English
Related papers

Related papers: Sentence-wise Smooth Regularization for Sequence t…

200 papers

Current large language models (LLMs) primarily utilize next-token prediction method for inference, which significantly impedes their processing speed. In this paper, we introduce a novel inference methodology termed next-sentence…

Artificial Intelligence · Computer Science 2024-08-15 Hongjun An , Yifan Chen , Zhe Sun , Xuelong Li

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…

Machine Learning · Computer Science 2022-10-26 Dongkyu Lee , Ka Chun Cheung , Nevin L. Zhang

Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…

Computation and Language · Computer Science 2022-08-31 Taehee Kim , ChaeHun Park , Jimin Hong , Radhika Dua , Edward Choi , Jaegul Choo

Maximum regularized likelihood estimators (MRLEs) are arguably the most established class of estimators in high-dimensional statistics. In this paper, we derive guarantees for MRLEs in Kullback-Leibler divergence, a general measure of…

Machine Learning · Statistics 2018-10-18 Rui Zhuang , Johannes Lederer

We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning…

Computation and Language · Computer Science 2017-10-03 Preslav Nakov , Stephan Vogel

With the widespread application of Large Language Models (LLMs) in the field of Natural Language Processing (NLP), enhancing their performance has become a research hotspot. This paper presents a novel multi-prompt ensemble decoding…

Computation and Language · Computer Science 2024-12-25 Jiaxin Guo , Daimeng Wei , Yuanchang Luo , Shimin Tao , Hengchao Shang , Zongyao Li , Shaojun Li , Jinlong Yang , Zhanglin Wu , Zhiqiang Rao , Hao Yang

Modelling statistical relationships beyond the conditional mean is crucial in many settings. Conditional density estimation (CDE) aims to learn the full conditional probability density from data. Though highly expressive, neural network…

Machine Learning · Statistics 2020-02-17 Jonas Rothfuss , Fabio Ferreira , Simon Boehm , Simon Walther , Maxim Ulrich , Tamim Asfour , Andreas Krause

We simplify sentences with an attentive neural network sequence to sequence model, dubbed S4. The model includes a novel word-copy mechanism and loss function to exploit linguistic similarities between the original and simplified sentences.…

Computation and Language · Computer Science 2018-05-16 Alexander Mathews , Lexing Xie , Xuming He

Current benchmark tasks for natural language processing contain text that is qualitatively different from the text used in informal day to day digital communication. This discrepancy has led to severe performance degradation of…

Computation and Language · Computer Science 2021-10-13 Ana-Maria Bucur , Adrian Cosma , Liviu P. Dinu

We present an adaptation of RNN sequence models to the problem of multi-label classification for text, where the target is a set of labels, not a sequence. Previous such RNN models define probabilities for sequences but not for sets;…

Computation and Language · Computer Science 2019-04-12 Kechen Qin , Cheng Li , Virgil Pavlu , Javed A. Aslam

Processing of multi-word expressions (MWEs) is a known problem for any natural language processing task. Even neural machine translation (NMT) struggles to overcome it. This paper presents results of experiments on investigating NMT…

Computation and Language · Computer Science 2019-05-07 Matīss Rikters , Ondřej Bojar

Sequence-to-sequence models are a powerful workhorse of NLP. Most variants employ a softmax transformation in both their attention mechanism and output layer, leading to dense alignments and strictly positive output probabilities. This…

Computation and Language · Computer Science 2019-06-14 Ben Peters , Vlad Niculae , André F. T. Martins

Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks. With only a few demonstration examples, these LLMs can quickly adapt to target tasks without expensive gradient updates. Common…

Computation and Language · Computer Science 2023-11-14 Yue Yu , Jiaming Shen , Tianqi Liu , Zhen Qin , Jing Nathan Yan , Jialu Liu , Chao Zhang , Michael Bendersky

Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results when predicting the overall quality of translated sentences. Predicting translation errors, i.e. detecting…

Computation and Language · Computer Science 2021-08-30 Marina Fomicheva , Lucia Specia , Nikolaos Aletras

Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by…

Computation and Language · Computer Science 2020-02-26 Wenxuan Zhou , Junyi Du , Xiang Ren

Prior research has demonstrated noticeable performance gains through the use of probabilistic tokenizations, an approach that involves employing multiple tokenizations of the same input string during the training phase of a language model.…

Computation and Language · Computer Science 2024-07-08 Ashutosh Sathe , Divyanshu Aggarwal , Sunayana Sitaram

Mixture of Experts (MoE) are successful models for modeling heterogeneous data in many statistical learning problems including regression, clustering and classification. Generally fitted by maximum likelihood estimation via the well-known…

Machine Learning · Statistics 2018-10-30 Faicel Chamroukhi , Bao-Tuyen Huynh

Tokenising continuous speech into sequences of discrete tokens and modelling them with language models (LMs) has led to significant success in text-to-speech (TTS) synthesis. Although these models can generate speech with high quality and…

Sound · Computer Science 2024-08-30 Zehai Tu , Guangyan Zhang , Yiting Lu , Adaeze Adigwe , Simon King , Yiwen Guo

Maximum likelihood estimation problems are, in general, intractable optimization problems. As a result, it is common to approximate the maximum likelihood estimator (MLE) using convex relaxations. In some cases, the relaxation is tight: it…

Optimization and Control · Mathematics 2016-08-15 Afonso S. Bandeira , Nicolas Boumal , Amit Singer

Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair…

Computation and Language · Computer Science 2021-10-20 HyoJung Han , Seokchan Ahn , Yoonjung Choi , Insoo Chung , Sangha Kim , Kyunghyun Cho