Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension

By Xinyun Chen, Chen Liang, Adams Wei Yu, Denny Zhou, Dawn Song, Quoc V. Le. 2020

109 citations recorded by the source corpus.

Subfields: Natural Language Processing, Graph Learning

How researchers see this paper

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

In Natural Language Processing

In Graph Learning

Citations in the corpus

Chain of Thought Prompting Elicits Reasoning in Large Language Models (2022, background): “First, in neuro-symbolic computing it has been recognized that generating intermediate results significantly improves accuracy when a desired input-output mapping involves multiple computational steps (Chen et al., 2019; Dong et al., 2019; Mao et al., 2021).”
Reasoning Like Program Executors (2022, methodology): “, symbolic reasoners attached to LMs, neuralsymbolic reasoning shines in a variety of reasoning tasks (Chen et al., 2020c; Tu et al., 2020; Wolfson et al., 2020).”
Training Verifiers to Solve Math Word Problems (2021, background): “…specialized encoder-decoder architectures (Amini et al., 2019; Chiang and Chen, 2018; Xie and Sun, 2019; Chen et al., 2020; Li et al., 2020), with the strongest results often relying on large pretrained encoders from the BERT family (Chen et al., 2019; Kim et al., 2020; Liang et al., 2021).”
Injecting Numerical Reasoning Skills into Language Models (2020, background): “Two recent work (Andor et al., 2019; Chen et al., 2020) take a more symbolic approach and output a symbolic program augmented with operations over text.”
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models (2022, background): “The two benchmarks considered in this paper, SCAN (Lake & Baroni, 2018) and DROP (Dua et al., 2019), have often been tackled by neural-symbolic methods (Andor et al., 2019; Chen et al., 2019, 2020; Nye et al., 2020; Shaw et al., 2021; Kim, 2021).”
Learning from Task Descriptions (2020, background): “Attempts to generalize semantic parsing to more open domains are still nascent (Chen et al., 2020; Gupta et al., 2020).”
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models (2021, methodology): “This includes, in addition, frameworks for mapping math word problems to a symbolic representation based on mathematical operations (Seo et al., 2015; Roy and Roth, 2018; Amini et al., 2019; Chen et al., 2020), as well as mapping questions to pre-defined set of operations (Berant et al.”
Question Directed Graph Attention Network for Numerical Reasoning over Text (2020, background): “(Chen et al., 2020) provides a semantic parser that points to locations in the text that can be used in further numerical operations.”
Explanations for CommonsenseQA: New Dataset and Models (2021, background): “, 2020), or (ii) proposing a model with improved answer accuracy (Amini et al., 2019; Bhargav et al., 2020; Chen et al., 2020).”
FinQA: A Dataset of Numerical Reasoning over Financial Data (2021, methodology): “As most existing QA datasets were constructed by MTurk workers (Yang et al., 2018; Dua et al., 2019; Chen et al., 2020c), it requires substantial domain-specific knowledge to compose meaningful questions that are hard for computers to answer.”
From LSAT: The Progress and Challenges of Complex Reasoning (2021, methodology): “Here we adopt a pre-trained encoderdecoder model for program generation [18, 88].”
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs (2021, methodology): “Besides structured databases, there are other works on learning to synthesize programs for unstructured text understanding, including reading comprehension (Chen et al., 2020b; Amini et al., 2019) and sequence-to-sequence translation (Chen et al., 2020a; Nye et al., 2020b).”
Successive Prompting for Decomposing Complex Questions (2022, methodology): “…et al., 2022) the latent steps are supervised, interpretable sentences; in other models these latent steps might be a program (Gupta et al., 2020; Chen et al., 2020) or even just the (unsupervised) hidden states in the model (Segal et al., 2020; Andor et al., 2019) We focus on models that take…”
Learning to Solve Complex Tasks by Talking to Agents (2021, background): “Semantic Parsing is typically focused on building models that can map language problems to executable symbolic representation based on pre-deﬁned grammar (Roy and Roth, 2018; Krishna-murthy et al., 2017; Chen et al., 2020).”
Neurosymbolic Programming (2021, background): “Chen et al. (2019) develop a Neural Symbolic Reader (NeRd) architecture for reading comprehension, i.e. question answering over natural language passages.”
Teaching Machine Comprehension with Compositional Explanations (2020, background): “In the broader context, N E R D framework with domain-speciﬁc language (Chen et al., 2020) is proposed to bridge “sym-bolic and distributed representations”, which can also be interpreted as breaking down a complex task into individual modules.”
Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations (2022, methodology): “Another line of works apply symbolic methods on top of LMs to improve their consistency, spanning from a lexical constraint on sequence decoding (Lu et al., 2021a) to a symbolic world model (Nye et al., 2021b) and discrete operations (Chen et al., 2019; Cobbe et al., 2021).”