中文
相关论文

相关论文: EDITOR: an Edit-Based Transformer with Repositioni…

200 篇论文

Semantic parsing is the problem of deriving machine interpretable meaning representations from natural language utterances. Neural models with encoder-decoder architectures have recently achieved substantial improvements over traditional…

计算与语言 · 计算机科学 2019-09-30 Huseyin A. Inan , Gaurav Singh Tomar , Huapu Pan

We propose an interactive-predictive neural machine translation framework for easier model personalization using reinforcement and imitation learning. During the interactive translation process, the user is asked for feedback on uncertain…

计算与语言 · 计算机科学 2019-07-08 Tsz Kin Lam , Shigehiko Schamoni , Stefan Riezler

Neural language models (LMs) have been extensively trained on vast corpora to store factual knowledge about various aspects of the world described in texts. Current technologies typically employ knowledge editing methods or specific prompts…

计算与语言 · 计算机科学 2024-05-14 Yuchen Cai , Ding Cao , Rongxi Guo , Yaqin Wen , Guiquan Liu , Enhong Chen

Spaced repetition systems are fundamental to efficient learning and memory retention, but existing algorithms often struggle with semantic interference and personalized adaptation. We present LECTOR (\textbf{L}LM-\textbf{E}nhanced…

计算与语言 · 计算机科学 2025-08-06 Jiahao Zhao

Lexically constrained decoding for machine translation has shown to be beneficial in previous studies. Unfortunately, constraints provided by users may contain mistakes in real-world situations. It is still an open question that how to…

计算与语言 · 计算机科学 2021-01-27 Huayang Li , Guoping Huang , Deng Cai , Lemao Liu

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

计算与语言 · 计算机科学 2019-04-08 Jie Hao , Xing Wang , Baosong Yang , Longyue Wang , Jinfeng Zhang , Zhaopeng Tu

Numerical reasoning over text is a challenging task of Artificial Intelligence (AI), requiring reading comprehension and numerical reasoning abilities. Previous approaches use numerical reasoning programs to represent the reasoning process.…

人工智能 · 计算机科学 2022-10-21 Jiaxin Zhang , Yashar Moshfeghi

We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained to perform decoding in an iterative manner, a Levenshtein…

计算与语言 · 计算机科学 2021-09-17 Shuoyang Ding , Marcin Junczys-Dowmunt , Matt Post , Philipp Koehn

Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effectiveness of existing…

计算与语言 · 计算机科学 2025-02-05 Daniel Tamayo , Aitor Gonzalez-Agirre , Javier Hernando , Marta Villegas

Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they…

计算与语言 · 计算机科学 2021-09-16 Josef Jon , João Paulo Aires , Dušan Variš , Ondřej Bojar

Existing sentence ordering approaches generally employ encoder-decoder frameworks with the pointer net to recover the coherence by recurrently predicting each sentence step-by-step. Such an autoregressive manner only leverages unilateral…

计算与语言 · 计算机科学 2023-10-20 Yi Bin , Wenhao Shi , Bin Ji , Jipeng Zhang , Yujuan Ding , Yang Yang

Recent advances in large language models (LLMs) have made it increasingly difficult to distinguish human-written text from AI-generated content. Many existing detectors train supervised neural classifiers that achieve strong in-distribution…

计算与语言 · 计算机科学 2026-05-27 Pingfan Su , Kai Ye , Shijin Gong , Erhan Xu , Jin Zhu , Giulia Livieri , Chengchun Shi

While a considerable amount of semantic parsing approaches have employed RNN architectures for code generation tasks, there have been only few attempts to investigate the applicability of Transformers for this task. Including hierarchical…

计算与语言 · 计算机科学 2022-06-28 Klaudia-Doris Thellmann , Bernhard Stadler , Ricardo Usbeck , Jens Lehmann

The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and…

计算与语言 · 计算机科学 2019-07-01 Denis Emelin , Ivan Titov , Rico Sennrich

This paper targets interactive object-level editing (e.g., deletion, recoloring, transformation, composition) in dynamic scenes. Recently, some methods aiming for flexible editing static scenes represented by neural radiance field (NeRF)…

计算机视觉与模式识别 · 计算机科学 2023-11-08 Dadong Jiang , Zhihui Ke , Xiaobo Zhou , Xidong Shi

In the rapidly evolving field of deep learning, the demand for models that are both expressive and computationally efficient has never been more critical. This paper introduces Orchid, a novel architecture designed to address the quadratic…

机器学习 · 计算机科学 2026-01-01 Mahdi Karami , Ali Ghodsi

Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption. However, all existing caption editing works are implicit models, ie, they directly produce the…

计算机视觉与模式识别 · 计算机科学 2022-07-21 Zhen Wang , Long Chen , Wenbo Ma , Guangxing Han , Yulei Niu , Jian Shao , Jun Xiao

We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the…

机器学习 · 计算机科学 2024-10-31 Mingze Wang , Weinan E

Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue that common seq2seq models (with a facility to copy single…

机器学习 · 计算机科学 2020-12-15 Sheena Panthaplackel , Miltiadis Allamanis , Marc Brockschmidt

We introduce NSEdit (neural-symbolic edit), a novel Transformer-based code repair method. Given only the source code that contains bugs, NSEdit predicts an editing sequence that can fix the bugs. The edit grammar is formulated as a regular…

机器学习 · 计算机科学 2022-04-19 Yaojie Hu , Xingjian Shi , Qiang Zhou , Lee Pike