Learning Dependency-Based Compositional Semantics

By Percy Liang, Michael I. Jordan, Daniel Klein. 2011

618 citations recorded by the source corpus.

Suppose we want to build a system that answers a natural language question by representing its semantics as a logical forxm and computing the answer given a structured database of facts. The core part of such a system is the semantic parser that maps questions to logical forms. Semantic parsers are typically trained from examples of questions annotated with their target logical forms, but this type of annotation is expensive.Our goal is to instead learn a semantic parser from question–answer pairs, where the logical form is modeled as a latent variable. We develop a new semantic formalism, dependency-based compositional semantics (DCS) and define a log-linear distribution over DCS logical forms. The model parameters are estimated using a simple procedure that alternates between beam search and numerical optimization. On two standard semantic parsing benchmarks, we show that our system obtains comparable accuracies to even state-of-the-art systems that do require annotated logical forms.

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

In Natural Language Processing

Citations in the corpus

Semantic Parsing on Freebase from Question-Answer Pairs (2013, methodology): “Recent developments aim to lift these limitations, either by reducing the amount of supervision (Clarke et al., 2010; Liang et al., 2011; Goldwasser et al., 2011; Artzi and Zettlemoyer, 2011) or by increasing the number of logical Occidental College, Columbia University”
Break-It-Fix-It: Unsupervised Learning for Program Repair (2021, methodology): “This is commonly used in structured generation problems such as semantic parsing, program synthesis and molecule generation (Liang et al., 2013; Berant et al., 2013; Guu et al., 2017; Min et al., 2019; Zhong et al., 2020; Yang et al., 2020).”
SPoC: Search-based Pseudocode to Code (2019, background): “One of its traditional tasks is to parse a given question (usually a single sentence) into an executable database query [42, 43, 20, 4, 44, 39].”
Latent Retrieval for Weakly Supervised Open Domain Question Answering (2019, background): “Our approach is also reminiscent of weakly supervised semantic parsing (Clarke et al., 2010; Liang et al., 2013; Artzi and Zettlemoyer, 2013; Fader et al., 2014; Berant et al., 2013; Kwiatkowski et al., 2013), with which we share similar challenges—(1) inference and learning are tightly coupled,…”
A Discrete Hard EM Approach for Weakly Supervised Question Answering (2019, background): “Latent-variable learning has been extensively studied in the literature of semantic parsing (Zettlemoyer and Collins, 2005; Clarke et al., 2010; Liang et al., 2013; Berant et al., 2013; Artzi and Zettlemoyer, 2013).”
ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, background): “Handling such range expressions is beyond the expressive power of the natural logic, and often other logical forms are needed to perform such computations (Liang et al., 2013).”
Training Classifiers with Natural Language Explanations (2018, background): “Semantic parsing of natural language into logical forms is recognized as a challenging problem and has been studied extensively (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Liang et al., 2011; Liang, 2016).”
Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, methodology): “In turn, since we never observe the correct interpretation l for any statement, but only model its evaluation z j , we marginalize over all interpretations whose evaluations in a context x matches z j (similar to Liang et al. (2011)).”
A simple neural network module for relational reasoning (2017, background): “ts on CLEVR [15] than [14], and on par with strongly supervised system of [16]. Text-based question answering Answering text-based questions has long been an active research area in the NLP community [3, 22, 27, 48]. Recently, in addition to traditional symbolic-based question answering architecture”
Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning (2017, background): “…parsing focus on learning parsers without relying on annotated logical forms by leveraging conversational logs (Artzi & Zettlemoyer, 2011), demonstrations (Artzi & Zettlemoyer, 2013), distant supervision (Cai & Yates, 2013; Reddy et al., 2014), and question-answer pairs (Liang et al., 2011).”
Neural Module Networks (2015, background): “These representations bear a certain resemblance to pieces of a combinatory logic [24]: every leaf is implicitly a function taking the image as input, and the root represents the ﬁnal value of the computation.”
The Web as a Knowledge-Base for Answering Complex Questions (2018, background): “Conversely, work on QA through semantic parsing has focused primarily on compositionality: questions are translated to compositional programs that encode a sequence of actions for finding the answer in a knowledge-base (KB) (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Artzi and Zettlemoye”
A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input (2014, methodology): “We use the same templates as [1]: string triggers a predicate, string is under a relation, string is under a trace predicate, two predicates are linked via relation and a predicate has a child.”
Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (2013, methodology): “Clarke et al. (2010), Goldwasser and Roth (2011) and Liang et al. (2011) describe approaches for learning semantic parsers from sentences paired with responses, Krishnamurthy and Mitchell (2012) describe using distant supervision, Artzi and Zettlemoyer (2011) use weak supervision from…”
MovieQA: Understanding Stories in Movies through Question-Answering (2015, neutral): “In computer vision, [20] proposed a Bayesian approach on top of a logic-based QA system [17], while [21, 26] encoded both an image and the question us-2 ing an LSTM and decoded an answer.”
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (2018, neutral): “They have been studied extensively (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Wong and Mooney, 2007; Das et al., 2010; Liang et al., 2011; Banarescu et al., 2013; Artzi and Zettlemoyer, 2013; Reddy et al., 2014; Berant and Liang, 2014; Dong and Lapata, 2016).”
Learning to Compose Neural Networks for Question Answering (2016, methodology): “We can use a familiar functional notation from formal semantics (e.g. Liang et al., 2011) to represent these computations.”