Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension

By Liang Wang, Meng Sun, Wei Zhao, Kewei Shen, Jingming Liu. 2018

78 citations recorded by the source corpus.

This paper describes our system for SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. We use Three-way Attentive Networks (TriAN) to model interactions between the passage, question and answers. To incorporate commonsense knowledge, we augment the input with relation embedding from the graph of general knowledge ConceptNet. As a result, our system achieves state-of-the-art performance with 83.95% accuracy on the official test data. Code is publicly available at https://github.com/intfloat/commonsense-rc.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Improving Question Answering with External Knowledge (2019, methodology): “…Rajpurkar et al., 2016; Lai et al., 2017; Mihaylov et al., 2018; Clark et al., 2018; Choi et al., 2018; Reddy et al., 2018; Sun et al., 2019) and models (Chen et al., 2016; Wang et al., 2018b; Radford et al., 2018; Devlin et al., 2018; Sun et al., 2018) to drive progress in question answering.”
Dual Co-Matching Network for Multi-choice Reading Comprehension (2019, background): “However, previous unidirectional matching strategies usually calculate question-aware passage representation and ignore passage-aware question representation when modeling the relationship between passage and question (Wang et al. 2018b; Tang, Cai, and Zhuo 2019; Chen et al. 2019).”
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning (2019, background): “For example, in Figure 5, the Commonsense-RC base-line mistakenly selected the choice which has the most overlapped words with the paragraph without any commonsense reasoning.”
Improving Machine Reading Comprehension with General Reading Strategies (2018, methodology): “RACE has been used to pre-train a model for other MRC tasks as it contains the largest number of general domain non-extractive questions (Table 1) (Ostermann et al., 2018; Wang et al., 2018a).”
Getting Closer to AI Complete Question Answering: A Set of Prerequisite Real Tasks (2020, methodology): “We tested the TriAN model (Wang et al. 2018), which is currently the bestperforming system on MCScript dataset and the winner of SemEval 2018 Task 11.”
WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge (2020, background): “…(Liu and Singh, 2004), and quantity (Elazar et al., 2019), and has been proven crucial in many downstream tasks like question answering (Lin et al., 2019), dialogue system (Zhou et al., 2018), reading comprehension (Wang et al., 2018), and pronoun coreference resolution (Levesque et al., 2012).”
Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (2019, background): “Weissenborn et al. (2017), Bauer et al. (2018), Mihaylov and Frank (2018), Pan et al. (2019), Chen et al. (2018), Wang et al. (2018) follow a retrieve-then-encode paradigm, i.e., they ﬁrst retrieve relevant knowledge from KBs, and only the retrieved knowledge relevant locally to the reading text…”
Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks (2020, background): “KG Attentive Representations Motivated by previous work on question answering (Seo et al., 2017; Zhu et al., 2018; Wang et al., 2018; Huang et al., 2019), which uses attention among different segments of the input, here we treat the knowledge tuples as a new segment.”
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering (2018, background): “Similar to Wang (2018), we consider the following components for each word: Word Embedding.”
TransOMCS: From Linguistic Graphs to Commonsense Knowledge (2020, methodology): “, 2019] and reading comprehension [Wang et al., 2018].”
Using Natural Language Relations between Answer Choices for Machine Comprehension (2019, methodology): “TriAN-single results are as reported in (Wang et al., 2018).”
Improving Question Answering by Commonsense-Based Pre-Training (2018, unknown): “We ﬁnd that TriAN performs comparably to a recent state-of-the-art system (Zhang et al. 2018), therefore we use it as our document-based model for ARC as well.”