Holistic Exploration on Universal Decompositional Semantic Parsing:
Architecture, Data Augmentation, and LLM Paradigm
- URL: http://arxiv.org/abs/2307.13424v1
- Date: Tue, 25 Jul 2023 11:44:28 GMT
- Title: Holistic Exploration on Universal Decompositional Semantic Parsing:
Architecture, Data Augmentation, and LLM Paradigm
- Authors: Hexuan Deng, Xin Zhang, Meishan Zhang, Xuebo Liu, Min Zhang
- Abstract summary: We introduce a cascade model for UDS parsing that decomposes the complex parsing task into semantically appropriate subtasks.
Our approach outperforms the prior models, while significantly reducing inference time.
Different ways for data augmentation are explored, which further improve the UDS Parsing.
- Score: 24.993992573870145
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we conduct a holistic exploration of the Universal
Decompositional Semantic (UDS) Parsing. We first introduce a cascade model for
UDS parsing that decomposes the complex parsing task into semantically
appropriate subtasks. Our approach outperforms the prior models, while
significantly reducing inference time. We also incorporate syntactic
information and further optimized the architecture. Besides, different ways for
data augmentation are explored, which further improve the UDS Parsing. Lastly,
we conduct experiments to investigate the efficacy of ChatGPT in handling the
UDS task, revealing that it excels in attribute parsing but struggles in
relation parsing, and using ChatGPT for data augmentation yields suboptimal
results. Our code is available at https://github.com/hexuandeng/HExp4UDS.
Related papers
- Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls [83.89771461061903]
Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>We identify two key challenges contributing to this inefficiency: $textitover-exploration$ due to redundant states with semantically equivalent content, and $textitunder-exploration$ caused by high variance in verifier scoring.<n>We propose FETCH, a flexible, plug-and-play system compatible with various tree search algorithms.
arXiv Detail & Related papers (2025-02-16T16:12:01Z) - TAIA: Large Language Models are Out-of-Distribution Data Learners [30.57872423927015]
We propose an effective inference-time intervention method: Training All parameters but Inferring with only Attention (trainallInfAttn)
trainallInfAttn achieves superior improvements compared to both the fully fine-tuned model and the base model in most scenarios.
The high tolerance of trainallInfAttn to data mismatches makes it resistant to jailbreaking tuning and enhances specialized tasks using general data.
arXiv Detail & Related papers (2024-05-30T15:57:19Z) - SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation [55.2480439325792]
We study the synthesis of six datasets, covering topic classification, sentiment analysis, tone detection, and humor.
We find that SynthesizRR greatly improves lexical and semantic diversity, similarity to human-written text, and distillation performance.
arXiv Detail & Related papers (2024-05-16T12:22:41Z) - GDA: Generative Data Augmentation Techniques for Relation Extraction
Tasks [81.51314139202152]
We propose a dedicated augmentation technique for relational texts, named GDA, which uses two complementary modules to preserve both semantic consistency and syntax structures.
Experimental results in three datasets under a low-resource setting showed that GDA could bring em 2.0% F1 improvements compared with no augmentation technique.
arXiv Detail & Related papers (2023-05-26T06:21:01Z) - SUBS: Subtree Substitution for Compositional Semantic Parsing [50.63574492655072]
We propose to use subtree substitution for compositional data augmentation, where we consider subtrees with similar semantic functions as exchangeable.
Experiments showed that such augmented data led to significantly better performance on SCAN and GeoQuery, and reached new SOTA on compositional split of GeoQuery.
arXiv Detail & Related papers (2022-05-03T14:47:35Z) - Fine-Grained Scene Graph Generation with Data Transfer [127.17675443137064]
Scene graph generation (SGG) aims to extract (subject, predicate, object) triplets in images.
Recent works have made a steady progress on SGG, and provide useful tools for high-level vision and language understanding.
We propose a novel Internal and External Data Transfer (IETrans) method, which can be applied in a play-and-plug fashion and expanded to large SGG with 1,807 predicate classes.
arXiv Detail & Related papers (2022-03-22T12:26:56Z) - C$^{4}$Net: Contextual Compression and Complementary Combination Network
for Salient Object Detection [0.0]
We show that feature concatenation works better than other combination methods like multiplication or addition.
Also, joint feature learning gives better results, because of the information sharing during their processing.
arXiv Detail & Related papers (2021-10-22T16:14:10Z) - RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing [11.157958012672202]
We are applying retrieval-based modeling ideas to the problem of multi-domain task-oriented semantic parsing.
Our approach, RetroNLU, extends a sequence-to-sequence model architecture with a retrieval component.
We analyze the nearest neighbor retrieval component's quality, model sensitivity and break down the performance for semantic parses of different utterance complexity.
arXiv Detail & Related papers (2021-09-21T19:30:30Z) - Learning to Synthesize Data for Semantic Parsing [57.190817162674875]
We propose a generative model which models the composition of programs and maps a program to an utterance.
Due to the simplicity of PCFG and pre-trained BART, our generative model can be efficiently learned from existing data at hand.
We evaluate our method in both in-domain and out-of-domain settings of text-to-Query parsing on the standard benchmarks of GeoQuery and Spider.
arXiv Detail & Related papers (2021-04-12T21:24:02Z) - DecAug: Augmenting HOI Detection via Decomposition [54.65572599920679]
Current algorithms suffer from insufficient training samples and category imbalance within datasets.
We propose an efficient and effective data augmentation method called DecAug for HOI detection.
Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset.
arXiv Detail & Related papers (2020-10-02T13:59:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.