中文
相关论文

相关论文: Incorporating Structural Alignment Biases into an …

200 篇论文

Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To alleviate these issues, we propose a novel key-value…

计算与语言 · 计算机科学 2018-07-02 Fandong Meng , Zhaopeng Tu , Yong Cheng , Haiyang Wu , Junjie Zhai , Yuekui Yang , Di Wang

Attention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly…

计算与语言 · 计算机科学 2020-04-08 Danish Pruthi , Mansi Gupta , Bhuwan Dhingra , Graham Neubig , Zachary C. Lipton

Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is…

计算与语言 · 计算机科学 2018-10-02 Lesly Miculicich , Dhananjay Ram , Nikolaos Pappas , James Henderson

Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…

计算与语言 · 计算机科学 2015-04-06 Felix Hill , Kyunghyun Cho , Sebastien Jean , Coline Devin , Yoshua Bengio

The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has…

计算与语言 · 计算机科学 2019-03-07 Mathias Müller , Annette Rios , Elena Voita , Rico Sennrich

Context-aware translation can be achieved by processing a concatenation of consecutive sentences with the standard Transformer architecture. This paper investigates the intuitive idea of providing the model with explicit information about…

计算与语言 · 计算机科学 2023-04-06 Lorenzo Lupo , Marco Dinarelli , Laurent Besacier

Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic parsers are trained…

计算与语言 · 计算机科学 2019-09-11 Bailin Wang , Ivan Titov , Mirella Lapata

The dominant neural machine translation models are based on the encoder-decoder structure, and many of them rely on an unconstrained receptive field over source and target sequences. In this paper we study a new architecture that breaks…

计算与语言 · 计算机科学 2019-05-17 José A. R. Fonollosa , Noe Casas , Marta R. Costa-jussà

Previous work on neural noisy channel modeling relied on latent variable models that incrementally process the source and target sentence. This makes decoding decisions based on partial source prefixes even though the full source is…

计算与语言 · 计算机科学 2019-08-19 Kyra Yee , Nathan Ng , Yann N. Dauphin , Michael Auli

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated…

机器学习 · 计算机科学 2021-06-10 Shujian Zhang , Xinjie Fan , Bo Chen , Mingyuan Zhou

Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer…

计算与语言 · 计算机科学 2020-10-16 Zhengxuan Wu , Thanh-Son Nguyen , Desmond C. Ong

Neural machine translation (NMT) systems require large amounts of high quality in-domain parallel corpora for training. State-of-the-art NMT systems still face challenges related to out-of-vocabulary words and dealing with low-resource…

计算与语言 · 计算机科学 2019-09-18 Jetic Gū , Hassan S. Shavarani , Anoop Sarkar

In this paper, we study the problem of enabling neural machine translation (NMT) to reuse previous translations from similar examples in target prediction. Distinguishing reusable translations from noisy segments and learning to reuse them…

计算与语言 · 计算机科学 2019-12-02 Qian Cao , Shaohui Kuang , Deyi Xiong

Modularity is a paradigm of machine translation with the potential of bringing forth models that are large at training time and small during inference. Within this field of study, modular approaches, and in particular attention bridges,…

计算与语言 · 计算机科学 2024-05-01 Timothee Mickus , Raúl Vázquez , Joseph Attieh

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

计算与语言 · 计算机科学 2018-09-06 Ankur Bapna , Mia Xu Chen , Orhan Firat , Yuan Cao , Yonghui Wu

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

计算与语言 · 计算机科学 2021-09-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

Phrases play an important role in natural language understanding and machine translation (Sag et al., 2002; Villavicencio et al., 2005). However, it is difficult to integrate them into current neural machine translation (NMT) which reads…

计算与语言 · 计算机科学 2017-08-08 Xing Wang , Zhaopeng Tu , Deyi Xiong , Min Zhang

In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly…

计算与语言 · 计算机科学 2022-11-08 Javier Ferrando , Gerard I. Gállego , Belen Alastruey , Carlos Escolano , Marta R. Costa-jussà

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent…

计算与语言 · 计算机科学 2022-10-11 Chenze Shao , Yang Feng

We propose a multi-head attention mechanism as a blending layer in a neural network model that translates natural language to a high level behavioral language for indoor robot navigation. We follow the framework established by (Zang et al.,…

机器学习 · 计算机科学 2020-06-09 Patricio Cerda-Mardini , Vladimir Araujo , Alvaro Soto