Humans understand language based on the rich background knowledge about how the physical world works, which in turn allows us to reason about the physical world through language. In addition to the properties of objects (e.g., boats require fuel) and their affordances, i.e., the actions that are applicable to them (e.g., boats can be driven), we can also reason about if-then inferences between what properties of objects imply the kind of actions that are applicable to them (e.g., that if we can drive something then it likely requires fuel).
In this paper, we investigate the extent to which state-of-the-art neural language representations, trained on a vast amount of natural language text, demonstrate physical commonsense reasoning. While recent advancements of neural language models have demonstrated strong performance on various types of natural language inference tasks, our study based on a dataset of over 200k newly collected annotations suggests that neural language representations still only learn associations that are explicitly written down.
We consider the task of incorporating real-world commonsense knowledge into deep Natural Language Inference (NLI) models. Existing external knowledge incorporation methods are limited to lexical level knowledge and lack generalization across NLI models, datasets, and commonsense knowledge sources. To address these issues, we propose a novel NLI model-independent neural framework, BiCAM. BiCAM incorporates real-world commonsense knowledge into NLI models. Combined with convolutional feature detectors and bilinear feature fusion, BiCAM provides a conceptually simple mechanism that generalizes we…
University of Sheffield（谢菲尔德大学）；University of Durham（杜伦大学）
Neural language representation models such as BERT, pre-trained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasoning and inference. Natural Language Inference (NLI) is a challenging reasoning task that relies on common human understanding of language and real-world commonsense knowledge. We introduce a new model for NLI called External Knowledge Enhanced BERT (ExBERT), to enrich the contextual representation with real-world commonsense knowledge from external knowledge sources and enhance B…
The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Korea Advanced Institute of Science and Technology（韩国科学技术院）
Many contextualized word representations are now learned by intricate neural network models, such as masked neural language models (MNLMs) which are made up of huge neural network structures and trained to restore the masked text. Such representations demonstrate superhuman performance in some reading comprehension (RC) tasks which extract a proper answer in the context given a question. However, identifying the detailed knowledge trained in MNLMs is challenging owing to numerous and intermingled model parameters. This paper provides new insights and empirical analyses on commonsense knowledge…
Explaining the outcome of deep learning decisions based on affect is challenging but necessary if we expect social companion robots to interact with users on an emotional level. In this paper, we present a commonsense approach that utilizes an interpretable hybrid neural-symbolic system to associate extracted targets, noun chunks determined to be associated with the expressed emotion, with affective labels from a natural language expression. We leverage a pre-trained neural network that is well adapted to tree and sub-tree processing, the Dependency Tree-LSTM, to learn the affect labels of dyn…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Washington（华盛顿大学）
The common practice for training commonsense models has gone from-human-to-corpus-to-machine: humans author commonsense knowledge graphs in order to train commonsense models. In this work, we investigate an alternative, from-machine-to-corpus-to-machine: general language models author these commonsense knowledge graphs to train commonsense models. Our study leads to a new framework, Symbolic Knowledge Distillation. As with prior art in Knowledge Distillation (Hinton et al., 2015), our approach uses larger models to teach smaller models. A key difference is that we distill knowledge symbolicall…
Allen Institute for AI（艾伦人工智能研究所）；Paul G. Allen School of Computer Science & Engineering（保罗·G·艾伦计算机科学与工程学院）；Stanford University（斯坦福大学）
Recent years have brought about a renewed interest in commonsense representation and reasoning in the field of natural language understanding. The development of new commonsense knowledge graphs (CSKG) has been central to these advances as their diverse facts can be used and referenced by machine learning models for tackling new and challenging tasks. At the same time, there remain questions about the quality and coverage of these resources due to the massive scale required to comprehensively encompass general commonsense knowledge. In this work, we posit that manually constructed CSKGs will n…
The University of Queensland（昆士兰大学）；Monash University（莫纳什大学）；The University of New South Wales（新南威尔士大学）
Commonsense reasoning aims to incorporate sets of commonsense facts, retrieved from Commonsense Knowledge Graphs (CKG), to draw conclusion about ordinary situations. The dynamic nature of commonsense knowledge postulates models capable of performing multi-hop reasoning over new situations. This feature also results in having large-scale sparse Knowledge Graphs, where such reasoning process is needed to predict relations between new events. However, existing approaches in this area are limited by considering CKGs as a limited set of facts, thus rendering them unfit for reasoning over new unseen…
