paper-with-me

홈 › Papers

Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems

2022-11-14 · Jialiang Xu, Mengyu Zhou, Xinyi He, Shi Han, Dongmei Zhang

Numerical Question Answering is the task of answering questions that require numerical capabilities. Previous works introduce general adversarial attacks to Numerical Question Answering, while not systematically exploring numerical capabilities specific to the topic. In this paper, we propose to conduct numerical capability diagnosis on a series of Numerical Question Answering systems and datasets. A series of numerical capabilities are highlighted, and corresponding dataset perturbations are designed. Empirical results indicate that existing systems are severely challenged by these perturbations. E.g., Graph2Tree experienced a 53.83% absolute accuracy drop against the `Extra'' perturbation on ASDiv-a, and BART experienced 13.80% accuracy drop against the `Language'' perturbation on the numerical subset of DROP. As a counteracting approach, we also investigate the effectiveness of applying perturbations as data augmentation to relieve systems' lack of robust numerical capabilities. With experiment analysis and empirical studies, it is demonstrated that Numerical Question Answering with robust numerical capabilities is still to a large extent an open question. We discuss future directions of Numerical Question Answering and summarize guidelines on future dataset collection and system design.

📄 PDF Abstract BibTeX arXiv:2211.07455

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationOpen-Ended Question AnsweringQuestion Answering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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 &…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question Answering

2022-07-01 · Findings (NAACL) 2022 7 · Jeonghwan Kim, Junmo Kang, Kyung-Min Kim, Giwon Hong 외

Numerical reasoning over text is a challenging subtask in question answering (QA) that requires both the understanding of texts and numbers. However, existing language models in these numerical reasoning QA models tend t…

HallucinationQuestion Answering

Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text

2021-09-06 · Findings (EMNLP) 2021 11 · Xiao-Yu Guo, Yuan-Fang Li, Gholamreza Haffari

Numerical reasoning skills are essential for complex question answering (CQA) over text. It requires opertaions including counting, comparison, addition and subtraction. A successful approach to CQA on text, Neural Modul…

Question Answering

Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks

2020-05-18 · Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva 외

Numerical reasoning is often important to accurately understand the world. Recently, several format-specific datasets have been proposed, such as numerical reasoning in the settings of Natural Language Inference (NLI), R…

Natural Language InferenceQuestion AnsweringReading Comprehension

A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base

2021-11-01 · Findings (EMNLP) 2021 11 · Yu Feng, Jing Zhang, Gaole He, Wayne Xin Zhao 외

Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs). This paper targets at empowering the IR-based KBQA models with the ability of numerical reasoning for ans…

Knowledge Base Question AnsweringQuestion Answering

Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models

2021-12-12 · Yu Feng, Jing Zhang, Xiaokang Zhang, Lemao Liu 외

Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions. This paper proposes a ne…

Data AugmentationKnowledge Base Question AnsweringQuestion Answering