SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing

By Tao Yu, Rui Zhang, Oleksandr Polozov, Christopher Meek, Ahmed Hassan Awadallah. 2021

75 citations recorded by the source corpus.

Subfields: Natural Language Processing, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Dragomir R. Radev
2. Caiming Xiong
3. Percy Liang
4. Rui Zhang
5. Xi Victoria Lin
6. Luke S. Zettlemoyer
7. Mohit Bansal
8. Ahmed Elgohary

In Information Extraction

1. Jian-Guang Lou
2. Qian Liu
3. Jiaqi Guo
4. Zeqi Lin
5. Fei Huang
6. Ahmed Hassan Awadallah
7. Caiming Xiong

Citations in the corpus

• Can Large Language Models Transform Computational Social Science? (2023, background): “NLP researchers who aim to improve existing LLMs to empower more CSS tasks should study the unique technical challenges of conversations, long documents, and cross-document reasoning (Beltagy et al., 2020; Caciularu et al., 2021; Yu et al., 2021).”
• TAPEX: Table Pre-training via Learning a Neural SQL Executor (2021, methodology): “(Yin et al., 2020; Herzig et al., 2020), leveraged human-annotated parallel NL-table datasets for pre-training (Deng et al., 2021; Yu et al., 2021a), or synthesized a NL-table corpus using human-written templates (Yu et al., 2021a; Eisenschlos et al., 2020).”
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs (2023, background): “R(2)SQL [16], SCORE [56], and STAR [3] enhance contextual learning for conversational text-to-SQL tasks.”
• FeTaQA: Free-form Table Question Answering (2021, background): “…language models, recent work (Yin et al., 2020; Herzig et al., 2020; Eisenschlos et al., 2020; Iida et al., 2021) jointly learns representations for nat-ural language sentences and structured tables, and Yu et al. (2020, 2021) use pre-training approach for table semantic parsing.”
• Dialogue State Tracking with a Language Model using Schema-Driven Prompting (2021, methodology): “The evaluation results on MultiWOZ 2.1 are shown in Table 3, where we compare with TRADE (Wu et al., 2019), MinTL (Lin et al., 2020a), SST (Chen et al., 2020), TripPy (Heck et al., 2020), Simple-TOD (Hosseini-Asl et al., 2020), SOLOIST (Peng et al., 2020a) and TripPy+SCORE (Yu et al., 2020).”
• NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction (2021, methodology): “Recent progress in model architectures (Wang et al., 2020) and pretraining (Yin et al., 2020; Yu et al., 2021a) has led to parsers that already outperform Seq2Struct by more than 30% in parsing accuracy.3 Here, we ask whether NL-EDIT that we train on SPLASH (and synthetic feedback) can generalize…”