Search Results for author:
Found 22 papers, 15 papers with code
ICT’s System for AutoSimTrans 2021: Robust Char-Level Simultaneous Translation
Aiming at the robustness of ST, we first propose char-level simultaneous translation and applied wait-k policy on it.
Truth-Aware Context Selection: Mitigating the Hallucinations of Large Language Models Being Misled by Untruthful Contexts
Although large language models (LLMs) have demonstrated impressive text generation capabilities, they are easily misled by the untruthful context provided by users or knowledge augmentation tools, thereby producing hallucinations.
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
During inference, by editing LLM's internal representations in truthful space, TruthX effectively enhances the truthfulness of LLMs.
Ranked #2 on
Question Answering
on TruthfulQA
SiLLM: Large Language Models for Simultaneous Machine Translation
We propose SiLLM, which delegates the two sub-tasks to separate agents, thereby incorporating LLM into SiMT.
Unified Segment-to-Segment Framework for Simultaneous Sequence Generation
To accomplish this, Seg2Seg introduces a latent segment as the pivot between source to target and explores all potential source-target mappings via the proposed expectation training, thereby learning the optimal moments for generating.
Non-autoregressive Streaming Transformer for Simultaneous Translation
Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality.
Simultaneous Machine Translation with Tailored Reference
Training the model with ground-truth at low latency may introduce forced anticipations, whereas utilizing reference consistent with the source word order at high latency results in performance degradation.
Glancing Future for Simultaneous Machine Translation
Simultaneous machine translation (SiMT) outputs translation while reading the source sentence.
BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
To minimize human workload, we propose to transfer the capabilities of language generation and instruction following from English to other languages through an interactive translation task.
End-to-End Simultaneous Speech Translation with Differentiable Segmentation
Therefore, learning to segment the speech inputs at those moments that are beneficial for the translation model to produce high-quality translation is the key to SimulST.
Learning Optimal Policy for Simultaneous Machine Translation via Binary Search
Simultaneous machine translation (SiMT) starts to output translation while reading the source sentence and needs a precise policy to decide when to output the generated translation.
Hidden Markov Transformer for Simultaneous Machine Translation
Simultaneous machine translation (SiMT) outputs the target sequence while receiving the source sequence, and hence learning when to start translating each target token is the core challenge for SiMT task.
TriDoNet: A Triple Domain Model-driven Network for CT Metal Artifact Reduction
Recent deep learning-based methods have achieved promising performance for computed tomography metal artifact reduction (CTMAR).
Information-Transport-based Policy for Simultaneous Translation
Simultaneous translation (ST) outputs translation while receiving the source inputs, and hence requires a policy to determine whether to translate a target token or wait for the next source token.
Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation
Compared to the fixed policy, the adaptive policy achieves better latency-quality tradeoffs by adopting a flexible translation policy.
Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation
In this paper, we propose a Wait-info Policy to balance source and target at the information level.
Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework
Simultaneous machine translation (SiMT) starts translating while receiving the streaming source inputs, and hence the source sentence is always incomplete during translating.
Gaussian Multi-head Attention for Simultaneous Machine Translation
For SiMT policy, GMA models the aligned source position of each target word, and accordingly waits until its aligned position to start translating.
Modeling Dual Read/Write Paths for Simultaneous Machine Translation
According to duality constraints, the read/write path in source-to-target and target-to-source SiMT models can be mapped to each other.
Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model
Cross-attention is an important component of neural machine translation (NMT), which is always realized by dot-product attention in previous methods.
Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy
Simultaneous machine translation (SiMT) generates translation before reading the entire source sentence and hence it has to trade off between translation quality and latency.
Future-Guided Incremental Transformer for Simultaneous Translation
Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios.
