Question Answering as Global Reasoning Over Semantic Abstractions

By Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Dan Roth. 2018

83 citations recorded by the source corpus.

We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set of linguistic constructs but have limited training data. To address these challenges, we present the first system, to the best of our knowledge, that reasons over a wide range of semantic abstractions of the text, which are derived using off-the-shelf, general-purpose, pre-trained natural language modules such as semantic role labelers, coreference resolvers, and dependency parsers. Representing multiple abstractions as a family of graphs, we translate question answering (QA) into a search for an optimal subgraph that satisfies certain global and local properties. This formulation generalizes several prior structured QA systems. Our system, SEMANTICILP, demonstrates strong performance on two domains simultaneously. In particular, on a collection of challenging science QA datasets, it outperforms various state-of-the-art approaches, including neural models, broad coverage information retrieval, and specialized techniques using structured knowledge bases, by 2%-6%.

Subfields: Artificial Intelligence, Molecular Biology, Prompting & Reasoning, Question Answering & Reading Comprehension

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 Molecular Biology

In Prompting & Reasoning

In Question Answering & Reading Comprehension

Citations in the corpus

Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences (2018, neutral): “tions (Khashabi et al., 2018a).”
QASC: A Dataset for Question Answering via Sentence Composition (2019, methodology): “Standard IR approaches for QA retrieve facts using question + answer as their IR query (Clark et al. 2016; Khot, Sabharwal, and Clark 2017; Khashabi et al. 2018b).”
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models (2021, methodology): “Traditionally, this idea has been used to compose outputs of lower-level language tasks to solve the higher-level NLU tasks (Harabagiu and Hickl, 2006; Lally et al., 2012; Khot et al., 2017; Khashabi et al., 2018b).”
A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset (2018, methodology): “search over semantically-motivated graph structures (Khashabi et al., 2018).”
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project (2019, methodology): “Early work was dominated by information retrieval, statistical, and automated rule extraction and reasoning methods (Clark et al., 2014, 2016; Khashabi et al., 2016; Khot et al., 2017; Khashabi et al., 2018).”
Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds (2018, methodology): “, 2004) and methods that build on extracted structured representations from both the question and the input text (Sachan et al., 2015; Sachan and Xing, 2016; Khot et al., 2017; Khashabi et al., 2018b).”
Case-Based Abductive Natural Language Inference (2020, methodology): “A I] 2 D ec 2 02 1 straints to guide the generation of a plausible explanation graph (Khashabi et al., 2018; Khot et al., 2017).”
Explainable Natural Language Reasoning via Conceptual Unification (2020, background): “Recent approaches adopt global and local semantic constraints to guide the generation of plausible multi-hop explanations (Khashabi et al., 2018; Jansen et al., 2017; Khashabi et al., 2016).”
Temporal Reasoning on Implicit Events from Distant Supervision (2020, background): “, 2019) and other decomposition-based approaches (Talmor and Berant, 2018; Khashabi et al., 2018; Li et al., 2019; Wolfson et al., 2020; Khot et al., 2021).”
Frame- and Entity-Based Knowledge for Common-Sense Argumentative Reasoning (2018, background): “Multiple levels of knowledge processing help: combining several kinds of annotations beneﬁts question answering (Khashabi et al., 2018), exter-nal knowledge about synonyms enhances inference (Chen et al., 2018), and jointly modeling several tasks (e.g., frame-semantic parsing and dependency…”
Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering (2019, methodology): “On the Multi-Sentence Reading Comprehension (MultiRC) dataset (Khashabi et al., 2018a), we achieved a gain of 8.3% EM0 with ROCC justifications when compared to the case where the complete comprehension passage was provided to the BERT classifier.”
Joint Constrained Learning for Event-Event Relation Extraction (2020, background): “This is not only at the core of text understanding, but is also beneﬁcial to various applications such as question answering (Khashabi et al., 2018), narrative prediction (Chaturvedi et al., 2017), timeline construction (Do et al., 2012a) and summarization (Daum´e III and Marcu, 2006).”