Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning compositional structures for semantic graph parsing
تعلم الهياكل التركيبية لتحليل الرسم البياني الدلالي
246
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
AM تحليل التبعية هي طريقة لتحليل الرسم البياني الدلالي العصبي الذي يستغل مبدأ التركيبية.على الرغم من أن محلل التبعية، فقد تبين أن محلل التبعية سريعة ودقيقة عبر العديد من الرسوم البيانية، فإنها تتطلب عبائيات صريحة لهياكل الأشجار التركيبية للتدريب.في الماضي، تم الحصول على هؤلاء استخدام الاستدلال المعقدة من الرسوم المشتركة من قبل الخبراء.هنا نظهر كيف يمكن تدريبهم بدلا من ذلك مباشرة على الرسوم البيانية مع نموذج متغير كامنة عصبي، مما يقلل بشكل كبير من كمية وتعقيد الاستدلال اليدوي.نوضح أن نموذجنا يلتقط العديد من الظواهر اللغوية بمفرده وتحقق دقة مماثلة للتدريب الخاضع للإشراف، مما يسهل بشكل كبير استخدام تحليل التبعية لشبانس جديدة.
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of the compositional tree structures for training. In the past, these were obtained using complex graphbank-specific heuristics written by experts. Here we show how they can instead be trained directly on the graphs with a neural latent-variable model, drastically reducing the amount and complexity of manual heuristics. We demonstrate that our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training, greatly facilitating the use of AM dependency parsing for new sembanks.
References used
https://aclanthology.org/
rate research
Read More
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic
parsing as a dependency parsing task, applying graph-based decoding techniques developed for syntactic parsing. We compare various decoding techniques given the same pre-trained Transformer encoder on the TOP dataset, including settings where training data is limited or contains only partially-annotated examples. We find that our graph-based approach is competitive with sequence decoders on the standard setting, and offers significant improvements in data efficiency and settings where partially-annotated data is available.
Synthesizing data for semantic parsing has gained increasing attention recently. However, most methods require handcrafted (high-precision) rules in their generative process, hindering the exploration of diverse unseen data. In this work, we propose
a generative model which features a (non-neural) PCFG that models the composition of programs (e.g., SQL), and a BART-based translation model that 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. Moreover, explicitly modeling compositions using PCFG leads to better exploration of unseen programs, thus generate more diverse data. We evaluate our method in both in-domain and out-of-domain settings of text-to-SQL parsing on the standard benchmarks of GeoQuery and Spider, respectively. Our empirical results show that the synthesized data generated from our model can substantially help a semantic parser achieve better compositional and domain generalization.
Frame semantic parsing is a semantic analysis task based on FrameNet which has received great attention recently. The task usually involves three subtasks sequentially: (1) target identification, (2) frame classification and (3) semantic role labelin
g. The three subtasks are closely related while previous studies model them individually, which ignores their intern connections and meanwhile induces error propagation problem. In this work, we propose an end-to-end neural model to tackle the task jointly. Concretely, we exploit a graph-based method, regarding frame semantic parsing as a graph construction problem. All predicates and roles are treated as graph nodes, and their relations are taken as graph edges. Experiment results on two benchmark datasets of frame semantic parsing show that our method is highly competitive, resulting in better performance than pipeline models.
Graph-based semantic parsing aims to represent textual meaning through directed graphs. As one of the most promising general-purpose meaning representations, these structures and their parsing have gained a significant interest momentum during recent
years, with several diverse formalisms being proposed. Yet, owing to this very heterogeneity, most of the research effort has focused mainly on solutions specific to a given formalism. In this work, instead, we reframe semantic parsing towards multiple formalisms as Multilingual Neural Machine Translation (MNMT), and propose SGL, a many-to-many seq2seq architecture trained with an MNMT objective. Backed by several experiments, we show that this framework is indeed effective once the learning procedure is enhanced with large parallel corpora coming from Machine Translation: we report competitive performances on AMR and UCCA parsing, especially once paired with pre-trained architectures. Furthermore, we find that models trained under this configuration scale remarkably well to tasks such as cross-lingual AMR parsing: SGL outperforms all its competitors by a large margin without even explicitly seeing non-English to AMR examples at training time and, once these examples are included as well, sets an unprecedented state of the art in this task. We release our code and our models for research purposes at https://github.com/SapienzaNLP/sgl.
We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers. Our approach builds on existing losses that encourage attention maps in neural sequence-to-sequence models to imitate the output of cla
ssical word alignment algorithms. Where past work has used word-level alignments, we focus on spans; borrowing ideas from phrase-based machine translation, we align subtrees in semantic parses to spans of input sentences, and encourage neural attention mechanisms to mimic these alignments. This method improves the performance of transformers, RNNs, and structured decoders on three benchmarks of compositional generalization.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
