Improving Natural Language Inference Using External Knowledge in the Science Questions Domain

By Xiaoyang Wang, Pavan Kapanipathi, Ryan Musa, Mo Yu, Kartik Talamadupula, Ibrahim Abdelaziz, Maria Chang, Achille Fokoue, Bassem Makni, Nicholas Mattei and 1 more. 2018

177 citations recorded by the source corpus.

Natural Language Inference (NLI) is fundamental to many Natural Language Processing (NLP) applications including semantic search and question answering. The NLI problem has gained significant attention due to the release of large scale, challenging datasets. Present approaches to the problem largely focus on learning-based methods that use only textual information in order to classify whether a given premise entails, contradicts, or is neutral with respect to a given hypothesis. Surprisingly, the use of methods based on structured knowledge – a central topic in artificial intelligence – has not received much attention vis-a-vis the NLI problem. While there are many open knowledge bases that contain various types of reasoning information, their use for NLI has not been well explored. To address this, we present a combination of techniques that harness external knowledge to improve performance on the NLI problem in the science questions domain. We present the results of applying our techniques on text, graph, and text-and-graph based models; and discuss the implications of using external knowledge to solve the NLI problem. Our model achieves close to state-of-the-art performance for NLI on the SciTail science questions dataset.

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, background): “…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.”
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering (2020, methodology): “As in our framework, we use the pooling of the last layer of hidden states from the pre-trained language model et al., 2019) which models the alignment between entities via attention and pools over all the entity embeddings.”
Making Language Models Better Reasoners with Step-Aware Verifier (2022, background): “…learning systems by exploiting symbolic systems, including knowledge graphs (Mihaylov and Frank, 2018; Bauer et al., 2018; Kundu et al., 2019; Wang et al., 2019; Lin et al., 2019; Ding et al., 2019; Feng et al., 2020; Wang et al., 2022b), or question taxonomies (Dua et al., 2019; Andor et…”
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning (2019, methodology): “C AT (Wang et al., 2019c) concatenates the graph-based and text-based representations of the statement and then feed it into a classiﬁer.”
Unifying Large Language Models and Knowledge Graphs: A Roadmap (2023, background): “inputs and the other one processes the relevant knowledge graph inputs [134].”
Kformer: Knowledge Injection in Transformer Feed-Forward Layers (2022, methodology): “Another way [1,20,22] is to obtain the context representation (c) using the pre-tained model and the knowledge representation (k) through a knowledge based model.”
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (2020, background): “This has led many to leverage knowledge graphs (KGs) (Mihaylov and Frank, 2018; Lin et al., 2019; Wang et al., 2019; Yang et al., 2019).”
Framework for Evaluating LLM Performance in Undergraduate Calculus (2026, unknown): “Moreover, natural language inference (NLI) tasks have benefited from utilizing external knowledge bases, highlighting the potential of structured knowledge in enhancing model performance in specific domains, such as science questions [23].”
Interpretability Framework for LLMs in Undergraduate Calculus (2025, unknown): “Moreover, natural language inference (NLI) tasks have benefited from utilizing external knowledge bases, highlighting the potential of structured knowledge in enhancing model performance in specific domains, such as science questions[15].”