中文
相关论文

相关论文: Coloring the Blank Slate: Pre-training Imparts a H…

200 篇论文

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

计算与语言 · 计算机科学 2023-06-01 Aaron Mueller , Tal Linzen

Sequence-to-sequence (seq2seq) models have been successful across many NLP tasks, including ones that require predicting linguistic structure. However, recent work on compositional generalization has shown that seq2seq models achieve very…

计算与语言 · 计算机科学 2022-10-25 Yuekun Yao , Alexander Koller

Transformers trained on natural language data have been shown to learn its hierarchical structure and generalize to sentences with unseen syntactic structures without explicitly encoding any structural bias. In this work, we investigate…

计算与语言 · 计算机科学 2025-03-18 Kabir Ahuja , Vidhisha Balachandran , Madhur Panwar , Tianxing He , Noah A. Smith , Navin Goyal , Yulia Tsvetkov

In recent years, significant advancements in pre-trained language models have driven the creation of numerous non-English language variants, with a particular emphasis on encoder-only and decoder-only architectures. While Spanish language…

计算与语言 · 计算机科学 2024-03-22 Vladimir Araujo , Maria Mihaela Trusca , Rodrigo Tufiño , Marie-Francine Moens

Sequence-to-sequence (seq2seq) models are prevalent in semantic parsing, but have been found to struggle at out-of-distribution compositional generalization. While specialized model architectures and pre-training of seq2seq models have been…

计算与语言 · 计算机科学 2021-04-16 Jonathan Herzig , Peter Shaw , Ming-Wei Chang , Kelvin Guu , Panupong Pasupat , Yuan Zhang

Natural language exhibits patterns of hierarchically governed dependencies, in which relations between words are sensitive to syntactic structure rather than linear ordering. While re-current network models often fail to generalize in a…

计算与语言 · 计算机科学 2021-09-27 Jackson Petty , Robert Frank

Pre-trained language models have recently emerged as a powerful tool for fine-tuning a variety of language tasks. Ideally, when models are pre-trained on large amount of data, they are expected to gain implicit knowledge. In this paper, we…

计算与语言 · 计算机科学 2023-06-22 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kühnberger

Learners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise from any aspect of the model architecture. We investigate…

计算与语言 · 计算机科学 2020-01-14 R. Thomas McCoy , Robert Frank , Tal Linzen

Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are highly versatile and powerful, they can still benefit from…

计算与语言 · 计算机科学 2024-07-08 Matthias Lindemann , Alexander Koller , Ivan Titov

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce…

计算与语言 · 计算机科学 2020-10-13 Ethan Wilcox , Peng Qian , Richard Futrell , Ryosuke Kohita , Roger Levy , Miguel Ballesteros

Seq2Seq based neural architectures have become the go-to architecture to apply to sequence to sequence language tasks. Despite their excellent performance on these tasks, recent work has noted that these models usually do not fully capture…

计算与语言 · 计算机科学 2018-05-10 Noah Weber , Leena Shekhar , Niranjan Balasubramanian

For multilingual sequence-to-sequence pretrained language models (multilingual Seq2Seq PLMs), e.g. mBART, the self-supervised pretraining task is trained on a wide range of monolingual languages, e.g. 25 languages from CommonCrawl, while…

计算与语言 · 计算机科学 2022-09-22 Changtong Zan , Liang Ding , Li Shen , Yu Cao , Weifeng Liu , Dacheng Tao

Despite success in many domains, neural models struggle in settings where train and test examples are drawn from different distributions. In particular, in contrast to humans, conventional sequence-to-sequence (seq2seq) models fail to…

计算与语言 · 计算机科学 2021-10-28 Bailin Wang , Mirella Lapata , Ivan Titov

We describe a neural transducer that maintains the flexibility of standard sequence-to-sequence (seq2seq) models while incorporating hierarchical phrases as a source of inductive bias during training and as explicit constraints during…

计算与语言 · 计算机科学 2022-11-17 Bailin Wang , Ivan Titov , Jacob Andreas , Yoon Kim

This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights…

计算与语言 · 计算机科学 2018-02-23 Prajit Ramachandran , Peter J. Liu , Quoc V. Le

In the last half-decade, the field of natural language processing (NLP) has undergone two major transitions: the switch to neural networks as the primary modeling paradigm and the homogenization of the training regime (pre-train, then…

计算与语言 · 计算机科学 2021-10-19 Artur Kulmizev , Joakim Nivre

Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…

计算与语言 · 计算机科学 2020-11-10 Çağla Aksoy , Alper Ahmetoğlu , Tunga Güngör

Sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining language models. However, the prior seq2seq pretraining models generally focus on reconstructive objectives on the decoder side and neglect the effect…

计算与语言 · 计算机科学 2024-01-10 Qihuang Zhong , Liang Ding , Juhua Liu , Bo Du , Dacheng Tao

Pre-trained language models (e.g. BART) have shown impressive results when fine-tuned on large summarization datasets. However, little is understood about this fine-tuning process, including what knowledge is retained from pre-training time…

计算与语言 · 计算机科学 2022-03-16 Tanya Goyal , Jiacheng Xu , Junyi Jessy Li , Greg Durrett

While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic…

计算与语言 · 计算机科学 2020-05-26 Jennifer Hu , Jon Gauthier , Peng Qian , Ethan Wilcox , Roger P. Levy
‹ 上一页 1 2 3 10 下一页 ›