scholarly journals QASC: A Dataset for Question Answering via Sentence Composition

2020 ◽  
Vol 34 (05) ◽  
pp. 8082-8090
Author(s):  
Tushar Khot ◽  
Peter Clark ◽  
Michal Guerquin ◽  
Peter Jansen ◽  
Ashish Sabharwal
Keyword(s):  
Common Sense ◽  
Human Performance ◽  
Question Answering ◽  
State Of The Art ◽  
Multiple Choice ◽  
Training Data ◽  
Language Models ◽  
Current State ◽  
New Concepts ◽  
Large Corpus

Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus and composing them to answer a multiple-choice question. QASC is the first dataset to offer two desirable properties: (a) the facts to be composed are annotated in a large corpus, and (b) the decomposition into these facts is not evident from the question itself. The latter makes retrieval challenging as the system must introduce new concepts or relations in order to discover potential decompositions. Further, the reasoning model must then learn to identify valid compositions of these retrieved facts using common-sense reasoning. To help address these challenges, we provide annotation for supporting facts as well as their composition. Guided by these annotations, we present a two-step approach to mitigate the retrieval challenges. We use other multiple-choice datasets as additional training data to strengthen the reasoning model. Our proposed approach improves over current state-of-the-art language models by 11% (absolute). The reasoning and retrieval problems, however, remain unsolved as this model still lags by 20% behind human performance.

scholarly journals Attending to Entities for Better Text Understanding

2020 ◽  
Vol 34 (05) ◽  
pp. 7554-7561
Author(s):  
Pengxiang Cheng ◽  
Katrin Erk
Keyword(s):  
Large Scale ◽  
Human Performance ◽  
State Of The Art ◽  
Syntactic Structure ◽  
Semantic Knowledge ◽  
Training Data ◽  
Language Models ◽  
Long Distance ◽  
Future Directions ◽  
Text Understanding

Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BERT, XLNet, etc.) based on Transformer (Vaswani et al. 2017), and in a range of end tasks, such models have achieved state-of-the-art results, approaching human performance. This clearly demonstrates the power of the stacked self-attention architecture when paired with a sufficient number of layers and a large amount of pre-training data. However, on tasks that require complex and long-distance reasoning where surface-level cues are not enough, there is still a large gap between the pre-trained models and human performance. Strubell et al. (2018) recently showed that it is possible to inject knowledge of syntactic structure into a model through supervised self-attention. We conjecture that a similar injection of semantic knowledge, in particular, coreference information, into an existing model would improve performance on such complex problems. On the LAMBADA (Paperno et al. 2016) task, we show that a model trained from scratch with coreference as auxiliary supervision for self-attention outperforms the largest GPT-2 model, setting the new state-of-the-art, while only containing a tiny fraction of parameters compared to GPT-2. We also conduct a thorough analysis of different variants of model architectures and supervision configurations, suggesting future directions on applying similar techniques to other problems.

scholarly journals Relevance-guided Supervision for OpenQA with ColBERT

2021 ◽  
Vol 9 ◽  
pp. 929-944
Author(s):  
Omar Khattab ◽  
Christopher Potts ◽  
Matei Zaharia
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Training Data ◽  
Coarse Grained ◽  
Retrieval Model ◽  
Open Domain ◽  
Weak Supervision ◽  
Fine Grained ◽  
Vector Representations ◽  
Large Corpus

Abstract Systems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for finding candidate passages in a large corpus and a reader for extracting answers from those passages. In much recent work, the retriever is a learned component that uses coarse-grained vector representations of questions and passages. We argue that this modeling choice is insufficiently expressive for dealing with the complexity of natural language questions. To address this, we define ColBERT-QA, which adapts the scalable neural retrieval model ColBERT to OpenQA. ColBERT creates fine-grained interactions between questions and passages. We propose an efficient weak supervision strategy that iteratively uses ColBERT to create its own training data. This greatly improves OpenQA retrieval on Natural Questions, SQuAD, and TriviaQA, and the resulting system attains state-of-the-art extractive OpenQA performance on all three datasets.

scholarly journals Multiple-Choice Question Answering Models for Automatic Depression Severity Estimation

2021 ◽  
Vol 7 (1) ◽  
pp. 23
Author(s):  
Jorge Gabín ◽  
Anxo Pérez ◽  
Javier Parapar
Keyword(s):  
Social Media ◽  
Question Answering ◽  
Multiple Choice ◽  
Multiple Choice Question ◽  
Self Report ◽  
Training Data ◽  
Language Models ◽  
Depression Severity ◽  
Suitable Alternative ◽  
Severity Estimation

