Semantic Parsing

380 papers with code • 20 benchmarks • 42 datasets

Semantic Parsing is the task of transducing natural language utterances into formal meaning representations. The target meaning representations can be defined according to a wide variety of formalisms. This include linguistically-motivated semantic representations that are designed to capture the meaning of any sentence such as λ-calculus or the abstract meaning representations. Alternatively, for more task-driven approaches to Semantic Parsing, it is common for meaning representations to represent executable programs such as SQL queries, robotic commands, smart phone instructions, and even general-purpose programming languages like Python and Java.

Source: Tranx: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

Libraries

Use these libraries to find Semantic Parsing models and implementations

Improving Generalization in Semantic Parsing by Increasing Natural Language Variation

saparina/text2sql-nlvariation 13 Feb 2024

Text-to-SQL semantic parsing has made significant progress in recent years, with various models demonstrating impressive performance on the challenging Spider benchmark.

2
13 Feb 2024

Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings

jiangyctarheel/sq-transformer 9 Feb 2024

Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity.

10
09 Feb 2024

Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs

sebischair/llm-sp-cqa 3 Jan 2024

Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input.

2
03 Jan 2024

Rethinking Tabular Data Understanding with Large Language Models

Leolty/tablellm 27 Dec 2023

Large Language Models (LLMs) have shown to be capable of various tasks, yet their capability in interpreting and reasoning over tabular data remains an underexplored area.

7
27 Dec 2023

Leveraging Code to Improve In-context Learning for Semantic Parsing

allenai/code-semparse 16 Nov 2023

In-context learning (ICL) is an appealing approach for semantic parsing due to its few-shot nature and improved generalization.

4
16 Nov 2023

Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering

klee972/exec-filter 2 Nov 2023

The problem of spurious programs is a longstanding challenge when training a semantic parser from weak supervision.

0
02 Nov 2023

SLOG: A Structural Generalization Benchmark for Semantic Parsing

bingzhilee/slog 23 Oct 2023

The goal of compositional generalization benchmarks is to evaluate how well models generalize to new complex linguistic expressions.

5
23 Oct 2023

A Unified View of Evaluation Metrics for Structured Prediction

wanmok/metametric 20 Oct 2023

We present a conceptual framework that unifies a variety of evaluation metrics for different structured prediction tasks (e. g. event and relation extraction, syntactic and semantic parsing).

2
20 Oct 2023

Semantic Decomposition of Question and SQL for Text-to-SQL Parsing

bgunlp/qpl 20 Oct 2023

However, this strategy encounters two major obstacles: (1) existing datasets lack question decomposition; (2) due to the syntactic complexity of SQL, most complex queries cannot be disentangled into sub-queries that can be readily recomposed.

1
20 Oct 2023

MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations

mcgill-nlp/magnifico 18 Oct 2023

Additionally, our analysis uncovers the semantic predispositions in LLMs and reveals the impact of recency bias for information presented in long contexts.

0
18 Oct 2023