paper-with-me

홈 › Papers

Enhancing Review Comprehension with Domain-Specific Commonsense

2020-04-06 · Aaron Traylor, Chen Chen, Behzad Golshan, Xiaolan Wang, Yuliang Li, Yoshihiko Suhara, Jinfeng Li, Cagatay Demiralp, Wang-Chiew Tan

Review comprehension has played an increasingly important role in improving the quality of online services and products and commonsense knowledge can further enhance review comprehension. However, existing general-purpose commonsense knowledge bases lack sufficient coverage and precision to meaningfully improve the comprehension of domain-specific reviews. In this paper, we introduce xSense, an effective system for review comprehension using domain-specific commonsense knowledge bases (xSense KBs). We show that xSense KBs can be constructed inexpensively and present a knowledge distillation method that enables us to use xSense KBs along with BERT to boost the performance of various review comprehension tasks. We evaluate xSense over three review comprehension tasks: aspect extraction, aspect sentiment classification, and question answering. We find that xSense outperforms the state-of-the-art models for the first two tasks and improves the baseline BERT QA model significantly, demonstrating the usefulness of incorporating commonsense into review comprehension pipelines. To facilitate future research and applications, we publicly release three domain-specific knowledge bases and a domain-specific question answering benchmark along with this paper.

📄 PDF Abstract BibTeX arXiv:2004.03020

Code (0)

등록된 구현이 없습니다.

Tasks

Aspect ExtractionKnowledge DistillationQuestion AnsweringSentiment AnalysisSentiment Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

FAQ-Gen: An automated system to generate domain-specific FAQs to aid content comprehension

2024-02-08 · Sahil Kale, Gautam Khaire, Jay Patankar

Frequently Asked Questions (FAQs) refer to the most common inquiries about specific content. They serve as content comprehension aids by simplifying topics and enhancing understanding through succinct presentation of inf…

Question Answering

Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

2017-09-01 · EMNLP 2017 9 · Hongyu Lin, Le Sun, Xianpei Han

Reasoning with commonsense knowledge is critical for natural language understanding. Traditional methods for commonsense machine comprehension mostly only focus on one specific kind of knowledge, neglecting the fact that…

Natural Language UnderstandingReading Comprehensionvalid

Commonsense Knowledge + BERT for Level 2 Reading Comprehension Ability Test

2019-09-08 · Yidan Hu, Gongqi Lin, Yuan Miao, Chunyan Miao

Commonsense knowledge plays an important role when we read. The performance of BERT on SQuAD dataset shows that the accuracy of BERT can be better than human users. However, it does not mean that computers can surpass th…

ArticlesReading Comprehension

Commonsense Evidence Generation and Injection in Reading Comprehension

2020-05-11 · SIGDIAL (ACL) 2020 7 · Ye Liu, Tao Yang, Zeyu You, Wei Fan 외

Human tackle reading comprehension not only based on the given context itself but often rely on the commonsense beyond. To empower the machine with commonsense reasoning, in this paper, we propose a Commonsense Evidence …

Language ModelingLanguage ModellingReading Comprehension

CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension

2023-02-17 · Zhi Zhang, Helen Yannakoudakis, XianTong Zhen, Ekaterina Shutova

The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently received increasing attention within the research comminity. …

Referring ExpressionReferring Expression Comprehension