首页/论文/2006.04232

arXiv 2006.042322020-06-07cs.CLcs.LO

Tensors over Semirings for Latent-Variable Weighted Logic Programs

University of Edinburgh（爱丁堡大学）；University of Rochester（罗切斯特大学）

Esma Balkir, Daniel Gildea, Shay Cohen

备注：: Accepted to IWPT

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Semiring parsing is an elegant framework for describing parsers by using semiring weighted logic programs. In this paper we present a generalization of this concept: latent-variable semiring parsing. With our framework, any semiring weighted logic program can be latentified by transforming weights from scalar values of a semiring to rank-n arrays, or tensors, of semiring values, allowing the modelling of latent variables within the semiring parsing framework. Semiring is too strong a notion when dealing with tensors, and we have to resort to a weaker structure: a partial semiring. We prove that this generalization preserves all the desired properties of the original semiring framework while strictly increasing its expressiveness.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Statistical Machine Translation by Generalized Parsing

Designers of statistical machine translation (SMT) systems have begun to employ tree-structured translation models. Systems involving tree-structured translation models tend to be complex. This article aims to reduce the conceptual complexity of such systems, in order to make them easier to design, implement, debug, use, study, understand, explain, modify, and improve. In service of this goal, the article extends the theory of semiring parsing to arrive at a novel abstract parsing algorithm with five functional parameters: a logic, a grammar, a semiring, a search strategy, and a termination co…

2005-11-24cs.CL

面向大语言模型事件序列解释的隐式逻辑树提取

Latent Logic Tree Extraction for Event Sequence Explanation from LLMs

School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Skywork AI（Skywork AI公司）

本文提出一种基于时间点过程与摊销EM框架的方法，利用LLM先验和GFlowNet从事件序列中高效提取隐式逻辑树解释，并通过在线轻量级模型迭代获取最相关规则，在多个实验中验证了其性能与适应性。

2024-06-28cs.CLcs.LG

LC-ERD：通过一致性调节奖励分解挖掘潜在逻辑以实现自我进化推理

LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition

The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiaotong University（上海交通大学）；Fudan University（复旦大学）

针对大语言模型推理中高质量过程数据稀缺的问题，提出LC-ERD框架，通过潜在逻辑挖掘和一致性调节的奖励分解，实现自我对齐与推理进化。

2026-05-30cs.AIcs.CL

LatentChem: 从文本思维链到化学推理中的潜在思考

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

University of Science and Technology of China（中国科学技术大学）

针对化学大语言模型依赖显式思维链导致的模态不匹配问题，提出LatentChem推理接口，通过连续思维向量和动态感知解耦化学逻辑与语言生成，在ChemCoTBench上以59.88%非平局胜率超越强CoT基线，并实现平均10.84倍推理步骤开销降低（5.96倍实际加速）。

2026-07-23cs.AIcs.CLcs.LG

HE-SNR：通过熵揭示潜在逻辑以指导SWE-bench上的中期训练

HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench

School of Mathematical Sciences, Peking University, Beijing, China（北京大学数学科学学院）；Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（中国科学院计算技术研究所）

针对SWE-bench基准，提出基于熵压缩假说的HE-SNR指标，通过细粒度熵分析指导中期训练数据筛选，在高达560B参数模型上验证有效性。

2026-05-28cs.CLcs.LGcs.SE

使用领域知识通过神经概率软逻辑来引导对话结构归纳

Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic

UC Santa Cruz（加州大学圣克鲁兹分校）；Google Research（谷歌研究院）；Harvard University（哈佛大学）

本文提出神经符号方法NEUPSL DSI，将符号知识注入生成神经模型的潜在空间，以解决对话结构归纳在有限数据和分布偏移下表现不佳的问题，并在多个数据集和设置下实现一致性能提升。

2024-03-26cs.CLcs.LG

更多相关论文收起更多论文

PermaFrost-Attack： stealth pretraining seeding (spS) 用于在LLM训练期间种植逻辑地雷

PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training

Manipal University Jaipur（Manipal大学斋普尔）；NIT, Karnataka（Karnataka理工学院）；Pragya Lab, BITS Pilani Goa, India（BITS Pilani Goa印度普拉吉亚实验室）；Apple, USA（美国苹果公司）；Google, USA（美国谷歌公司）

本文研究了在LLM训练中通过隐蔽预训练播种（SPS）植入逻辑地雷的威胁模型，通过几何诊断方法揭示了潜藏的中毒行为，展示了SPS对基础模型的安全性影响。

2026-10-14cs.AIcs.CLcs.LG

Neural Programmer: Inducing Latent Programs with Gradient Descent

University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Google Brain（谷歌大脑）

Deep neural networks have achieved impressive supervised classification performance in many tasks including image recognition, speech recognition, and sequence to sequence learning. However, this success has not been translated to applications like question answering that may involve complex arithmetic and logic reasoning. A major limitation of these models is in their inability to learn even simple arithmetic and logic operations. For example, it has been shown that neural networks fail to learn to add two binary numbers reliably. In this work, we propose Neural Programmer, an end-to-end diff…

2016-08-04cs.CLcs.LGstat.ML

A Novel Document Generation Process for Topic Detection based on Hierarchical Latent Tree Models

The Hong Kong University of Science and Technology（香港科技大学）

We propose a novel document generation process based on hierarchical latent tree models (HLTMs) learned from data. An HLTM has a layer of observed word variables at the bottom and multiple layers of latent variables on top. For each document, we first sample values for the latent variables layer by layer via logic sampling, then draw relative frequencies for the words conditioned on the values of the latent variables, and finally generate words for the document using the relative word frequencies. The motivation for the work is to take word counts into consideration with HLTMs. In comparison w…

2019-06-28cs.CLcs.IRcs.LG

Generating Contradictory, Neutral, and Entailing Sentences

Université de Montréal（蒙特利尔大学）

Learning distributed sentence representations remains an interesting problem in the field of Natural Language Processing (NLP). We want to learn a model that approximates the conditional latent space over the representations of a logical antecedent of the given statement. In our paper, we propose an approach to generating sentences, conditioned on an input sentence and a logical inference label. We do this by modeling the different possibilities for the output sentence as a distribution over the latent representation, which we train using an adversarial objective. We evaluate the model using t…

2018-03-07cs.AIcs.CL