scholarly journals PIQA: Reasoning about Physical Commonsense in Natural Language

2020 ◽  
Vol 34 (05) ◽  
pp. 7432-7439
Author(s):  
Yonatan Bisk ◽  
Rowan Zellers ◽  
Ronan Le bras ◽  
Jianfeng Gao ◽  
Yejin Choi
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Natural Language Understanding ◽  
Physical World ◽  
Future Research ◽  
Physical Interaction ◽  
Commonsense Reasoning ◽  
Cotton Swab ◽  
Language Understanding ◽  
Abstract Domains

To apply eyeshadow without a brush, should I use a cotton swab or a toothpick? Questions requiring this kind of physical commonsense pose a challenge to today's natural language understanding systems. While recent pretrained models (such as BERT) have made progress on question answering over more abstract domains – such as news articles and encyclopedia entries, where text is plentiful – in more physical domains, text is inherently limited due to reporting bias. Can AI systems learn to reliably answer physical commonsense questions without experiencing the physical world?In this paper, we introduce the task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA. Though humans find the dataset easy (95% accuracy), large pretrained models struggle (∼75%). We provide analysis about the dimensions of knowledge that existing models lack, which offers significant opportunities for future research.

scholarly journals A Lexical Knowledge Representation Model for Natural Language Understanding

2009 ◽  
Vol 1 (4) ◽  
pp. 17-35 ◽  
Author(s):  
Ping Chen ◽  
Wei Ding ◽  
Chengmin Ding
Keyword(s):  
Knowledge Representation ◽  
Natural Language ◽  
Language Processing ◽  
Large Scale ◽  
Natural Language Understanding ◽  
Commonsense Reasoning ◽  
Lexical Knowledge ◽  
Language Understanding ◽  
Representation Model ◽  
Intelligent Information

Knowledge representation is essential for semantics modeling and intelligent information processing. For decades researchers have proposed many knowledge representation techniques. However, it is a daunting problem how to capture deep semantic information effectively and support the construction of a large-scale knowledge base efficiently. This article describes a new knowledge representation model, SenseNet, which provides semantic support for commonsense reasoning and natural language processing. SenseNet is formalized with a Hidden Markov Model. An inference algorithm is proposed to simulate human-like natural language understanding procedure. A new measurement, confidence, is introduced to facilitate the natural language understanding. The authors present a detailed case study of applying SenseNet to retrieving compensation information from company proxy filings.

scholarly journals A Lexical Knowledge Representation Model for Natural Language Understanding

2012 ◽  
pp. 193-210
Author(s):  
Ping Chen ◽  
Wei Ding ◽  
Chengmin Ding
Keyword(s):  
Knowledge Representation ◽  
Natural Language ◽  
Language Processing ◽  
Large Scale ◽  
Natural Language Understanding ◽  
Commonsense Reasoning ◽  
Language Understanding ◽  
Representation Model ◽  
Intelligent Information ◽  
Representation Techniques

Knowledge representation is essential for semantics modeling and intelligent information processing. For decades researchers have proposed many knowledge representation techniques. However, it is a daunting problem how to capture deep semantic information effectively and support the construction of a large-scale knowledge base efficiently. This paper describes a new knowledge representation model, SenseNet, which provides semantic support for commonsense reasoning and natural language processing. SenseNet is formalized with a Hidden Markov Model. An inference algorithm is proposed to simulate human-like natural language understanding procedure. A new measurement, confidence, is introduced to facilitate the natural language understanding. The authors present a detailed case study of applying SenseNet to retrieving compensation information from company proxy filings.

scholarly journals Ask me in your own words: paraphrasing for multitask question answering

2021 ◽  
Vol 7 ◽  
pp. e759
Author(s):  
G. Thomas Hudson ◽  
Noura Al Moubayed
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Question Answering ◽  
Natural Language Understanding ◽  
Multitask Learning ◽  
Single Model ◽  
Language Understanding ◽  
Class Labels ◽  
Paraphrase Generation

Multitask learning has led to significant advances in Natural Language Processing, including the decaNLP benchmark where question answering is used to frame 10 natural language understanding tasks in a single model. In this work we show how models trained to solve decaNLP fail with simple paraphrasing of the question. We contribute a crowd-sourced corpus of paraphrased questions (PQ-decaNLP), annotated with paraphrase phenomena. This enables analysis of how transformations such as swapping the class labels and changing the sentence modality lead to a large performance degradation. Training both MQAN and the newer T5 model using PQ-decaNLP improves their robustness and for some tasks improves the performance on the original questions, demonstrating the benefits of a model which is more robust to paraphrasing. Additionally, we explore how paraphrasing knowledge is transferred between tasks, with the aim of exploiting the multitask property to improve the robustness of the models. We explore the addition of paraphrase detection and paraphrase generation tasks, and find that while both models are able to learn these new tasks, knowledge about paraphrasing does not transfer to other decaNLP tasks.

scholarly journals Using Answer Set Programming for Commonsense Reasoning in the Winograd Schema Challenge

2019 ◽  
Vol 19 (5-6) ◽  
pp. 1021-1037
Author(s):  
ARPIT SHARMA
Keyword(s):  
Natural Language ◽  
Answer Set Programming ◽  
Natural Language Understanding ◽  
Turing Test ◽  
Subgraph Isomorphism ◽  
Commonsense Reasoning ◽  
Language Understanding ◽  
Commonsense Knowledge ◽  
Additional Constraints ◽  
Answer Set

AbstractThe Winograd Schema Challenge (WSC) is a natural language understanding task proposed as an alternative to the Turing test in 2011. In this work we attempt to solve WSC problems by reasoning with additional knowledge. By using an approach built on top of graph-subgraph isomorphism encoded using Answer Set Programming (ASP) we were able to handle 240 out of 291 WSC problems. The ASP encoding allows us to add additional constraints in an elaboration tolerant manner. In the process we present a graph based representation of WSC problems as well as relevant commonsense knowledge.

Recognizing textual entailment: Rational, evaluation and approaches

2009 ◽  
Vol 15 (4) ◽  
pp. i-xvii ◽  
Author(s):  
IDO DAGAN ◽  
BILL DOLAN ◽  
BERNARDO MAGNINI ◽  
DAN ROTH
Keyword(s):  
Natural Language ◽  
Question Answering ◽  
Natural Language Understanding ◽  
Language Understanding ◽  
Knowledge Representations ◽  
Semantic Relationships ◽  
Textual Entailment ◽  
Inference Methods ◽  
Recognizing Textual Entailment ◽  
Core Problem

AbstractThe goal of identifying textual entailment – whether one piece of text can be plausibly inferred from another – has emerged in recent years as a generic core problem in natural language understanding. Work in this area has been largely driven by the PASCAL Recognizing Textual Entailment (RTE) challenges, which are a series of annual competitive meetings. The current work exhibits strong ties to some earlier lines of research, particularly automatic acquisition of paraphrases and lexical semantic relationships and unsupervised inference in applications such as question answering, information extraction and summarization. It has also opened the way to newer lines of research on more involved inference methods, on knowledge representations needed to support this natural language understanding challenge and on the use of learning methods in this context. RTE has fostered an active and growing community of researchers focused on the problem of applied entailment. This special issue of the JNLE provides an opportunity to showcase some of the most important work in this emerging area.

Sign in / Sign up

Export Citation Format

Share Document