In recent years, vision-language models (VLMs) have shown remarkable performance on visual reasoning tasks (e.g. attributes, location). While such tasks measure the requisite knowledge to ground and reason over a given visual instance, they do not, however, measure the ability of VLMs to retain and generalize such knowledge. In this work, we evaluate their ability to acquire "visible" physical knowledge -- the information that is easily accessible from images of static scenes, particularly across the dimensions of object color, size and space. We build an automatic pipeline to derive a compreh…
School of Informatics（信息学院）；University of Edinburgh（爱丁堡大学）
Large Language Models (LLMs) handle physical commonsense information inadequately. As a result of being trained in a disembodied setting, LLMs often fail to predict an action's outcome in a given environment. However, predicting the effects of an action before it is executed is crucial in planning, where coherent sequences of actions are often needed to achieve a goal. Therefore, we introduce the multi-modal task of predicting the outcomes of actions solely from realistic sensory inputs (images and text). Next, we extend an LLM to model latent representations of objects to better predict actio…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Columbia University（哥伦比亚大学）；University of Pennsylvania（宾夕法尼亚大学）
Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such type of safety that has been scarcely studied is commonsense physical safety, i.e. text that is not explicitly violent and requires additional commonsense knowledge to comprehend that it leads to physical harm. We create the first benchmark dataset, SafeText, comprising real-life scenarios with paired safe and physically unsafe pieces of advice. We utilize SafeText to empirically study commonsense physical safety across…
PIQA: Reasoning about Physical Commonsense in Natural Language
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Microsoft Research AI（微软研究院AI）；Carnegie Mellon University（卡内基梅隆大学）；Paul G. Allen School for Computer Science and Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
Carnegie Mellon University（卡内基梅隆大学）；University of California, Berkeley（加州大学伯克利分校）
In order for AI to be safely deployed in real-world scenarios such as hospitals, schools, and the workplace, it must be able to robustly reason about the physical world. Fundamental to this reasoning is physical common sense: understanding the physical properties and affordances of available objects, how they can be manipulated, and how they interact with other objects. Physical commonsense reasoning is fundamentally a multi-sensory task, since physical properties are manifested through multiple modalities - two of them being vision and acoustics. Our paper takes a step towards real-world phys…
Commonsense question answering (CQA) aims to test if models can answer questions regarding commonsense knowledge that everyone knows. Prior works that incorporate external knowledge bases have shown promising results, but knowledge bases are expensive to construct and are often limited to a fixed set of relations. In this paper, we instead focus on better utilizing the \textit{implicit knowledge} stored in pre-trained language models. While researchers have found that the knowledge embedded in pre-trained language models can be extracted by having them fill in the blanks of carefully designed …
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）
Neural predictive models have achieved remarkable performance improvements in various natural language processing tasks. However, most neural predictive models suffer from the lack of explainability of predictions, limiting their practical utility. This paper proposes a neural predictive approach to make a prediction and generate its corresponding explanation simultaneously. It leverages the knowledge entailed in explanations as an additional distillation signal for more efficient learning. We conduct a preliminary study on Chinese medical multiple-choice question answering, English natural la…
Enthymemes are defined as arguments where a premise or conclusion is left implicit. We tackle the task of generating the implicit premise in an enthymeme, which requires not only an understanding of the stated conclusion and premise but also additional inferences that could depend on commonsense knowledge. The largest available dataset for enthymemes (Habernal et al., 2018) consists of 1.7k samples, which is not large enough to train a neural text generation model. To address this issue, we take advantage of a similar task and dataset: Abductive reasoning in narrative text (Bhagavatula et al.,…
Facebook（脸书）；EPFL（洛桑联邦理工学院）；University of Washington（华盛顿大学）；Carnegie Mellon University（卡内基梅隆大学）
One of the challenges faced by conversational agents is their inability to identify unstated presumptions of their users' commands, a task trivial for humans due to their common sense. In this paper, we propose a zero-shot commonsense reasoning system for conversational agents in an attempt to achieve this. Our reasoner uncovers unstated presumptions from user commands satisfying a general template of if-(state), then-(action), because-(goal). Our reasoner uses a state-of-the-art transformer-based generative commonsense knowledge base (KB) as its source of background knowledge for reasoning. W…
