We present CovidQA, the beginnings of a question answering dataset specifically designed for COVID-19, built by hand from knowledge gathered from Kaggle's COVID-19 Open Research Dataset Challenge. To our knowledge, this is the first publicly available resource of its type, and intended as a stopgap measure for guiding research until more substantial evaluation resources become available. While this dataset, comprising 124 question-article pairs as of the present version 0.1 release, does not have sufficient examples for supervised machine learning, we believe that it can be helpful for evaluating the zero-shot or transfer capabilities of existing models on topics specifically related to COVID-19. This paper describes our methodology for constructing the dataset and presents the effectiveness of a number of baselines, including term-based techniques and various transformer-based models. The dataset is available at http://covidqa.ai/
We present the Neural Covidex, a search engine that exploits the latest neural ranking architectures to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI. This web application exists as part of a suite of tools that we have developed over the past few weeks to help domain experts tackle the ongoing global pandemic. We hope that improved information access capabilities to the scientific literature can inform evidence-based decision making and insight generation. This paper describes our initial efforts and offers a few thoughts about lessons we have learned along the way.
The semantics of a text is manifested not only by what is read, but also by what is not read. In this article, we will study how those implicit "not read" information such as end-of-paragraph (EOP) and end-of-sequence (EOS) affect the quality of text generation. Transformer-based pretrained language models (LMs) have demonstrated the ability to generate long continuations with good quality. This model gives us a platform for the first time to demonstrate that paragraph layouts and text endings are also important components of human writing. Specifically, we find that pretrained LMs can generate better continuations by learning to generate the end of the paragraph (EOP) in the fine-tuning stage. Experimental results on English story generation show that EOP can lead to higher BLEU score and lower EOS perplexity. To further investigate the relationship between text ending and EOP, we conduct experiments with a self-collected Chinese essay dataset on Chinese-GPT2, a character level LM without paragraph breaker or EOS during pre-training. Experimental results show that the Chinese GPT2 can generate better essay endings with paragraph information. Experiments on both English stories and Chinese essays demonstrate that learning to end paragraphs can benefit the continuation generation with pretrained LMs.
This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs). We leverage PLMs to address the strong token-to-token independence assumption made in the common objective, maximum likelihood estimation, for the CQR task. In CQR benchmarks of task-oriented dialogue systems, we evaluate fine-tuned PLMs on the recently-introduced CANARD dataset as an in-domain task and validate the models using data from the TREC 2019 CAsT Track as an out-domain task. Examining a variety of architectures with different numbers of parameters, we demonstrate that the recent text-to-text transfer transformer (T5) achieves the best results both on CANARD and CAsT with fewer parameters, compared to similar transformer architectures.
We applied the T5 sequence-to-sequence model to tackle the AI2 WinoGrande Challenge by decomposing each example into two input text strings, each containing a hypothesis, and using the probabilities assigned to the "entailment" token as a score of the hypothesis. Our first (and only) submission to the official leaderboard yielded 0.7673 AUC on March 13, 2020, which is the best known result at this time and beats the previous state of the art by over five points.
This work proposes a novel adaptation of a pretrained sequence-to-sequence model to the task of document ranking. Our approach is fundamentally different from a commonly-adopted classification-based formulation of ranking, based on encoder-only pretrained transformer architectures such as BERT. We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words", and how the underlying logits of these target words can be interpreted as relevance probabilities for ranking. On the popular MS MARCO passage ranking task, experimental results show that our approach is at least on par with previous classification-based models and can surpass them with larger, more-recent models. On the test collection from the TREC 2004 Robust Track, we demonstrate a zero-shot transfer-based approach that outperforms previous state-of-the-art models requiring in-dataset cross-validation. Furthermore, we find that our approach significantly outperforms an encoder-only model in a data-poor regime (i.e., with few training examples). We investigate this observation further by varying target words to probe the model's use of latent knowledge.
Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient. This problem can be formulated as a sequence labeling task, and we demonstrate the adaption of BERT to two types of business documents: regulatory filings and property lease agreements. There are aspects of this problem that make it easier than "standard" information extraction tasks and other aspects that make it more difficult, but on balance we find that modest amounts of annotated data (less than 100 documents) are sufficient to achieve reasonable accuracy. We integrate our models into an end-to-end cloud platform that provides both an easy-to-use annotation interface as well as an inference interface that allows users to upload documents and inspect model outputs.
Accurate streamflow prediction largely relies on historical records of both meteorological data and streamflow measurements. For many regions around the world, however, such data are only scarcely or not at all available. To select an appropriate model for a region with a given amount of historical data, it is therefore indispensable to know a model's sensitivity to limited training data, both in terms of geographic diversity and different spans of time. In this study, we provide decision support for tree- and LSTM-based models. We feed the models meteorological measurements from the CAMELS dataset, and individually restrict the training period length and the number of basins used in training. Our findings show that tree-based models provide more accurate predictions on small datasets, while LSTMs are superior given sufficient training data. This is perhaps not surprising, as neural networks are known to be data-hungry; however, we are able to characterize each model's strengths under different conditions, including the "breakeven point" when LSTMs begin to overtake tree-based models.
Public vulnerability databases such as CVE and NVD account for only 60% of security vulnerabilities present in open-source projects, and are known to suffer from inconsistent quality. Over the last two years, there has been considerable growth in the number of known vulnerabilities across projects available in various repositories such as NPM and Maven Central. Such an increasing risk calls for a mechanism to infer the presence of security threats in a timely manner. We propose novel hierarchical deep learning models for the identification of security-relevant commits from either the commit diff or the source code for the Java classes. By comparing the performance of our model against code2vec, a state-of-the-art model that learns from path-based representations of code, and a logistic regression baseline, we show that deep learning models show promising results in identifying security-related commits. We also conduct a comparative analysis of how various deep learning models learn across different input representations and the effect of regularization on the generalization of our models.
In this paper, we explore the knowledge distillation approach under the multi-task learning setting. We distill the BERT model refined by multi-task learning on seven datasets of the GLUE benchmark into a bidirectional LSTM with attention mechanism. Unlike other BERT distillation methods which specifically designed for Transformer-based architectures, we provide a general learning framework. Our approach is model agnostic and can be easily applied on different future teacher models. Compared to a strong, similarly BiLSTM-based approach, we achieve better quality under the same computational constraints. Compared to the present state of the art, we reach comparable results with much faster inference speed.