Simpler Context-Dependent Logical Forms via Model Projections

By Reginald Long, Panupong Pasupat, Percy Liang. 2016

106 citations recorded by the source corpus.

We consider the task of learning a context-dependent mapping from utterances to denotations. With only denotations at training time, we must search over a combinatorially large space of logical forms, which is even larger with context-dependent utterances. To cope with this challenge, we perform successive projections of the full model onto simpler models that operate over equivalence classes of logical forms. Though less expressive, we find that these simpler models are much faster and can be surprisingly effective. Moreover, they can be used to bootstrap the full model. Finally, we collected three new context-dependent semantic parsing datasets, and develop a new left-to-right parser.

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

SPoC: Search-based Pseudocode to Code (2019, background): “Instead of a single query, some work aims to parse a sequence of utterances into queries that can be sequentially executed [2, 17, 23].”
Speaker-Follower Models for Vision-and-Language Navigation (2018, background): “Systems that learn to carry out natural language instructions in an interactive environment include approaches based on intermediate structured and executable representations of language [50, 9, 4, 28, 20] and approaches that map directly from language and world state observations to actions [7, 2, ”
Search-based Neural Structured Learning for Sequential Question Answering (2017, background): “More recently, Long et al. (2016) collect three contextual semantic parsing datasets (from synthetic domains) that contain coreferences to entities and 1.”
NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System (2018, background): “Others (Kwiatkowski et al., 2013; Long et al., 2016; Guu et al., 2017; Iyer et al., 2017; Zhong et al., 2017) evaluate the generated code through execution.”
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension (2018, methodology): “The SCoNE dataset (Long et al., 2016) contains paragraphs describing a changing world state in three synthetic, deterministic domains, and”
Implicit Representations of Meaning in Neural Language Models (2021, methodology): “Data: Alchemy Alchemy, the first dataset used in our experiments, is derived from the SCONE (Long et al., 2016) semantic parsing tasks.”
From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood (2017, methodology): “Following Long et al. (2016), we de-compose each training example into smaller examples.”
Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing (2019, background): “Recently, context-dependent semantic parsing has drawn plenty of attention (Long et al., 2016; Iyyer et al., 2017; Iyer et al., 2018; Suhr et al., 2018; Suhr and Artzi, 2018), where the generation of logical forms is conditioned on the context environment.”
QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships (2018, background): “There has been rapid progress in question-answering (QA), spanning a wide variety of tasks and phenomena, including factoid QA (Rajpurkar et al. 2016), entailment (Bow-man et al. 2015), sentiment (Maas et al. 2011), and ellipsis and coreference (Long, Pasupat, and Liang 2016).”
FlowQA: Grasping Flow in History for Conversational Machine Comprehension (2018, methodology): “When tested on SCONE (Long et al., 2016), FLOWQA outperforms all existing systems in three different domains, resulting in a range of accuracy improvement from +1.”
Can we generate shellcodes via natural language? An empirical study (2021, background): “, 2020), has been previously addressed to generate executable snippets in domain-specific languages (Guu et al., 2017; Long et al., 2016), and several programming languages, including Python (Yin and Neubig, 2017) and Java (Ling et al.”
Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos (2017, background): “Our goal of resolving reference in transcription of instructional videos is related to the procedure text understanding in the NLP community [4, 18, 23, 29, 33, 34, 36].”
Learning Adaptive Language Interfaces through Decomposition (2020, methodology): “Later, Long et al. (2016) introduced the SCONE Dataset, requiring building models that can reason over both types of context.”
Learning to Generalize from Sparse and Underspecified Rewards (2019, background): “…environments where a learning agent is provided with a natural language input and asked to produce a sequence of actions for achieving a goal speciﬁed in the input text ( e.g., Long et al. (2016); Hermann et al. (2017); Chaplot et al. (2018); Fu et al. (2019); Chevalier-Boisvert et al. (2019)).”
Coupling Distributed and Symbolic Execution for Natural Language Queries (2016, background): “A typical approach is to convert a natural language sentence to an “executable” logic forms for table/knowledge base querying, known as semantic parsing [Long et al., 2016; Pasupat and Liang, 2016].”
CONVERSATIONAL MACHINE COMPREHENSION (2019, methodology): “We compare our approaches with previous semantic parsing approaches (Long et al., 2016; Guu et al., 2017), which map each instruction into a logical form, and then execute the logical form to update the world state, and (Fried et al., 2018; Suhr & Artzi, 2018), which maps each instruction into…”