HFL-RC System at SemEval-2018 Task 11: Hybrid Multi-Aspects Model for Commonsense Reading Comprehension
Joint Laboratory of HIT and iFLYTEK (HFL), iFLYTEK Research（哈尔滨工业大学与科大讯飞联合实验室（HFL）、科大讯飞研究院）；Research Center for Social Computing and Information Retrieval (SCIR),Harbin Institute of Technology（哈尔滨工业大学社会计算与信息检索研究中心（SCIR））；Harbin Institute of Technology（哈尔滨工业大学）；iFLYTEK Research（科大讯飞研究院）
Mila / McGill University（米拉实验室/麦吉尔大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of CSE, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Stanford University（斯坦福大学）
Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the generated text is repetitive, generic, self-contradictory, and often lacks commonsense. Our analyses on sentence-level attention patterns in LMs reveal that neural degeneration may be associated with insufficient learning of task-specific characteristics by the attention mechanism. This finding motivates on-the-fly attention modulation -- a simple but effective method that enables the injection of priors into attention computation during inference. Automatic and…
Posts and Telecommunications Institute of Technology（邮电技术学院）
An ultimate goal of artificial intelligence is to build computer systems that can understand human languages. Understanding commonsense knowledge about the world expressed in text is one of the foundational and challenging problems to create such intelligent systems. As a step towards this goal, we present in this paper ALMEn, an Autoencoding Language Model based Ensemble learning method for commonsense validation and explanation. By ensembling several advanced pre-trained language models including RoBERTa, DeBERTa, and ELECTRA with Siamese neural networks, our method can distinguish natural l…
Recent years have seen significant advancement in text generation tasks with the help of neural language models. However, there exists a challenging task: generating math problem text based on mathematical equations, which has made little progress so far. In this paper, we present a novel equation-to-problem text generation model. In our model, 1) we propose a flexible scheme to effectively encode math equations, we then enhance the equation encoder by a Varitional Autoen-coder (VAE) 2) given a math equation, we perform topic selection, followed by which a dynamic topic memory mechanism is int…
Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）
Commonsense knowledge-graphs (CKGs) are important resources towards building machines that can 'reason' on text or environmental inputs and make inferences beyond perception. While current CKGs encode world knowledge for a large number of concepts and have been effectively utilized for incorporating commonsense in neural models, they primarily encode declarative or single-condition inferential knowledge and assume all conceptual beliefs to have the same likelihood. Further, these CKGs utilize a limited set of relations shared across concepts and lack a coherent knowledge organization structure…
Bosch Research（博世研究院）；Carnegie Mellon University（卡内基梅隆大学）；Information Sciences Institute, Viterbi School of Engineering, University of Southern California（南加州大学维特比工程学院信息科学研究所）；Michigan State University（密歇根州立大学）
This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are discussed. The situations in which this combination is most appropriate are characterized, including quantitative evaluation and qualitative error analysis on a variety of commonsense question answering benchmark datasets.
University of Southern California（南加州大学）；Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；University of California, San Diego（加州大学圣地亚哥分校）
Humans use natural language to compose common concepts from their environment into plausible, day-to-day scene descriptions. However, such generative commonsense reasoning (GCSR) skills are lacking in state-of-the-art text generation methods. Descriptive sentences about arbitrary concepts generated by neural text generation models (e.g., pre-trained text-to-text Transformers) are often grammatically fluent but may not correspond to human common sense, largely due to their lack of mechanisms to capture concept relations, to identify implicit concepts, and to perform generalizable reasoning abou…
Recent works show that pre-trained language models (PTLMs), such as BERT, possess certain commonsense and factual knowledge. They suggest that it is promising to use PTLMs as "neural knowledge bases" via predicting masked words. Surprisingly, we find that this may not work for numerical commonsense knowledge (e.g., a bird usually has two legs). In this paper, we investigate whether and to what extent we can induce numerical commonsense knowledge from PTLMs as well as the robustness of this process. To study this, we introduce a novel probing task with a diagnostic dataset, NumerSense, containi…
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Information, Renmin University of China（中国人民大学信息学院）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）
Commonsense reasoning in natural language is a desired ability of artificial intelligent systems. For solving complex commonsense reasoning tasks, a typical solution is to enhance pre-trained language models~(PTMs) with a knowledge-aware graph neural network~(GNN) encoder that models a commonsense knowledge graph~(CSKG). Despite the effectiveness, these approaches are built on heavy architectures, and can't clearly explain how external knowledge resources improve the reasoning capacity of PTMs. Considering this issue, we conduct a deep empirical analysis, and find that it is indeed relation fe…
