Ambiguous learning from retrieval: Towards zero-shot semantic parsing
Current neural semantic parsers take a supervised approach requiring a considerable
amount of training data which is expensive and difficult to obtain. Thus, minimizing the …
amount of training data which is expensive and difficult to obtain. Thus, minimizing the …
From paraphrasing to semantic parsing: Unsupervised semantic parsing via synchronous semantic decoding
Semantic parsing is challenging due to the structure gap and the semantic gap between
utterances and logical forms. In this paper, we propose an unsupervised semantic parsing …
utterances and logical forms. In this paper, we propose an unsupervised semantic parsing …
BEAT: Considering question types for bug question answering via templates
Software bugs are ubiquitous in the process of software development and evolution. To
accelerate bug fixing, developers need to quickly obtain bug information and understand the …
accelerate bug fixing, developers need to quickly obtain bug information and understand the …
Program Synthesis for Complex QA on Charts via Probabilistic Grammar Based Filtered Iterative Back-Translation
Answering complex reasoning questions from chart images is a challenging problem
requiring a combination of natural language understanding, fine-grained perception, and …
requiring a combination of natural language understanding, fine-grained perception, and …
A novel multi-task learning framework for semi-supervised semantic parsing
While sequence-to-sequence (seq2seq) models on semantic parsing have demonstrated
significant performance, the need for large amounts of labeled data still hinders the …
significant performance, the need for large amounts of labeled data still hinders the …
Learning to map frequent phrases to sub-structures of meaning representation for neural semantic parsing
Neural semantic parsers usually generate meaning representation tokens from natural
language tokens via an encoder-decoder model. However, there is often a vocabulary …
language tokens via an encoder-decoder model. However, there is often a vocabulary …
Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms
Semantic parsing aims to convert natural language utterances to logical forms. A critical
challenge for constructing semantic parsers is the lack of labeled data. In this paper, we …
challenge for constructing semantic parsers is the lack of labeled data. In this paper, we …
Improving the Consistency of Semantic Parsing in KBQA Through Knowledge Distillation
Abstract Knowledge base question answering (KBQA) is an important task that involves
analyzing natural language questions and retrieving relevant answers from a knowledge …
analyzing natural language questions and retrieving relevant answers from a knowledge …
SETNet: A Novel Semi-Supervised Approach for Semantic Parsing
In this work, we study on semi-supervised semantic parsing under a multi-task learning
framework to alleviate limited performance caused by limited annotated data. Two novel …
framework to alleviate limited performance caused by limited annotated data. Two novel …
Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms
Abstract “Semantic parsing aims to convert natural language utterances to logical forms. A
critical challenge for constructing semantic parsers is the lack of labeled data. In this paper …
critical challenge for constructing semantic parsers is the lack of labeled data. In this paper …