English
Related papers

Related papers: Investigating semantic subspaces of Transformer se…

200 papers

We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…

Computation and Language · Computer Science 2022-06-30 Arabella Sinclair , Jaap Jumelet , Willem Zuidema , Raquel Fernández

We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…

Computation and Language · Computer Science 2014-04-21 Karl Moritz Hermann , Phil Blunsom

The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…

Computation and Language · Computer Science 2025-03-31 Zhuo-Yang Song , Zeyu Li , Qing-Hong Cao , Ming-xing Luo , Hua Xing Zhu

We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM encoder-decoder model that…

Computation and Language · Computer Science 2021-10-22 Takashi Wada , Tomoharu Iwata , Yuji Matsumoto , Timothy Baldwin , Jey Han Lau

The goal of this paper is to learn more about how idiomatic information is structurally encoded in embeddings, using a structural probing method. We repurpose an existing English verbal multi-word expression (MWE) dataset to suit the…

Computation and Language · Computer Science 2023-04-28 Filip Klubička , Vasudevan Nedumpozhimana , John D. Kelleher

Lexico-semantic networks represent words as nodes and their semantic relatedness as edges. While such networks are traditionally constructed using embeddings from encoder-based models or static vectors, embeddings from decoder-only large…

Computation and Language · Computer Science 2025-05-20 Zhu Liu , Ying Liu , KangYang Luo , Cunliang Kong , Maosong Sun

Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…

Computation and Language · Computer Science 2025-10-14 Hyeonbin Hwang , Byeongguk Jeon , Seungone Kim , Jiyeon Kim , Hoyeon Chang , Sohee Yang , Seungpil Won , Dohaeng Lee , Youbin Ahn , Minjoon Seo

In this work, we leverage the linear algebraic structure of distributed word representations to automatically extend knowledge bases and allow a machine to learn new facts about the world. Our goal is to extract structured facts from…

Computation and Language · Computer Science 2015-11-24 Lisa Seung-Yeon Lee

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

Computation and Language · Computer Science 2022-02-21 Thomas Roland Barillot , Jacob Saks , Polena Lilyanova , Edward Torgas , Yachen Hu , Yuanqing Liu , Varun Balupuri , Paul Gaskell

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models…

Computation and Language · Computer Science 2024-06-11 Zhu Liu , Cunliang Kong , Ying Liu , Maosong Sun

Understanding how information propagates through Transformer models is a key challenge for interpretability. In this work, we study the effects of minimal token perturbations on the embedding space. In our experiments, we analyze the…

Machine Learning · Computer Science 2025-06-24 Eddie Conti , Alejandro Astruc , Alvaro Parafita , Axel Brando

Distributed word embeddings have yielded state-of-the-art performance in many NLP tasks, mainly due to their success in capturing useful semantic information. These representations assign only a single vector to each word whereas a large…

Machine Learning · Computer Science 2020-02-04 Shobhit Jain , Sravan Babu Bodapati , Ramesh Nallapati , Anima Anandkumar

Multilingual sentence encoders have seen much success in cross-lingual model transfer for downstream NLP tasks. Yet, we know relatively little about the properties of individual languages or the general patterns of linguistic variation that…

Computation and Language · Computer Science 2020-09-29 Rochelle Choenni , Ekaterina Shutova

Large language models use high-dimensional latent spaces to encode and process textual information. Much work has investigated how the conceptual content of words translates into geometrical relationships between their vector…

Computation and Language · Computer Science 2025-05-26 Raphaël Sarfati , Haley Moller , Toni J. B. Liu , Nicolas Boullé , Christopher Earls

Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream…

Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus on input-oriented feature extraction, such as supervised…

Computation and Language · Computer Science 2025-12-03 Marco Bronzini , Carlo Nicolini , Bruno Lepri , Jacopo Staiano , Andrea Passerini

While the successes of transformers across many domains are indisputable, accurate understanding of the learning mechanics is still largely lacking. Their capabilities have been probed on benchmarks which include a variety of structured and…

Machine Learning · Computer Science 2023-07-25 Yuchen Li , Yuanzhi Li , Andrej Risteski

The success of pretrained contextual encoders, such as ELMo and BERT, has brought a great deal of interest in what these models learn: do they, without explicit supervision, learn to encode meaningful notions of linguistic structure? If so,…

Computation and Language · Computer Science 2020-10-12 Julian Michael , Jan A. Botha , Ian Tenney

Sentence embeddings induced with various transformer architectures encode much semantic and syntactic information in a distributed manner in a one-dimensional array. We investigate whether specific grammatical information can be accessed in…

Computation and Language · Computer Science 2023-12-18 Vivi Nastase , Paola Merlo

Large language models (LLMs) take sequences of subwords as input, requiring them to effective compose subword representations into meaningful word-level representations. In this paper, we present a comprehensive set of experiments to probe…

Computation and Language · Computer Science 2025-08-26 Qiwei Peng , Yekun Chai , Anders Søgaard
‹ Prev 1 4 5 6 7 8 10 Next ›