Depression is one of the most prevalent mental health diseases. Although there are effective treatments, the main problem relies on providing early and effective risk detection. Medical experts use self-reporting questionnaires to elaborate their diagnosis, but these questionnaires have some limitations. Social stigmas and the lack of awareness often negatively affect the success of these self-report questionnaires. This article aims to describe techniques to automatically estimate the depression severity from users on social media. We explored the use of pre-trained language models over the subject’s writings. We addressed the task “Measuring the Severity of the Signs of Depression” of eRisk 2020, an initiative in the CLEF Conference. In this task, participants have to fill the Beck Depression Questionnaire (BDI-II). Our proposal explores the application of pre-trained Multiple-Choice Question Answering (MCQA) models to predict user’s answers to the BDI-II questionnaire using their posts on social media. These MCQA models are built over the BERT (Bidirectional Encoder Representations from Transformers) architecture. Our results showed that multiple-choice question answering models could be a suitable alternative for estimating the depression degree, even when small amounts of training data are available (20 users).

scholarly journals WinoGrande: An Adversarial Winograd Schema Challenge at Scale

2020 ◽  
Vol 34 (05) ◽  
pp. 8732-8740 ◽  
Author(s):  
Keisuke Sakaguchi ◽  
Ronan Le Bras ◽  
Chandra Bhagavatula ◽  
Yejin Choi
Keyword(s):  
Large Scale ◽  
Human Performance ◽  
State Of The Art ◽  
Bias Reduction ◽  
Training Data ◽  
Language Models ◽  
Systematic Bias ◽  
Commonsense Reasoning ◽  
Word Associations ◽  
Key Steps

The Winograd Schema Challenge (WSC) (Levesque, Davis, and Morgenstern 2011), a benchmark for commonsense reasoning, is a set of 273 expert-crafted pronoun resolution problems originally designed to be unsolvable for statistical models that rely on selectional preferences or word associations. However, recent advances in neural language models have already reached around 90% accuracy on variants of WSC. This raises an important question whether these models have truly acquired robust commonsense capabilities or whether they rely on spurious biases in the datasets that lead to an overestimation of the true capabilities of machine commonsense.To investigate this question, we introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original WSC design, but adjusted to improve both the scale and the hardness of the dataset. The key steps of the dataset construction consist of (1) a carefully designed crowdsourcing procedure, followed by (2) systematic bias reduction using a novel AfLite algorithm that generalizes human-detectable word associations to machine-detectable embedding associations. The best state-of-the-art methods on WinoGrande achieve 59.4 – 79.1%, which are ∼15-35% (absolute) below human performance of 94.0%, depending on the amount of the training data allowed (2% – 100% respectively).Furthermore, we establish new state-of-the-art results on five related benchmarks — WSC (→ 90.1%), DPR (→ 93.1%), COPA(→ 90.6%), KnowRef (→ 85.6%), and Winogender (→ 97.1%). These results have dual implications: on one hand, they demonstrate the effectiveness of WinoGrande when used as a resource for transfer learning. On the other hand, they raise a concern that we are likely to be overestimating the true capabilities of machine commonsense across all these benchmarks. We emphasize the importance of algorithmic bias reduction in existing and future benchmarks to mitigate such overestimation.

scholarly journals Transcription Alignment of Historical Vietnamese Manuscripts without Human-Annotated Learning Samples

2021 ◽  
Vol 11 (11) ◽  
pp. 4894
Author(s):  
Anna Scius-Bertrand ◽  
Michael Jungo ◽  
Beat Wolf ◽  
Andreas Fischer ◽  
Marc Bui
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Positive Impact ◽  
Detection System ◽  
Training Data ◽  
Detection Accuracy ◽  
Current State ◽  
Alignment Task ◽  
Scanned Image ◽  
Automatic Transcription

The current state of the art for automatic transcription of historical manuscripts is typically limited by the requirement of human-annotated learning samples, which are are necessary to train specific machine learning models for specific languages and scripts. Transcription alignment is a simpler task that aims to find a correspondence between text in the scanned image and its existing Unicode counterpart, a correspondence which can then be used as training data. The alignment task can be approached with heuristic methods dedicated to certain types of manuscripts, or with weakly trained systems reducing the required amount of annotations. In this article, we propose a novel learning-based alignment method based on fully convolutional object detection that does not require any human annotation at all. Instead, the object detection system is initially trained on synthetic printed pages using a font and then adapted to the real manuscripts by means of self-training. On a dataset of historical Vietnamese handwriting, we demonstrate the feasibility of annotation-free alignment as well as the positive impact of self-training on the character detection accuracy, reaching a detection accuracy of 96.4% with a YOLOv5m model without using any human annotation.

scholarly journals Analyzing the Effect of Masking Length Distribution of MLM: An Evaluation Framework and Case Study on Chinese MRC Datasets

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Changchang Zeng ◽  
Shaobo Li
Keyword(s):  
Reading Comprehension ◽  
Language Processing ◽  
Question Answering ◽  
Multiple Choice ◽  
Length Distribution ◽  
Research Field ◽  
Evaluation Framework ◽  
Language Models ◽  
Training Objective ◽  
Machine Reading

