English
Related papers

Related papers: Two heads are better than two tapes

200 papers

We show that equivalence of deterministic top-down tree-to-string transducers is decidable, thus solving a long standing open problem in formal language theory. We also present efficient algorithms for subclasses: polynomial time for total…

Formal Languages and Automata Theory · Computer Science 2017-01-30 Helmut Seidl , Sebastian Maneth , Gregor Kemper

This work does not introduce a new method. Instead, we present an interesting finding that questions the necessity of the inductive bias of locality in modern computer vision architectures. Concretely, we find that vanilla Transformers can…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Duy-Kien Nguyen , Mahmoud Assran , Unnat Jain , Martin R. Oswald , Cees G. M. Snoek , Xinlei Chen

Constraint Handling Rules (CHR) is a committed-choice declarative language which has been originally designed for writing constraint solvers and which is nowadays a general purpose language. CHR programs consist of multi-headed guarded…

Logic in Computer Science · Computer Science 2011-01-19 Cinzia Di Giusto , Maurizio Gabbrielli , Maria Chiara Meo

The state of the art in learning meaningful semantic representations of words is the Transformer model and its attention mechanisms. Simply put, the attention mechanisms learn to attend to specific parts of the input dispensing recurrence…

Computation and Language · Computer Science 2020-12-24 Dongsheng Wang , Casper Hansen , Lucas Chaves Lima , Christian Hansen , Maria Maistro , Jakob Grue Simonsen , Christina Lioma

Despite the success of neural machine translation (NMT), simultaneous neural machine translation (SNMT), the task of translating in real time before a full sentence has been observed, remains challenging due to the syntactic structure…

Computation and Language · Computer Science 2020-10-06 Yun Chen , Liangyou Li , Xin Jiang , Xiao Chen , Qun Liu

Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in…

Computation and Language · Computer Science 2023-07-28 Jiaoda Li , Ryan Cotterell , Mrinmaya Sachan

This note is a survey of various results on the capabilities of unique hard attention transformers encoders (UHATs) to recognize formal languages. We distinguish between masked vs. non-masked, finite vs. infinite image and general vs.…

Machine Learning · Computer Science 2025-06-05 Leonid Ryvkin

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2024-05-01 Fabian Gloeckle , Badr Youbi Idrissi , Baptiste Rozière , David Lopez-Paz , Gabriel Synnaeve

The famous problem of Busy Beavers can be stated as the question on how long a $n$-state Turing machine (using a 2-symbol alphabet or -- in a generalization -- a $m$-symbol alphabet) can run if it is started on the blank tape before it…

Formal Languages and Automata Theory · Computer Science 2025-10-21 Christian Hercher

In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target.…

Machine Learning · Computer Science 2024-02-26 Maurice Kraus , Felix Divo , David Steinmann , Devendra Singh Dhami , Kristian Kersting

Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the…

Computation and Language · Computer Science 2021-09-22 Jitao Xu , François Yvon

This paper studies the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. Prior research has found that only a few attention heads are important in each…

Computation and Language · Computer Science 2021-08-20 Weicheng Ma , Kai Zhang , Renze Lou , Lili Wang , Soroush Vosoughi

Working in the multitape Turing model, we show how to reduce the problem of matrix transposition to the problem of integer multiplication. If transposing an $n \times n$ binary matrix requires $\Omega(n^2 \log n)$ steps on a Turing machine,…

Computational Complexity · Computer Science 2025-04-01 David Harvey , Joris van der Hoeven

Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a…

Computation and Language · Computer Science 2019-04-08 Jian Li , Baosong Yang , Zi-Yi Dou , Xing Wang , Michael R. Lyu , Zhaopeng Tu

Functional transductions realized by two-way transducers (equivalently, by streaming transducers and by MSO transductions) are the natural and standard notion of "regular" mappings from words to words. It was shown recently (LICS'13) that…

Formal Languages and Automata Theory · Computer Science 2017-01-11 Félix Baschenis , Olivier Gauwin , Anca Muscholl , Gabriele Puppis

We explore a method for presenting word suggestions for non-visual text input using simultaneous voices. We conduct two perceptual studies and investigate the impact of different presentations of voices on a user's ability to detect which…

Human-Computer Interaction · Computer Science 2025-10-03 Dylan Gaines , Keith Vertanen

Real-world graphs often manifest as a massive temporal stream of edges. The need for real-time analysis of such large graph streams has led to progress on low memory, one-pass streaming graph algorithms. These algorithms were designed for…

Data Structures and Algorithms · Computer Science 2014-10-16 Madhav Jha , C. Seshadhri , Ali Pinar

Sequence-to-sequence learning naturally has two directions. How to effectively utilize supervision signals from both directions? Existing approaches either require two separate models, or a multitask-learned model but with inferior…

Computation and Language · Computer Science 2022-01-25 Zaixiang Zheng , Hao Zhou , Shujian Huang , Jiajun Chen , Jingjing Xu , Lei Li

We show that the equivalence of deterministic linear top-down tree-to-word transducers is decidable in polynomial time. Linear tree-to-word transducers are non-copying but not necessarily order-preserving and can be used to express XML and…

Formal Languages and Automata Theory · Computer Science 2016-06-14 Adrien Boiret , Raphaela Palenta

We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results. Such models were previously used for image generation by progressivly sampling groups…

Image and Video Processing · Electrical Eng. & Systems 2023-04-18 Fabian Mentzer , Eirikur Agustsson , Michael Tschannen