Semantic Parsing via Paraphrasing

By Jonathan Berant, Percy Liang. 2014

568 citations recorded by the source corpus.

A central challenge in semantic parsing is handling the myriad ways in which knowledge base predicates can be expressed. Traditionally, semantic parsers are trained primarily from text paired with knowledge base information. Our goal is to exploit the much larger amounts of raw text not tied to any knowledge base. In this paper, we turn semantic parsing on its head. Given an input utterance, we first use a simple method to deterministically generate a set of candidate logical forms with a canonical realization in natural language for each. Then, we use a paraphrase model to choose the realization that best paraphrases the input, and output the corresponding logical form. We present two simple paraphrase models, an association model and a vector space model, and train them jointly from question-answer pairs. Our system PARASEMPRE improves stateof-the-art accuracies on two recently released question-answering datasets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2021, methodology): “[124] explore the task of few-shot semantic parsing using LMs by (1) framing the semantic parsing task as a paraphrasing task [7] and (2) constraining the decoding process by only allowing output valid according to a grammar.”
Stacked Attention Networks for Image Question Answering (2015, background): “Unlike pure language based QA systems that have been studied extensively in the NLP community [28, 14, 4, 31, 3, 32], image QA systems are designed to automatically answer natural language questions according to the content of a reference image.”
Large-scale Simple Question Answering with Memory Networks (2015, background): “On WebQuestions , we evaluate against previous results on this benchmark (Berant et al., 2013; Yao and Van Durme, 2014; Berant and Liang, 2014; Bordes et al., 2014a; Yang et al., 2014) in terms of F1-score as deﬁned in (Berant and Liang, 2014), which is the average, over all test questions, of the…”
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 ﬁrst use a ﬁxed syntactic parse to generate a small set of candidate layouts, analogously to the way a semantic grammar generates candidate semantic parses in previous work (Berant and Liang, 2014).”
Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering (2015, background): “It has many real-life applications, such as automatic querying of surveillance video [4] or assisting the visually impaired [5].”
Compositional Semantic Parsing on Semi-Structured Tables (2015, methodology): “…and entities motivates new resources and techniques for improving the accuracy, including the use of ontology matching models (Kwiatkowski et al., 2013), paraphrase models (Fader et al., 2013; Berant and Liang, 2014), and unlabeled sentences (Krishna- murthy and Kollar, 2013; Reddy et al., 2014).”
Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems (2015, background): “There has been a recent surge in interest in such systems that try to answer a question posed in natural language by converting it into a database search over a knowledge base (Berant & Liang, 2014; Kwiatkowski et al., 2013; Fader et al., 2014), which is a setup natural for our QA task also.”
Question Answering with Subgraph Embeddings (2014, methodology): “We also considered an ensemble of our approach and that of (Berant and Liang, 2014).”
Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision (2016, background): “d programs greatly speeds up the training and helps to avoid local optimum. More details of the training procedure can be found in the long version. 3 Experiments and analysis Modern semantic parsers [4], which map natural language utterances to executable logical forms, have been successfully train”
Building a Semantic Parser Overnight (2015, methodology): “This rather unorthodox approach to semantic parsing can be seen as a generalization of Berant and Liang (2014) and is explained in more detail in Pasupat and Liang (2015).”
Automatically Solving Number Word Problems by Semantic Parsing and Reasoning (2015, background): “…type of semantic parsing work (Zelle & Mooney, 1996; Zettlemoyer & Collins, 2005; Zettlemoyer & Collins, 2007; Wong & Mooney, 2007; Cai & Yates, 2013; Berant et al., 2013; Kwiatkowski et al., 2013; Berant & Liang, 2014) maps NL text into logical forms by supervised or semi-supervised learning.”
Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base (2015, background): “is closely related to the knowledge base schema, finding the correct predicates from the large vocabulary in the KB to relations described in the utterance remains a difficult problem (Berant and Liang, 2014).”
Towards a Visual Turing Challenge (2014, background): “The progress in both fields has inspired researchers to build holistic architectures for challenging grounding [14, 15, 16], natural language generation from image/video [17, 18, 19, 20, 21] and recently presented question-answering problems [22, 23, 24, 25, 26].”
FVQA: Fact-Based Visual Question Answering (2016, background): “KB-QA approaches can be divided into two categories: semantic parsing methods [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47] that try to translate questions into accurate logical expressions and then map to KB queries, and information retrieval methods [48], [49], [50], [51], [52],”
Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph (2018, methodology): “to the simple QA task range from semantic parsing based methods (Berant and Liang 2014; Fader, Zettlemoyer, and Etzioni 2014) to embedding based methods (Bordes, Weston, and Usunier 2014; Bordes, Chopra, and Weston 2014; Yang et al.”