research
∙
08/12/2023
GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
Safety lies at the core of the development of Large Language Models (LLM...
share
research
∙
08/07/2023
Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench
Recently, the community has witnessed the advancement of Large Language ...
research
∙
07/16/2023
Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Modeling discourse – the linguistic phenomena that go beyond individual ...
research
∙
07/06/2023
On the Cultural Gap in Text-to-Image Generation
One challenge in text-to-image (T2I) generation is the inadvertent refle...
research
∙
06/15/2023
Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration
Although instruction-tuned large language models (LLMs) have exhibited r...
research
∙
05/25/2023
Revisiting Non-Autoregressive Translation at Scale
In real-world systems, scaling has been critical for improving the trans...
research
∙
05/18/2023
Cross-modality Data Augmentation for End-to-End Sign Language Translation
End-to-end sign language translation (SLT) aims to convert sign language...
research
∙
05/17/2023
A Survey on Zero Pronoun Translation
Zero pronouns (ZPs) are frequently omitted in pro-drop languages (e.g. C...
research
∙
04/05/2023
ParroT: Translating During Chat Using Large Language Models
Large language models (LLMs) like ChatGPT and GPT-4 have exhibited remar...
research
∙
04/05/2023
Document-Level Machine Translation with Large Language Models
Large language models (LLMs) such as Chat-GPT can produce coherent, cohe...
research
∙
02/16/2023
Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production
Knowledge-aided dialogue response generation aims at augmenting chatbots...
research
∙
01/20/2023
Is ChatGPT A Good Translator? A Preliminary Study
This report provides a preliminary evaluation of ChatGPT for machine tra...
research
∙
10/24/2022
Adapters for Enhanced Modeling of Multilingual Knowledge and Text
Large language models appear to learn facts from the large text corpora ...
research
∙
10/13/2022
Scaling Back-Translation with Domain Text Generation for Sign Language Gloss Translation
Sign language gloss translation aims to translate the sign glosses into ...
research
∙
10/08/2022
ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
Recently, a new training oaxe loss has proven effective to ameliorate th...
research
∙
05/20/2022
Understanding and Mitigating the Uncertainty in Zero-Shot Translation
Zero-shot translation is a promising direction for building a comprehens...
research
∙
03/16/2022
Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation
In this paper, we present a substantial step in better understanding the...
research
∙
10/05/2021
On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation
Pre-training (PT) and back-translation (BT) are two simple and powerful ...
research
∙
07/17/2021
On the Copying Behaviors of Pre-Training for Neural Machine Translation
Previous studies have shown that initializing neural machine translation...
research
∙
06/10/2021
Progressive Multi-Granularity Training for Non-Autoregressive Translation
Non-autoregressive translation (NAT) significantly accelerates the infer...
research
∙
06/09/2021
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
We propose a new training objective named order-agnostic cross entropy (...
research
∙
06/02/2021
Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation
Self-training has proven effective for improving NMT performance by augm...
research
∙
06/02/2021
Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation
Knowledge distillation (KD) is commonly used to construct synthetic data...
research
∙
05/27/2021
TranSmart: A Practical Interactive Machine Translation System
Automatic machine translation is super efficient to produce translations...
research
∙
12/29/2020
Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning
Encoder layer fusion (EncoderFusion) is a technique to fuse all the enco...
research
∙
12/29/2020
Understanding and Improving Lexical Choice in Non-Autoregressive Translation
Knowledge distillation (KD) is essential for training non-autoregressive...
research
∙
12/29/2020
Robust Dialogue Utterance Rewriting as Sequence Tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue u...
research
∙
11/07/2020
Rethinking the Value of Transformer Components
Transformer becomes the state-of-the-art translation model, while it is ...
research
∙
11/02/2020
Context-Aware Cross-Attention for Non-Autoregressive Translation
Non-autoregressive translation (NAT) significantly accelerates the infer...
research
∙
10/24/2020
Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation
Non-Autoregressive machine Translation (NAT) models have demonstrated si...
research
∙
10/06/2020
On the Sub-Layer Functionalities of Transformer Decoder
There have been significant efforts to interpret the encoder of Transfor...
research
∙
10/06/2020
On the Sparsity of Neural Machine Translation Models
Modern neural machine translation (NMT) models employ a large number of ...
research
∙
10/06/2020
Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation
Large-scale training datasets lie at the core of the recent success of n...
research
∙
05/03/2020
How Does Selective Mechanism Improve Self-Attention Networks?
Self-attention networks (SANs) with selective mechanism has produced sub...
research
∙
05/03/2020
On the Inference Calibration of Neural Machine Translation
Confidence calibration, which aims to make model predictions equal to th...
research
∙
04/28/2020
Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models
Machine translation (MT) systems translate text between different langua...
research
∙
11/22/2019
Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks
The key challenge of multi-domain translation lies in simultaneously enc...
research
∙
11/22/2019
Neuron Interaction Based Representation Composition for Neural Machine Translation
Recent NLP studies reveal that substantial linguistic information can be...
research
∙
11/20/2019
EmpGAN: Multi-resolution Interactive Empathetic Dialogue Generation
Conventional emotional dialogue system focuses on generating emotion-ric...
research
∙
09/05/2019
Multi-Granularity Self-Attention for Neural Machine Translation
Current state-of-the-art neural machine translation (NMT) uses a deep mu...
research
∙
09/04/2019
Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons
Recent studies have shown that a hybrid of self-attention networks (SANs...
research
∙
09/01/2019
Self-Attention with Structural Position Representations
Although self-attention networks (SANs) have advanced the state-of-the-a...
research
∙
09/01/2019
One Model to Learn Both: Zero Pronoun Prediction and Translation
Zero pronouns (ZPs) are frequently omitted in pro-drop languages, but sh...
research
∙
09/01/2019
Towards Understanding Neural Machine Translation with Word Importance
Although neural machine translation (NMT) has advanced the state-of-the-...
research
∙
06/04/2019
Exploiting Sentential Context for Neural Machine Translation
In this work, we present novel approaches to exploit sentential context ...
research
∙
06/03/2019
Assessing the Ability of Self-Attention Networks to Learn Word Order
Self-attention networks (SAN) have attracted a lot of interests due to t...
research
∙
04/21/2019
Dynamic Past and Future for Neural Machine Translation
Previous studies have shown that neural machine translation (NMT) models...
research
∙
04/05/2019
Convolutional Self-Attention Networks
Self-attention networks (SANs) have drawn increasing interest due to the...
research
∙
04/05/2019
Information Aggregation for Multi-Head Attention with Routing-by-Agreement
Multi-head attention is appealing for its ability to jointly extract dif...
research
∙
04/05/2019