English
Related papers

Related papers: On Support Samples of Next Word Prediction

200 papers

Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the…

Computation and Language · Computer Science 2018-10-23 Mahnaz Koupaee , William Yang Wang

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…

Computation and Language · Computer Science 2021-09-03 Chantal Amrhein , Rico Sennrich

Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study…

Computation and Language · Computer Science 2026-02-17 Jan Philip Wahle , Terry Ruas , Yang Xu , Bela Gipp

Progress in text understanding has been driven by large datasets that test particular capabilities, like recent datasets for reading comprehension (Hermann et al., 2015). We focus here on the LAMBADA dataset (Paperno et al., 2016), a word…

Computation and Language · Computer Science 2017-02-20 Zewei Chu , Hai Wang , Kevin Gimpel , David McAllester

Many methods now exist for conditioning model outputs on task instructions, retrieved documents, and user-provided explanations and feedback. Rather than relying solely on examples of task inputs and outputs, these approaches use valuable…

Computation and Language · Computer Science 2021-02-12 Peter Hase , Mohit Bansal

Infants, adults, non-human primates and non-primates all learn patterns implicitly, and they do so across modalities. The biological evidence supports the hypothesis that the mechanism for this learning is general but computationally local.…

Neurons and Cognition · Quantitative Biology 2021-08-16 John Rohrlich , Randall C. O'Reilly

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on…

Computation and Language · Computer Science 2026-04-21 Jonathan Kamp , Roos Bakker , Dominique Blok

Distributed word representations have been demonstrated to be effective in capturing semantic and syntactic regularities. Unsupervised representation learning from large unlabeled corpora can learn similar representations for those words…

Computation and Language · Computer Science 2015-12-01 Chunting Zhou , Chonglin Sun , Zhiyuan Liu , Francis C. M. Lau

We show that a language model's ability to predict text is tightly linked to the breadth of its embedding space: models that spread their contextual representations more widely tend to achieve lower perplexity. Concretely, we find that…

Computation and Language · Computer Science 2026-04-21 Yanhong Li , Ming Li , Karen Livescu , Jiawei Zhou

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner

Spoken communication occurs in a "noisy channel" characterized by high levels of environmental noise, variability within and between speakers, and lexical and syntactic ambiguity. Given these properties of the received linguistic input,…

Computation and Language · Computer Science 2021-01-26 Stephan C. Meylan , Sathvik Nair , Thomas L. Griffiths

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Computation and Language · Computer Science 2020-11-20 John Wieting , Graham Neubig , Taylor Berg-Kirkpatrick

Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events. While distributional models -- most recently pre-trained, Transformer language models -- have demonstrated…

Computation and Language · Computer Science 2021-04-22 Ian Porada , Kaheer Suleman , Adam Trischler , Jackie Chi Kit Cheung

Despite their success in a variety of NLP tasks, pre-trained language models, due to their heavy reliance on compositionality, fail in effectively capturing the meanings of multiword expressions (MWEs), especially idioms. Therefore,…

Computation and Language · Computer Science 2021-09-10 Harish Tayyar Madabushi , Edward Gow-Smith , Carolina Scarton , Aline Villavicencio

Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In…

Computation and Language · Computer Science 2019-10-08 Sebastian Ruder , Ivan Vulić , Anders Søgaard

We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifically, we train a Transformer model on a synthetic corpus of…

Machine Learning · Computer Science 2024-08-06 Charles Jin , Martin Rinard

Do large language models (LLMs) anticipate when they will answer correctly? To study this, we extract activations after a question is read but before any tokens are generated, and train linear probes to predict whether the model's…

Associative learning--forming links between co-occurring items--is fundamental to human cognition, reshaping internal representations in complex ways. Testing hypotheses on how representational changes occur in biological systems is…

Machine Learning · Computer Science 2025-10-27 Camila Kolling , Vy Ai Vo , Mariya Toneva

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

Computation and Language · Computer Science 2019-09-11 Lyan Verwimp , Jerome R. Bellegarda

A statistical model for segmentation and word discovery in continuous speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described. Results of empirical tests showing that the…

Computation and Language · Computer Science 2007-05-23 Anand Venkataraman