Error analysis prompting enables human-like translation evaluation in large language models: A case study on chatgpt
Generative large language models (LLMs), eg, ChatGPT, have demonstrated remarkable
proficiency across several NLP tasks such as machine translation, question answering, text …
proficiency across several NLP tasks such as machine translation, question answering, text …
Findings of the IWSLT 2022 Evaluation Campaign.
The evaluation campaign of the 19th International Conference on Spoken Language
Translation featured eight shared tasks:(i) Simultaneous speech translation,(ii) Offline …
Translation featured eight shared tasks:(i) Simultaneous speech translation,(ii) Offline …
Improving neural machine translation by bidirectional training
We present a simple and effective pretraining strategy--bidirectional training (BiT) for neural
machine translation. Specifically, we bidirectionally update the model parameters at the …
machine translation. Specifically, we bidirectionally update the model parameters at the …
Toward efficient language model pretraining and downstream adaptation via self-evolution: A case study on superglue
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the
SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general …
SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general …
Dynamic contrastive distillation for image-text retrieval
The recent advancement in vision-and-language pretraining (VLP) has significantly
improved the performance of cross-modal image-text retrieval (ITR) systems. However, the …
improved the performance of cross-modal image-text retrieval (ITR) systems. However, the …
Divide, conquer, and combine: Mixture of semantic-independent experts for zero-shot dialogue state tracking
Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of
task-oriented dialogue domains without the cost of collecting in-domain data. Existing works …
task-oriented dialogue domains without the cost of collecting in-domain data. Existing works …
Improving neural machine translation by denoising training
We present a simple and effective pretraining strategy {D} en {o} ising {T} raining DoT for
neural machine translation. Specifically, we update the model parameters with source-and …
neural machine translation. Specifically, we update the model parameters with source-and …
Bag of tricks for effective language model pretraining and downstream adaptation: A case study on glue
This technical report briefly describes our JDExplore d-team's submission Vega v1 on the
General Language Understanding Evaluation (GLUE) leaderboard, where GLUE is a …
General Language Understanding Evaluation (GLUE) leaderboard, where GLUE is a …
Improving simultaneous machine translation with monolingual data
Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge
distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However …
distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However …
Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?
The multimedia community has shown a significant interest in perceiving and representing
the physical world with multimodal pretrained neural network models, and among them, the …
the physical world with multimodal pretrained neural network models, and among them, the …