Results 1 to 10 of about 124,081 (292)
RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL [PDF]
One of the recent best attempts at Text-to-SQL is the pre-trained language model. Due to the structural property of the SQL queries, the seq2seq model takes the responsibility of parsing both the schema items (i.e., tables and columns) and the skeleton ...
Haoyang Li+3 more
semanticscholar +1 more source
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding [PDF]
Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms.
Kenton Lee+9 more
semanticscholar +1 more source
Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing [PDF]
The task of text-to-SQL parsing, which aims at converting natural language questions into executable SQL queries, has garnered increasing attention in recent years. One of the major challenges in text-to-SQL parsing is domain generalization, i.e., how to
Jinyang Li+9 more
semanticscholar +1 more source
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models [PDF]
Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate
Torsten Scholak+2 more
semanticscholar +1 more source
Log-based Anomaly Detection Without Log Parsing [PDF]
Software systems often record important runtime information in system logs for troubleshooting purposes. There have been many studies that use log data to construct machine learning models for detecting system anomalies.
Van-Hoang Le, Hongyu Zhang
semanticscholar +1 more source
Pyramid Scene Parsing Network [PDF]
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the ...
Hengshuang Zhao+4 more
semanticscholar +1 more source
TaPas: Weakly Supervised Table Parsing via Pre-training [PDF]
Answering natural language questions over tables is usually seen as a semantic parsing task. To alleviate the collection cost of full logical forms, one popular approach focuses on weak supervision consisting of denotations instead of logical forms ...
Jonathan Herzig+4 more
semanticscholar +1 more source
Named Entity Recognition as Dependency Parsing [PDF]
Named Entity Recognition (NER) is a fundamental task in Natural Language Processing, concerned with identifying spans of text expressing references to entities. NER research is often focused on flat entities only (flat NER), ignoring the fact that entity
Juntao Yu, Bernd Bohnet, Massimo Poesio
semanticscholar +1 more source
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing [PDF]
Spatial pooling has been proven highly effective to capture long-range contextual information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond conventional spatial pooling that usually has a regular shape of NxN, we rethink ...
Qibin Hou+3 more
semanticscholar +1 more source
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task [PDF]
We present Spider, a large-scale complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 unique complex SQL queries on 200 databases with multiple tables covering 138 ...
Tao Yu+11 more
semanticscholar +1 more source