Joint Concept Learning and Semantic Parsing from Natural Language Explanations

By Shashank Srivastava, Igor Labutov, Tom Michael Mitchell. 2017

96 citations recorded by the source corpus.

Natural language constitutes a predominant medium for much of human learning and pedagogy. We consider the problem of concept learning from natural language explanations, and a small number of labeled examples of the concept. For example, in learning the concept of a phishing email, one might say ‘this is a phishing email because it asks for your bank account number’. Solving this problem involves both learning to interpret open ended natural language statements, and learning the concept itself. We present a joint model for (1) language interpretation (semantic parsing) and (2) concept learning (classification) that does not require labeling statements with logical forms. Instead, the model prefers discriminative interpretations of statements in context of observable features of the data as a weak signal for parsing. On a dataset of email-related concepts, our approach yields across-the-board improvements in classification performance, with a 30% relative improvement in F1 score over competitive methods in the low data regime.

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

Learning Transferable Visual Models From Natural Language Supervision (2021, background): “Several papers have leveraged semantic parsing to convert natural language explanations into features (Srivastava et al., 2017) or additional training labels (Hancock et al., 2018).”
ALICE: Active Learning with Contrastive Natural Language Explanations (2020, background): “Another line of research collects heuristic rules as explanations (e.g., ‘honey month’ for predicting SPOUSE relationship) to automatically label unlabeled data (Srivastava et al., 2017; Zhou et al., 2020; Hancock et al., 2018).”
ExpBERT: Representation Engineering with Natural Language Explanations (2020, background): “logical form that is executable over the input sentence and uses the resulting outputs as features (Srivastava et al., 2017) or as noisy labels on unlabeled data (Hancock et al.”
Training Classifiers with Natural Language Explanations (2018, background): “Our work is most similar to that of Srivastava et al. (2017), who also use natural language explanations to train a classiﬁer, but with two important differences.”
Learning with Latent Language (2017, methodology): “Natural language annotations have been used in conjunction with training examples to guide the discovery of logical descriptions of concepts (Ling et al., 2017; Srivastava et al., 2017), and used as an auxiliary loss for training (Frome et al.”
Towards Interpretable Natural Language Understanding with Explanations as Latent Variables (2020, methodology): “Some early work [11, 9, 10] exploited NL explanation as additional features for prediction.”
LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation (2020, background): “(Srivastava et al., 2017) first demonstrated the idea of using natural language explanations for”
Learning from Explanations with Neural Execution Tree (2019, unknown): “Natural language (NL) explanations have shown effectiveness in providing additional supervision, especially in low-resource settings (Srivastava et al., 2017; Hancock et al., 2018).”
Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment (2022, background): “…language inference (Camburu et al., 2018; Kumar and Talukdar, 2020), commonsense question answering (Rajani et al., 2019), document classiﬁcation (Srivastava et al., 2017), relation clas-522 siﬁcation (Murty et al., 2020), reading comprehen-523 sion (Lamm et al., 2021), and fact checking…”
Teaching Machine Comprehension with Compositional Explanations (2020, methodology): “Following previous work (Srivastava et al., 2017; Wang et al., 2020), we ﬁrst use a Combinatory Categorial Grammar (CCG) based semantic parser P (Zettlemoyer & Collins, 2012) to transform explanations into structured parses.”
LIREx: Augmenting Language Inference with Relevant Explanation (2020, background): “Studies in this direction include (Li et al. 2016; Srivastava, Labutov, and Mitchell 2017; Wang et al. 2017; Hancock et al. 2018; Qin et al. 2020; Lee et al. 2020), in which the authors used semantic parsers to convert unstructured NLEs into structured feature-like logical forms.”
Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback (2020, background): “…semantic parsing, learning through interaction (Li et al., 2017a; Hancock et al., 2019; Li et al., 2017b, inter alia) and learning from natural language supervision (Srivastava et al., 2017; Co-Reyes et al., 2019; Srivastava et al., 2018; Hancock et al., 2018; Ling and Fidler, 2017, inter alia).”
Leveraging Language to Learn Program Abstractions and Search Heuristics (2021, background): “…2017; Ye et al., 2020b; Goyal et al., 2020; Liang et al., 2020; Mu et al., 2019; Luketina et al., 2019), and as a high-level specification for program synthesis tasks (Ye et al., 2020a; Nye et al., 2019; Polosukhin & Skidanov, 2018; Ye et al., 2020b; Desai et al., 2016; Srivastava et al., 2017).”
Learning to Learn Semantic Parsers from Natural Language Supervision (2019, background): “guage explanations have been used to augment labeled examples for concept learning (Srivastava et al., 2017) and to help induce programs that solve algebraic word problems (Ling et al.”
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing (2021, background): “[115] Shashank Srivastava, Igor Labutov, and Tom Mitchell.”
Learning to Annotate: Modularizing Data Augmentation for Text Classifiers with Natural Language Explanations (2019, methodology): “Natural language (NL) explanations have shown effectiveness in providing additional supervision, especially in low-resource settings (Srivastava et al., 2017; Hancock et al., 2018).”
Why Build an Assistant in Minecraft? (2019, background): “• For the assistant to get the most out of the (rich) feedback that is given [75, 34], i.”
Learning Adaptive Language Interfaces through Decomposition (2020, background): “Srivastava et al. (2017) used natural language explanations to teach new concepts.”