Most benchmark datasets targeting commonsense reasoning focus on everyday scenarios: physical knowledge like knowing that you could fill a cup under a waterfall [Talmor et al., 2019], social knowledge like bumping into someone is awkward [Sap et al., 2019], and other generic situations. However, there is a rich space of commonsense inferences anchored to knowledge about specific entities: for example, deciding the truthfulness of a claim "Harry Potter can teach classes on how to fly on a broomstick." Can models learn to combine entity knowledge with commonsense reasoning in this fashion? We in…
Research Center for Social Computing and Information Retrieval（社会计算与信息检索研究中心）；Harbin Institute of Technology（哈尔滨工业大学）
Existing KG-augmented models for commonsense question answering primarily focus on designing elaborate Graph Neural Networks (GNNs) to model knowledge graphs (KGs). However, they ignore (i) the effectively fusing and reasoning over question context representations and the KG representations, and (ii) automatically selecting relevant nodes from the noisy KGs during reasoning. In this paper, we propose a novel model, JointLK, which solves the above limitations through the joint reasoning of LM and GNN and the dynamic KGs pruning mechanism. Specifically, JointLK performs joint reasoning between L…
Carnegie Mellon University（卡内基梅隆大学）；University of Southern California（南加州大学）；Bosch Research（博世研究中心）
Recent developments in pre-trained neural language modeling have led to leaps in accuracy on commonsense question-answering benchmarks. However, there is increasing concern that models overfit to specific tasks, without learning to utilize external knowledge or perform general semantic reasoning. In contrast, zero-shot evaluations have shown promise as a more robust measure of a model's general reasoning abilities. In this paper, we propose a novel neuro-symbolic framework for zero-shot question answering across commonsense tasks. Guided by a set of hypotheses, the framework studies how to tra…
Tsinghua University（清华大学）；University of Southern California（南加州大学）；Carnegie Mellon University（卡内基梅隆大学）；Bosch Research Pittsburgh（博世匹兹堡研究院）
Self-supervision based on the information extracted from large knowledge graphs has been shown to improve the generalization of language models, in zero-shot evaluation on various downstream language reasoning tasks. Since these improvements are reported in aggregate, however, little is known about (i) how to select the appropriate knowledge for solid performance across tasks, (ii) how to combine this knowledge with neural language models, and (iii) how these pairings affect granular task performance. In this paper, we study the effect of knowledge sampling strategies and sizes that can be use…
Verb Physics: Relative Physical Knowledge of Actions and Objects
University of Washington（华盛顿大学）
从自然语言文本中学习常识知识是不平凡的，因为报告偏见：人们很少陈述显而易见的东西，例如，“我的房子比我大。然而，虽然很少明确指出，但这些琐碎的日常知识确实影响了人们谈论世界的方式，这为人们对世界的理性提供了间接线索。例如，“Tyler entered his house”（泰勒进入了他的房子）这句话暗示着他的房子比泰勒大。在本文中，我们提出了一种方法来推断相对物理知识的行动和对象沿五个维度（例如，大小、重量和强度）。我们将知识获取框架为两个密切相关问题的联合推理：学习（1）对象对的相对物理知识和（2）应用于这些对象对时动作的物理含义。实验结果表明，它是可能的，从语言中提取知识的动作和对象，联合推理不同类型的知识提高性能。
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech -- in an entirely label-free, self-supervised manner. By pretraining with a mix of both frame-level (spatial) and video-level (temporal) objectives, our model not only learns to match images to temporally corresponding words, but also to contextualize what is happening globally over time. As a result,…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Edinburgh（爱丁堡大学）
As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce MERLOT Reserve, a model that represents videos jointly over time -- through a new training objective that learns from audio, subtitles, and video frames. Given a video, we replace snippets of text and audio with a MASK token; the model learns by choosing the correct masked-out snippet. Our objective learns faster than alternatives, and performs well at scale: we pretrain on 20 million YouTube videos. Empirical results show that MERLOT Reserve learns strong multimodal representations. …
NCSOFT（NCSOFT公司）；Seoul National University（首尔国立大学）
Coherence is one of the critical factors that determine the quality of writing. We propose writing relevance (WR) training method for neural encoder-decoder natural language generation (NLG) models which improves coherence of the continuation by leveraging negative examples. WR loss regresses the vector representation of the context and generated sentence toward positive continuation by contrasting it with the negatives. We compare our approach with Unlikelihood (UL) training in a text continuation task on commonsense natural language inference (NLI) corpora to show which method better models …
Transformer-based language models have recently achieved remarkable results in many natural language tasks. However, performance on leaderboards is generally achieved by leveraging massive amounts of training data, and rarely by encoding explicit linguistic knowledge into neural models. This has led many to question the relevance of linguistics for modern natural language processing. In this dissertation, I present several case studies to illustrate how theoretical linguistics and neural language models are still relevant to each other. First, language models are useful to linguists by providi…
