English
Related papers

Related papers: Limited Attention and Discourse Structure

200 papers

Recognizing sarcasm often requires a deep understanding of multiple sources of information, including the utterance, the conversational context, and real world facts. Most of the current sarcasm detection systems consider only the utterance…

Computation and Language · Computer Science 2018-09-11 Reza Ghaeini , Xiaoli Z. Fern , Prasad Tadepalli

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

Computation and Language · Computer Science 2019-06-05 Matthias Sperber , Graham Neubig , Ngoc-Quan Pham , Alex Waibel

Learning high-quality embeddings for rare words is a hard problem because of sparse context information. Mimicking (Pinter et al., 2017) has been proposed as a solution: given embeddings learned by a standard algorithm, a model is first…

Computation and Language · Computer Science 2019-04-08 Timo Schick , Hinrich Schütze

Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention…

Computation and Language · Computer Science 2025-04-25 Yaniv Leviathan , Matan Kalman , Yossi Matias

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking…

Machine Learning · Computer Science 2024-12-12 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

Many state-of-art neural models designed for monotonicity reasoning perform poorly on downward inference. To address this shortcoming, we developed an attentive tree-structured neural network. It consists of a tree-based…

Computation and Language · Computer Science 2021-01-05 Zeming Chen

End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus. However, one of the fatal drawbacks in such approaches is that they are unable to generate…

Computation and Language · Computer Science 2019-03-26 Hao-Tong Ye , Kai-Ling Lo , Shang-Yu Su , Yun-Nung Chen

Attention based Transformer architecture has enabled significant advances in the field of natural language processing. In addition to new pre-training techniques, recent improvements crucially rely on working with a relatively larger…

Machine Learning · Computer Science 2020-02-18 Srinadh Bhojanapalli , Chulhee Yun , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Computation and Language · Computer Science 2025-05-13 Zihan Qiu , Zekun Wang , Bo Zheng , Zeyu Huang , Kaiyue Wen , Songlin Yang , Rui Men , Le Yu , Fei Huang , Suozhi Huang , Dayiheng Liu , Jingren Zhou , Junyang Lin

Cross-attention is a core mechanism in encoder-decoder architectures, widespread in many fields, including speech-to-text (S2T) processing. Its scores have been repurposed for various downstream applications--such as timestamp estimation…

Computation and Language · Computer Science 2025-09-23 Sara Papi , Dennis Fucci , Marco Gaido , Matteo Negri , Luisa Bentivogli

Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for DA…

Computation and Language · Computer Science 2019-10-11 Ruizhe Li , Chenghua Lin , Matthew Collinson , Xiao Li , Guanyi Chen

Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…

Computation and Language · Computer Science 2023-11-10 Sungjin Nam , David Jurgens , Gwen Frishkoff , Kevyn Collins-Thompson

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

Computation and Language · Computer Science 2018-06-19 Matthias Sperber , Jan Niehues , Graham Neubig , Sebastian Stüker , Alex Waibel

An observer wants to understand a decision-maker's welfare from her choice. She believes that decisions are made under limited attention. We argue that the standard model of limited attention cannot help the observer greatly. To address…

Theoretical Economics · Economics 2023-10-16 Mikhail Freer , Hassan Nosratabadi

We propose a simple neural architecture for natural language inference. Our approach uses attention to decompose the problem into subproblems that can be solved separately, thus making it trivially parallelizable. On the Stanford Natural…

Computation and Language · Computer Science 2016-09-27 Ankur P. Parikh , Oscar Täckström , Dipanjan Das , Jakob Uszkoreit

I propose a model for determining the hearer's attentional state which depends solely on a list of salient discourse entities (S-list). The ordering among the elements of the S-list covers also the function of the backward-looking center in…

cmp-lg · Computer Science 2007-05-23 Michael Strube

We propose a general class of language models that treat reference as an explicit stochastic latent variable. This architecture allows models to create mentions of entities and their attributes by accessing external databases (required by,…

Computation and Language · Computer Science 2017-08-10 Zichao Yang , Phil Blunsom , Chris Dyer , Wang Ling

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements of the model capabilities. Yet, a theoretical characterization…

Machine Learning · Computer Science 2025-02-10 Hugo Cui , Freya Behrens , Florent Krzakala , Lenka Zdeborová

Attention-based architectures, in particular transformers, are at the heart of a technological revolution. Interestingly, in addition to helping obtain state-of-the-art results on a wide range of applications, the attention mechanism…

Machine Learning · Statistics 2025-10-22 Gianluigi Lopardo , Frederic Precioso , Damien Garreau

Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data. Specifically, attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper…

Computation and Language · Computer Science 2019-05-07 Harris Partaourides , Kostantinos Papadamou , Nicolas Kourtellis , Ilias Leontiadis , Sotirios Chatzis
‹ Prev 1 4 5 6 7 8 10 Next ›