Machine reading comprehension (MRC) is a challenging natural language processing (NLP) task. It has a wide application potential in the fields of question answering robots, human-computer interactions in mobile virtual reality systems, etc. Recently, the emergence of pretrained models (PTMs) has brought this research field into a new era, in which the training objective plays a key role. The masked language model (MLM) is a self-supervised training objective widely used in various PTMs. With the development of training objectives, many variants of MLM have been proposed, such as whole word masking, entity masking, phrase masking, and span masking. In different MLMs, the length of the masked tokens is different. Similarly, in different machine reading comprehension tasks, the length of the answer is also different, and the answer is often a word, phrase, or sentence. Thus, in MRC tasks with different answer lengths, whether the length of MLM is related to performance is a question worth studying. If this hypothesis is true, it can guide us on how to pretrain the MLM with a relatively suitable mask length distribution for MRC tasks. In this paper, we try to uncover how much of MLM’s success in the machine reading comprehension tasks comes from the correlation between masking length distribution and answer length in the MRC dataset. In order to address this issue, herein, (1) we propose four MRC tasks with different answer length distributions, namely, the short span extraction task, long span extraction task, short multiple-choice cloze task, and long multiple-choice cloze task; (2) four Chinese MRC datasets are created for these tasks; (3) we also have pretrained four masked language models according to the answer length distributions of these datasets; and (4) ablation experiments are conducted on the datasets to verify our hypothesis. The experimental results demonstrate that our hypothesis is true. On four different machine reading comprehension datasets, the performance of the model with correlation length distribution surpasses the model without correlation.

scholarly journals MSA Transformer

2021 ◽  
Author(s):  
Roshan Rao ◽  
Jason Liu ◽  
Robert Verkuil ◽  
Joshua Meier ◽  
John F. Canny ◽  
...  
Keyword(s):  
Structure Learning ◽  
State Of The Art ◽  
Language Model ◽  
Language Modeling ◽  
Language Models ◽  
Multiple Sequence ◽  
Wide Margin ◽  
Current State ◽  
Individual Sequences ◽  
And Function

AbstractUnsupervised protein language models trained across millions of diverse sequences learn structure and function of proteins. Protein language models studied to date have been trained to perform inference from individual sequences. The longstanding approach in computational biology has been to make inferences from a family of evolutionarily related sequences by fitting a model to each family independently. In this work we combine the two paradigms. We introduce a protein language model which takes as input a set of sequences in the form of a multiple sequence alignment. The model interleaves row and column attention across the input sequences and is trained with a variant of the masked language modeling objective across many protein families. The performance of the model surpasses current state-of-the-art unsupervised structure learning methods by a wide margin, with far greater parameter efficiency than prior state-of-the-art protein language models.

scholarly journals Context-aware Frame-Semantic Role Labeling

2015 ◽  
Vol 3 ◽  
pp. 449-460 ◽  
Author(s):  
Michael Roth ◽  
Mirella Lapata
Keyword(s):  
Social Network ◽  
Question Answering ◽  
State Of The Art ◽  
Semantic Role ◽  
Context Aware ◽  
Semantic Role Labeling ◽  
Current State ◽  
Sentence Level ◽  
Small Set ◽  
Labeling System

Frame semantic representations have been useful in several applications ranging from text-to-scene generation, to question answering and social network analysis. Predicting such representations from raw text is, however, a challenging task and corresponding models are typically only trained on a small set of sentence-level annotations. In this paper, we present a semantic role labeling system that takes into account sentence and discourse context. We introduce several new features which we motivate based on linguistic insights and experimentally demonstrate that they lead to significant improvements over the current state-of-the-art in FrameNet-based semantic role labeling.

Clairvoyance vs. Common Sense: Therapist’s Duty to Warn and Protect

1986 ◽  
Vol 1 (1) ◽  
pp. 7-22 ◽  
Author(s):  
Daniel J. Sonkin
Keyword(s):  
Domestic Violence ◽  
Common Sense ◽  
State Of The Art ◽  
Clinical Interventions ◽  
Duty To Warn ◽  
Current State ◽  
Violent Acts ◽  
Victims Of Violence

This article addresses the issue of a therapist’s duty to warn and protect victims of domestic violence. In three different cases, California courts have found therapists liable for violent acts perpetrated by clients in their care. Based on the landmark Tarasoff case that mandated the therapist to report threats made by their clients regarding a specific victim, the courts have now extended the therapist’s duty to include the reporting of those clients they assess as dangerous but who have not made specific threats, as well as the protection of unintended victims of violence, such as children. Therapists are concerned that the courts are expecting them to be clairvoyant and that psychologists may not be able to predict dangerousness. This article will discuss these concerns in light of the current state of the art regarding the prediction of dangerousness and its relationship to domestic violence. The author suggests specific clinical interventions for victims and perpetrators of domestic violence.

Sign in / Sign up

Export Citation Format

Share Document