English
Related papers

Related papers: Bidirectional Transformer Reranker for Grammatical…

200 papers

Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on…

Computation and Language · Computer Science 2021-06-07 Inigo Jauregi Unanue , Jacob Parnell , Massimo Piccardi

Although deep pre-trained language models have shown promising benefit in a large set of industrial scenarios, including Click-Through-Rate (CTR) prediction, how to integrate pre-trained language models that handle only textual signals into…

Computation and Language · Computer Science 2023-08-23 Dong Wang , Kavé Salamatian , Yunqing Xia , Weiwei Deng , Qi Zhiang

The standard approach to mitigate errors made by an automatic speech recognition system is to use confidence scores associated with each predicted word. In the simplest case, these scores are word posterior probabilities whilst more complex…

Audio and Speech Processing · Electrical Eng. & Systems 2019-02-19 Qiujia Li , Preben Ness , Anton Ragni , Mark Gales

We present a new approach for pretraining a bi-directional transformer model that provides significant performance gains across a variety of language understanding problems. Our model solves a cloze-style word reconstruction task, where…

Computation and Language · Computer Science 2019-03-20 Alexei Baevski , Sergey Edunov , Yinhan Liu , Luke Zettlemoyer , Michael Auli

Robust tensor completion (RTC) aims to recover a low-rank tensor from its incomplete observation with outlier corruption. The recently proposed tensor ring (TR) model has demonstrated superiority in solving the RTC problem. However, the…

Machine Learning · Computer Science 2023-02-16 Zhenhao Huang , Yuning Qiu , Xinqi Chen , Weijun Sun , Guoxu Zhou

Attention-based models have made tremendous progress on end-to-end automatic speech recognition(ASR) recently. However, the conventional transformer-based approaches usually generate the sequence results token by token from left to right,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-12 Xi Chen , Songyang Zhang , Dandan Song , Peng Ouyang , Shouyi Yin

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation…

Computation and Language · Computer Science 2021-09-13 Haoran Xu , Benjamin Van Durme , Kenton Murray

We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To…

Computation and Language · Computer Science 2021-09-17 Liang Ding , Di Wu , Dacheng Tao

Pretrained bidirectional Transformers, such as BERT, have achieved significant improvements in a wide variety of language understanding tasks, while it is not straightforward to directly apply them for natural language generation. In this…

Computation and Language · Computer Science 2021-10-27 Hangbo Bao , Li Dong , Wenhui Wang , Nan Yang , Furu Wei

This thesis addresses automatic lexical error recovery and tokenization of corrupt text input. We propose a technique that can automatically correct misspellings, segmentation errors and real-word errors in a unified framework that uses…

cmp-lg · Computer Science 2009-09-25 Peter Ingels

Unbiased learning to rank (ULTR) aims to mitigate various biases existing in user clicks, such as position bias, trust bias, presentation bias, and learn an effective ranker. In this paper, we introduce our winning approach for the…

Information Retrieval · Computer Science 2023-02-16 Lulu Yu , Yiting Wang , Xiaojie Sun , Keping Bi , Jiafeng Guo

Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream text corpus and fine-tuned on a downstream task becomes a de facto training strategy for several natural language processing (NLP) tasks. Recently, an…

Computation and Language · Computer Science 2021-07-23 Junghoon Lee , Jounghee Kim , Pilsung Kang

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture…

Computation and Language · Computer Science 2020-06-19 Hongchao Fang , Sicheng Wang , Meng Zhou , Jiayuan Ding , Pengtao Xie

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

Machine Learning · Computer Science 2019-12-12 Megha Gupta , Angshul Majumdar

Back-translation (BT) is an effective semi-supervised learning framework in neural machine translation (NMT). A pre-trained NMT model translates monolingual sentences and makes synthetic bilingual sentence pairs for the training of the…

Computation and Language · Computer Science 2024-07-02 DongNyeong Heo , Heeyoul Choi

Language model based pre-trained models such as BERT have provided significant gains across different NLP tasks. In this paper, we study different types of transformer based pre-trained models such as auto-regressive models (GPT-2),…

Computation and Language · Computer Science 2021-02-02 Varun Kumar , Ashutosh Choudhary , Eunah Cho

Language models produce a distribution over the next token; can we use this information to recover the prompt tokens? We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of…

Computation and Language · Computer Science 2023-11-27 John X. Morris , Wenting Zhao , Justin T. Chiu , Vitaly Shmatikov , Alexander M. Rush

In this paper, we propose a bidimensional attention based recursive autoencoder (BattRAE) to integrate clues and sourcetarget interactions at multiple levels of granularity into bilingual phrase representations. We employ recursive…

Computation and Language · Computer Science 2016-11-28 Biao Zhang , Deyi Xiong , Jinsong Su

Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine…

We study sequence-to-sequence (seq2seq) pre-training with data augmentation for sentence rewriting. Instead of training a seq2seq model with gold training data and augmented data simultaneously, we separate them to train in different…

Computation and Language · Computer Science 2019-09-23 Yi Zhang , Tao Ge , Furu Wei , Ming Zhou , Xu Sun