English
Related papers

Related papers: Backpack Language Models

200 papers

We investigate the behavior of maps learned by machine translation methods. The maps translate words by projecting between word embedding spaces of different languages. We locally approximate these maps using linear maps, and find that they…

Computation and Language · Computer Science 2018-06-19 Ndapa Nakashole , Raphael Flauger

In the last few years, neural networks have been intensively used to develop meaningful distributed representations of words and contexts around them. When these representations, also known as "embeddings", are learned from unsupervised…

Computation and Language · Computer Science 2019-08-07 Giuseppe Marra , Andrea Zugarini , Stefano Melacci , Marco Maggini

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic…

Machine Learning · Computer Science 2019-10-29 Andy Coenen , Emily Reif , Ann Yuan , Been Kim , Adam Pearce , Fernanda Viégas , Martin Wattenberg

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

Style is ubiquitous in our daily language uses, while what is language style to learning machines? In this paper, by exploiting the second-order statistics of semantic vectors of different corpora, we present a novel perspective on this…

Computation and Language · Computer Science 2019-08-19 Ruozi Huang , Mi Zhang , Xudong Pan , Beina Sheng

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…

Computation and Language · Computer Science 2020-10-09 Satwik Bhattamishra , Kabir Ahuja , Navin Goyal

A context-aware language model uses location, user and/or domain metadata (context) to adapt its predictions. In neural language models, context information is typically represented as an embedding and it is given to the RNN as an…

Computation and Language · Computer Science 2018-05-08 Aaron Jaech , Mari Ostendorf

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable.…

Machine Learning · Statistics 2023-11-08 Alberto Bietti , Vivien Cabannes , Diane Bouchacourt , Herve Jegou , Leon Bottou

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

We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are…

Computation and Language · Computer Science 2022-12-07 Laurent Sartran , Samuel Barrett , Adhiguna Kuncoro , Miloš Stanojević , Phil Blunsom , Chris Dyer

In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems, including conversational agents. Our work derives from a…

Computation and Language · Computer Science 2018-08-06 Szymon Malik , Adrian Lancucki , Jan Chorowski

Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…

Computation and Language · Computer Science 2015-04-06 Felix Hill , Kyunghyun Cho , Sebastien Jean , Coline Devin , Yoshua Bengio

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Computation and Language · Computer Science 2025-09-23 Alok N. Shah , Khush Gupta , Keshav Ramji , Pratik Chaudhari

We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…

Computation and Language · Computer Science 2017-06-13 Lifu Tu , Kevin Gimpel , Karen Livescu

Word embeddings are rich word representations, which in combination with deep neural networks, lead to large performance gains for many NLP tasks. However, word embeddings are represented by dense, real-valued vectors and they are therefore…

Computation and Language · Computer Science 2019-12-24 Andreas Hanselowski , Iryna Gurevych

Tokenization and sub-tokenization based models like word2vec, BERT and the GPTs are the state-of-the-art in natural language processing. Typically, these approaches have limitations with respect to their input representation. They fail to…

Computation and Language · Computer Science 2026-02-26 Felix Schneider , Maria Gogolev , Sven Sickert , Joachim Denzler

Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore the morphology of words, by assigning a distinct vector to each…

Computation and Language · Computer Science 2017-06-20 Piotr Bojanowski , Edouard Grave , Armand Joulin , Tomas Mikolov

As the foundation of current natural language processing methods, pre-trained language model has achieved excellent performance. However, the black-box structure of the deep neural network in pre-trained language models seriously limits the…

Computation and Language · Computer Science 2023-06-28 Fanyu Wang , Zhenping Xie

Word embeddings represent words in a numeric space so that semantic relations between words are represented as distances and directions in the vector space. Cross-lingual word embeddings transform vector spaces of different languages so…

Computation and Language · Computer Science 2021-03-25 Marko Robnik-Sikonja , Kristjan Reba , Igor Mozetic