Backpropagating through Structured Argmax using a SPIGOT (P18-1)

Copied to clipboard

Challenge: Structured projection of intermediate gradients (SPIGOT) is a new method for backpropagating through neural networks . structure-based learning methods for natural language processing are increasingly dominated by end-to-end differentiable functions .
Approach: They propose a structured projection of intermediate gradients method for backpropagating through neural networks that includes hard-decision structured predictions in intermediate layers.
Outcome: The proposed method improves on two structured NLP pipelines: syntactic-then-semantic dependency parsing and semantic parser followed by sentiment classification.

Similar Papers

Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning (2020.emnlp-main)

Copied to clipboard

Challenge: Latent structure models can mitigate the error propagation and annotation bottleneck in pipeline systems, while uncovering linguistic insights about the data.
Approach: They propose a latent structure model with a pullback of the downstream learning objective.
Outcome: The proposed model outperforms the known and proposed model in the same family and yields new insights for practitioners and revealing intriguing failure cases.
Dependency Parsing with Backtracking using Deep Reinforcement Learning (2022.tacl-1)

Copied to clipboard

Challenge: Greedy algorithms for NLP such as transition-based parsing are prone to error propagation.
Approach: They propose to allow transition-based parsing to backtrack in cases where evidence contradicts the current solution.
Outcome: The proposed behavior can be implemented on POS tagging and dependency parsing . it shows that backtracking is an effective means to fight error propagation .
Coarse-to-Fine Decoding for Neural Semantic Parsing (P18-1)

Copied to clipboard

Challenge: Experimental results show that semantic parsing is more efficient than using simple decoders.
Approach: They propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages.
Outcome: The proposed architecture consistently improves performance on four datasets characteristic of different domains and meaning representations.
An End-to-End Submodular Framework for Data-Efficient In-Context Learning (2024.findings-naacl)

Copied to clipboard

Challenge: Recent advances in natural language tasks leverage the emergent In-Context Learning ability of pretrained Large Language Models (LLMs).
Approach: They propose a framework for exemplar selection for in-context learning that uses a pool-based active learning approach to select Diverse and informative exemplars from the target tasks’ unlabeled pool.
Outcome: The proposed framework outperforms existing methods for data annotation and similarity-based methods for test query-specific exemplar retrieval on 7 different NLP datasets and 5 LLMs of varying complexities.
Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods to generate source code summaries are coarse-grained and noise-filled . however, they do not capture contextual code semantics and are often outdated in continuous software iteration.
Approach: They propose a fine-grained Token-level retrieval-augmented mechanism on the decoder side to enhance performance of neural models.
Outcome: The proposed method produces more low-frequency tokens and is interpretable.
Randomized Deep Structured Prediction for Discourse-Level Processing (2021.eacl-main)

Copied to clipboard

Challenge: Expressive text encoders have been at the center of recent NLP work . however, some tasks require complex structural dependencies between texts .
Approach: They propose to leverage deep structured prediction and expressive neural encoders for argumentation mining tasks.
Outcome: The proposed framework can be used for argumentation mining tasks without expensive inference tools.
A Multi-Level Optimization Framework for End-to-End Text Augmentation (2022.tacl-1)

Copied to clipboard

Challenge: Existing methods for text augmentation perform data augmentation and downstream tasks separately.
Approach: They propose a framework to perform text augmentation and the downstream task end-to-end.
Outcome: The proposed framework performs text augmentation and the downstream task end-to-end on a text classification dataset.
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation (2026.acl-long)

Copied to clipboard

Challenge: Existing models rely on a single segmentation token whose hidden state implicitly encodes both semantic reasoning and spatial localization . Existing methods rely only on SEG>, which encodes semantic reasoning, limiting the model's ability to explicitly disentangle what to segment from where to segment.
Approach: They propose a method which reformulates reasoning segmentation as a structured conditional generation process over image tokens conditioned on language grounded query banks.
Outcome: The proposed model bridges token-level predictions and pixel-level supervision by decoupling spatial grounding from semantic reasoning through structured language grounded query banks.
SpanPredict: Extraction of Predictive Document Spans with Neural Attention (2021.naacl-main)

Copied to clipboard

Challenge: identifying predictive text in clinical notes can be as important as the predictions themselves . identifying specific content in clinical note descriptions may illuminate previously unknown risk factors .
Approach: They propose a method for identifying predictive text in clinical notes . they use linear attention to formalize the problem as predictive extraction .
Outcome: The proposed model preserves differentiability and allows scalable inference via stochastic gradient descent.
Span-based Semantic Parsing for Compositional Generalization (2021.acl-long)

Copied to clipboard

Challenge: despite success of sequence-to-sequence models, they fail in compositional generalization . a span-based parser that predicts a utterance over spans improves performance .
Approach: They propose a span-based parser that predicts a utterance over a given span tree . they propose to use CKY to encode how partial programs compose over spans .
Outcome: The proposed model performs better on random splits than baselines that require compositional generalization.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations