily Mail dataset. Qualitatively, we show that our model is able to generate more abstractive, readable and diverse summaries.

This paper describes a concept to support scalable multicast communications for small audio/video conferencing groups on the Internet. The solution presented in this paper is based on extensions of IPv6 and the session description protocol (SDP). A goal of the concept called multicast for small conferences (MSC) is the smooth deployment in the Internet.