Span-based Semantic Parsing for Compositional Generalization

By Jonathan Herzig, Jonathan Berant. 2020

105 citations recorded by the source corpus.

Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to generalize to new structures built of components observed during training. In this work, we posit that a span-based parser should lead to better compositional generalization. we propose SpanBasedSP, a parser that predicts a span tree over an input utterance, explicitly encoding how partial programs compose over spans in the input. SpanBasedSP extends Pasupat et al. (2019) to be comparable to seq2seq models by (i) training from programs, without access to gold trees, treating trees as latent variables, (ii) parsing a class of non-projective trees through an extension to standard CKY. On GeoQuery, SCAN and CLOSURE datasets, SpanBasedSP performs similarly to strong seq2seq baselines on random splits, but dramatically improves performance compared to baselines on splits that require compositional generalization: from 61.0 → 88.9 average accuracy.

Subfields: Information Extraction, Computational Linguistics & Semantics

How researchers see this paper

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

In Information Extraction

1. Jonathan Herzig
2. Josh Tenenbaum
3. Brenden M. Lake
4. Michael Henry Tessler
5. Maxwell Nye
6. Panupong Pasupat
7. Peter Shaw
8. Fei Sha

In Computational Linguistics & Semantics

1. Josh Tenenbaum
2. Panupong Pasupat
3. Peter Shaw
4. Maxwell Nye
5. Olivier Bousquet
6. Ming-Wei Chang
7. Kristina Toutanova
8. Jonathan Herzig

Citations in the corpus

• Compositional Semantic Parsing with Large Language Models (2022, background): “…architectures (Chen et al., 2020; Nye et al., 2020; Liu et al., 2020; Shaw et al., 2021; Russin et al., 2019; Li et al., 2019; Gordon et al., 2020; Herzig & Berant, 2021) and training algorithms (Lake, 2019; Kim, 2021), training data augmentation (Andreas, 2020; Akyürek et al., 2021), and…”
• Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning (2021, methodology): “Related work includes few or zero-shot semantic parsing using pre-training techniques and paraphrasing (Su & Yan, 2017; Herzig & Berant, 2020).”
• Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both? (2020, result): “We also compare with the concurrently developed SpanBasedSP model(5) (Herzig and Berant, 2020).”
• Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing (2022, background): “, 2022), specialized architectures (Li et al., 2019; Russin et al., 2019; Gordon et al., 2020; Liu et al., 2020; Nye et al., 2020; Chen et al., 2020; Zheng and Lapata, 2021; Oren et al., 2020; Herzig and Berant, 2021; Ruiz et al., 2021; Wang et al., 2021), ensemble models (Shaw et al.”
• Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations (2021, background): “…(Li et al., 2019; Russin et al., 2019; Gordon et al., 2020; Liu et al., 2020; Nye et al., 2020; Chen et al., 2020; Zheng and Lapata, 2020; Oren et al., 2020; Herzig and Berant, 2020), hybrid models (Shaw et al., 2020), meta-learning (Lake, 2019), and compositional data augmentation (Andreas, 2020).”
• SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models (2022, background): “2021) conducted few-shot semantic parsing by using pretrained LMs to first generate canonical natural language utterances, and then transform them to final formal language through synchronous context-free grammar (SCFG) (Jia and Liang, 2016).”