Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCompositional Generalization via Semantic Tagging
التعميم التركيبي عبر العلامات الدلالية
545
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
على الرغم من تطبيق نماذج التسلسل العصبي للتسلسل بنجاح على التحليل الدلالي، إلا أنها تفشل في التعميم التركيبي، أي أنها غير قادرة على التعميم بشكل منهجي لتركيبات غير مرئية من مكونات المشاهدة. بدافع من التحليل الدلالي التقليدي حيث يتم احتساب التركيز بشكل صريح من قبل النحو الرمزي، نقترح إطار فك التشفير الجديد الذي يحافظ على التعبير عن النماذج والعمومية من نماذج التسلسل إلى التسلسل مع تضم محاذاة على غرار المعجم ومعالجة المعلومات المنفذة. على وجه التحديد، نقوم بتحلل فك التشفير في مرحلتين حيث يتم وضع علامة على حامل الإدخال أولا مع رموز الدلالية التي تمثل معنى الكلمات الفردية، ثم يتم استخدام نموذج تسلسل إلى تسلسل للتنبؤ بتصميم تمثيل المعنى النهائي على الكلام والعلامة المتوقعة تسلسل. النتائج التجريبية على ثلاث مجموعات بيانات تحليل الدلالات توضح أن النهج المقترح يحسن باستمرار التعميم التركيبي عبر الهندسة النموذجية والنطاقات والإضفاءات الدلالية.
Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components. Motivated by traditional semantic parsing where compositionality is explicitly accounted for by symbolic grammars, we propose a new decoding framework that preserves the expressivity and generality of sequence-to-sequence models while featuring lexicon-style alignments and disentangled information processing. Specifically, we decompose decoding into two phases where an input utterance is first tagged with semantic symbols representing the meaning of individual words, and then a sequence-to-sequence model is used to predict the final meaning representation conditioning on the utterance and the predicted tag sequence. Experimental results on three semantic parsing datasets show that the proposed approach consistently improves compositional generalization across model architectures, domains, and semantic formalisms.
References used
https://aclanthology.org/
rate research
Read More
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.
Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents. However, the generalization still remains a big challenge as the agents depend critically
on the complexity and variety of training tasks. In this paper, we address this problem by introducing a hierarchical framework built upon the knowledge graph-based RL agent. In the high level, a meta-policy is executed to decompose the whole game into a set of subtasks specified by textual goals, and select one of them based on the KG. Then a sub-policy in the low level is executed to conduct goal-conditioned reinforcement learning. We carry out experiments on games with various difficulty levels and show that the proposed method enjoys favorable generalizability.
Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented with novel
sentences, systematic variation uncovers the limitations in the language-understanding abilities of networks. We demonstrate that these limitations can be overcome by addressing the generalization challenges in the gSCAN dataset, which explicitly measures how well an agent is able to interpret novel linguistic commands grounded in vision, e.g., novel pairings of adjectives and nouns. The key principle we employ is compositionality: that the compositional structure of networks should reflect the compositional structure of the problem domain they address, while allowing other parameters to be learned end-to-end. We build a general-purpose mechanism that enables agents to generalize their language understanding to compositional domains. Crucially, our network has the same state-of-the-art performance as prior work while generalizing its knowledge when prior work does not. Our network also provides a level of interpretability that enables users to inspect what each part of networks learns. Robust grounded language understanding without dramatic failures and without corner cases is critical to building safe and fair robots; we demonstrate the significant role that compositionality can play in achieving that goal.
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training. In spite of significant progress in image captioning with the help of the
autoregressive generation framework, current approaches fail to generalize well to novel concept combinations. We propose a new framework that revolves around probing several similar image caption training instances (retrieval), performing analogical reasoning over relevant entities in retrieved prototypes (analogy), and enhancing the generation process with reasoning outcomes (composition). Our method augments the generation model by referring to the neighboring instances in the training set to produce novel concept combinations in generated captions. We perform experiments on the widely used image captioning benchmarks. The proposed models achieve substantial improvement over the compared baselines on both composition-related evaluation metrics and conventional image captioning metrics.
Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervis
ed SRL training data are not abundant. Cross-lingual learning can improve performance in this setting by transferring knowledge from high-resource languages to low-resource ones. Moreover, we hypothesize that annotations of syntactic dependencies can be leveraged to further facilitate cross-lingual transfer. In this work, we perform an empirical exploration of the helpfulness of syntactic supervision for crosslingual SRL within a simple multitask learning scheme. With comprehensive evaluations across ten languages (in addition to English) and three SRL benchmark datasets, including both dependency- and span-based SRL, we show the effectiveness of syntactic supervision in low-resource scenarios.
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
