English
Related papers

Related papers: Language Design as Information Renormalization

200 papers

The springing up of Large Language Models (LLMs) has shifted the community from single-task-orientated natural language processing (NLP) research to a holistic end-to-end multi-task learning paradigm. Along this line of research endeavors…

Computation and Language · Computer Science 2023-10-31 Yuanfeng Song , Yuanqin He , Xuefang Zhao , Hanlin Gu , Di Jiang , Haijun Yang , Lixin Fan , Qiang Yang

We present a setup for training, evaluating and interpreting neural language models, that uses artificial, language-like data. The data is generated using a massive probabilistic grammar (based on state-split PCFGs), that is itself derived…

Computation and Language · Computer Science 2023-10-24 Jaap Jumelet , Willem Zuidema

Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experimental, and computed data, we present an automated method for…

NLP tasks differ in the semantic information they require, and at this time no single se- mantic representation fulfills all requirements. Logic-based representations characterize sentence structure, but do not capture the graded aspect of…

Computation and Language · Computer Science 2016-06-09 I. Beltagy , Stephen Roller , Pengxiang Cheng , Katrin Erk , Raymond J. Mooney

The thesis presents an attempt at using the syntactic structure in natural language for improved language models for speech recognition. The structured language model merges techniques in automatic parsing and language modeling using an…

Computation and Language · Computer Science 2007-05-23 Ciprian Chelba

We first present our work in machine translation, during which we used aligned sentences to train a neural network to embed n-grams of different languages into an $d$-dimensional space, such that n-grams that are the translation of each…

Machine Learning · Computer Science 2011-05-17 Etter Vincent

Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable…

Computation and Language · Computer Science 2026-02-25 Jan Philip Wahle

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Information Theory · Computer Science 2026-01-15 Mete Erdogan , Abhiram Gorle , Shubham Chandak , Mert Pilanci , Tsachy Weissman

The automated construction of coarse-grained models represents a pivotal component in computer simulation of physical systems and is a key enabler in various analysis and design tasks related to uncertainty quantification. Pertinent methods…

Machine Learning · Statistics 2019-09-11 Constantin Grigo , Phaedon-Stelios Koutsourelakis

A challenging task for word embeddings is to capture the emergent meaning or polarity of a combination of individual words. For example, existing approaches in word embeddings will assign high probabilities to the words "Penguin" and "Fly"…

Computation and Language · Computer Science 2018-05-30 Qiuchi Li , Sagar Uprety , Benyou Wang , Dawei Song

Tokenization is a necessary component within the current architecture of many language mod-els, including the transformer-based large language models (LLMs) of Generative AI, yet its impact on the model's cognition is often overlooked. We…

Modern generative machine learning models demonstrate surprising ability to create realistic outputs far beyond their training data, such as photorealistic artwork, accurate protein structures, or conversational text. These successes…

Machine Learning · Computer Science 2024-01-17 William Gilpin

Recurrent neural network grammars (RNNGs) are generative models of (tree,string) pairs that rely on neural networks to evaluate derivational choices. Parsing with them using beam search yields a variety of incremental complexity metrics…

Computation and Language · Computer Science 2018-06-12 John Hale , Chris Dyer , Adhiguna Kuncoro , Jonathan R. Brennan

We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure. We explain efficient inference procedures that allow application to both parsing and language modeling. Experiments show that…

Computation and Language · Computer Science 2016-10-13 Chris Dyer , Adhiguna Kuncoro , Miguel Ballesteros , Noah A. Smith

Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex and often…

A persistent challenge in AI is the effective integration of material and formal inference - the former concerning the plausibility and contextual relevance of arguments, while the latter focusing on their logical and structural validity.…

Artificial Intelligence · Computer Science 2025-04-08 Xin Quan , Marco Valentino , Danilo S. Carvalho , Dhairya Dalal , André Freitas

Sampling-based decoding underlies complex reasoning in large language models (LLMs), where decoding strategies critically shape model behavior. Temperature- and truncation-based methods reshape the next-token distribution through global…

Artificial Intelligence · Computer Science 2026-02-02 Yixin Yang , Qingxiu Dong , Zhifang Sui

We propose a data-driven, coarse-graining formulation in the context of equilibrium statistical mechanics. In contrast to existing techniques which are based on a fine-to-coarse map, we adopt the opposite strategy by prescribing a…

Machine Learning · Statistics 2017-02-01 Markus Schöberl , Nicholas Zabaras , Phaedon-Stelios Koutsourelakis

Natural data is often organized as a hierarchical composition of features. How many samples do generative models need in order to learn the composition rules, so as to produce a combinatorially large number of novel data? What signal in the…

Machine Learning · Statistics 2025-06-05 Alessandro Favero , Antonio Sclocchi , Francesco Cagnetta , Pascal Frossard , Matthieu Wyart

Standard Byte-Pair Encoding (BPE) tokenization compresses text by pairing a learned token vocabulary with a detailed merge list. Recent work has shown that this merge list exposes a potential attack surface for extracting information about…

Computation and Language · Computer Science 2025-08-12 Tomohiro Sawada , Kartik Goyal