Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering

Feng, Yanlin; Chen, Xinyue; Lin, Bill Yuchen; Wang, Peifeng; Yan, Jun; Ren, Xiang

doi:10.18653/v1/2020.emnlp-main.99

Cited by 133 publications

(136 citation statements)

References 28 publications

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…Results (as mean and standard deviation) are computed over 4 experimental runs with different random seeds (top score in boldface, second score underlined). Parts of the results for baselines are reported from our another work (Feng et al, 2020…”

Section: Baselinesmentioning

confidence: 99%

Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Wang¹,

Peng²,

Ilievski³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

Commonsense question answering (QA) requires background knowledge which is not explicitly stated in a given context. Prior works use commonsense knowledge graphs (KGs) to obtain this knowledge for reasoning. However, relying entirely on these KGs may not suffice, considering their limited coverage and the contextual dependence of their knowledge. In this paper, we augment a general commonsense QA framework with a knowledgeable path generator. By extrapolating over existing paths in a KG with a state-of-the-art language model, our generator learns to connect a pair of entities in text with a dynamic, and potentially novel, multi-hop relational path. Such paths can provide structured evidence for solving commonsense questions without finetuning the path generator. Experiments on two datasets show the superiority of our method over previous works which fully rely on knowledge from KGs (with up to 6% improvement in accuracy), across various amounts of training data. Further evaluation suggests that the generated paths are typically interpretable, novel, and relevant to the task.

show abstract

Section: Baselinesmentioning

confidence: 99%

Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Wang¹,

Peng²,

Ilievski³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…For CommonsenseQA (Table 2), our HGN ranks first among comparable approaches and shows remarkable improvement over PathGenerator and the LM Finetuning approach (ALBERT (Lan et al, 2020)). Higher-ranking (Schlichtkrull et al, 2018b) 65.56 82.42 GAT (Velickovic et al, 2018) 65.88 82.78 GN (Battaglia et al, 2018) 65.52 82.06 GconAttn (Wang et al, 2019a) 65.17 82.35 MHGRN (Feng et al, 2020) 65.92 83.07 PathGenerator 64 and AL-BERT+KD additionally use concept definitions from dictionaries. ALBERT+DESC-KCR and AL-BERT+KCR leverage "question concept" annotations, which are used during the construction of the CommmonsenseQA dataset and allow the model to learn shortcuts that don't generalize to other datasets.…”

Section: Resultsmentioning

confidence: 99%

Learning Contextualized Knowledge Structures for Commonsense Reasoning

Yan¹,

Raman²,

Chan³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

Self Cite

View full text Add to dashboard Cite

Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/generation often hinder models from obtaining useful knowledge to reason over. To address these issues, we propose a new KG-augmented model: Hybrid Graph Network (HGN). Unlike prior methods, HGN learns to jointly contextualize extracted and generated knowledge by reasoning over both within a unified graph structure. Given the task input context and an extracted KG subgraph, HGN is trained to generate embeddings for the subgraph's missing edges to form a "hybrid" graph, then reason over the hybrid graph while filtering out context-irrelevant edges. We demonstrate HGN's effectiveness through considerable performance gains across four commonsense reasoning benchmarks, plus a user study on edge validness and helpfulness. 1

show abstract

“…Most common approaches include adapting entity embeddings learned by models such as BERT by providing additional knowledge from different ontologies that define relations between entities. This can be done either by using templates to convert the relations to text before finetuning embeddings (Weissenborn et al, 2017;Lauscher et al, 2020;, by combining relational information from knowledge graphs with text embeddings (Mihaylov and Frank, 2018;Chen et al, 2018;Zhang et al, 2019;Yang et al, 2019a;, or by jointly learning knowledge graph and textual embeddings (Peters et al, 2019;Feng et al, 2020). These ontologies are either generic like WordNet (Miller, 1995), Concept-Net Singh, 2004), andWikidata (Vrandečić andKrötzsch, 2014), or more specific to a particular domain like the UMLS (Bodenreider, 2004).…”

Section: Related Workmentioning

confidence: 99%

Are we there yet? Exploring clinical domain knowledge of BERT models

Sushil¹,

Šuster²,

Daelemans³

2021

Proceedings of the 20th Workshop on Biomedical Language Processing

View full text Add to dashboard Cite

We explore whether state-of-the-art BERT models encode sufficient domain knowledge to correctly perform domain-specific inference. Although BERT implementations such as BioBERT are better at domain-based reasoning than those trained on general-domain corpora, there is still a wide margin compared to human performance on these tasks. To bridge this gap, we explore whether supplementing textual domain knowledge in the medical NLI task: a) by further language model pretraining on the medical domain corpora, b) by means of lexical match algorithms such as the BM25 algorithm, c) by supplementing lexical retrieval with dependency relations, or d) by using a trained retriever module, can push this performance closer to that of humans. We do not find any significant difference between knowledge supplemented classification as opposed to the baseline BERT models, however. This is contrary to the results for evidence retrieval on other tasks such as open domain question answering (QA). By examining the retrieval output, we show that the methods fail due to unreliable knowledge retrieval for complex domain-specific reasoning. We conclude that the task of unsupervised text retrieval to bridge the gap in existing information to facilitate inference is more complex than what the state-of-the-art methods can solve, and warrants extensive research in the future.

show abstract

Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering

Cited by 133 publications

References 28 publications

Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Learning Contextualized Knowledge Structures for Commonsense Reasoning

Are we there yet? Exploring clinical domain knowledge of BERT models

Contact Info

Product

Resources

About