Papers by Jiaan Wang

19 papers
Continual Learning with Semi-supervised Contrastive Distillation for Incremental Neural Machine Translation (2024.acl-long)

Copied to clipboard

Challenge: Multi-domain learning is a good solution for solving domain tasks but it requires retraining when adding a new domain.
Approach: They propose to exploit unlabeled data from the same distributions of the older domains to avoid catastrophic forgetting.
Outcome: The proposed framework exploits unlabeled data from the same distributions of the older domains to avoid catastrophic forgetting.
D2TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies focus on improving MMS models by filtering summary-unrelated visual features with implicit learning or explicitly complex training objectives.
Approach: They propose a multimodal multimodal summarization task that aims to generate summaries in any language with document inputs in any languages and the corresponding image sequence.
Outcome: The proposed task can generate summaries in any language with document inputs in any languages and the corresponding image sequence.
Retrieval-Augmented Machine Translation with Unstructured Knowledge (2025.findings-emnlp)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) is a new approach to enhance large language models (LLMs).
Approach: They propose a multi-task training method to teach LLMs how to use information from multilingual documents during their translation.
Outcome: The proposed method improves LLMs by 1.6-3.1 BLEU and 1.0-2.0 COMET scores in En-Zh, and 1.7-2.9 BLUE and 2.1-2.7 COMET score in En de.
Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to build a visual dialog (VD) Questioner do not provide explicit guidance for questioner to generate visually related and informative questions.
Approach: They propose a Related entity enhanced Questioner that learns entity-based questioning strategy from human dialogs.
Outcome: The proposed approach achieves state-of-the-art performance on image-guessing task and question diversity.
Cross-Lingual Knowledge Editing in Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Knowledge editing is a promising technique to adapt large language models to new knowledge without retraining from scratch.
Approach: They propose to use a multilingual dataset to translate a large-scale cross-lingual synthetic dataset from English to Chinese and then to evaluate their performance in Chinese.
Outcome: The proposed method can change model performance on several special cases without retraining from scratch.
DeepTrans: Deep Reasoning Translation via Reinforcement Learning (2026.tacl-1)

Copied to clipboard

Challenge: Recent studies have shown promising performance in various downstream tasks.
Approach: They propose a deep reasoning translation model that learns free translation via reinforcement learning (RL) they build a reward model with pre-defined scoring criteria on the translation results and thought processes .
Outcome: The proposed model outperforms strong deep reasoning LLMs in literature translation and outperformed other models.
Towards Unifying Multi-Lingual and Cross-Lingual Summarization (2023.acl-long)

Copied to clipboard

Challenge: Existing work on multilingual summarization and cross-lingual summmarization has been limited due to their different definitions.
Approach: They propose to unify MLS and CLS into a more general setting, i.e. many-to-many summarization.
Outcome: The proposed model outperforms the state-of-the-art models in the zero-shot directions.
Outdated Issue Aware Decoding for Factual Knowledge Editing (2024.findings-acl)

Copied to clipboard

Challenge: Existing knowledge editing methods retain outdated responses for reasoning questions . naively retraining LLMs can be computationally intensive and can lead to catastrophic forgetting .
Approach: They propose a simple yet effective decoding strategy to enhance edited models on reasoning questions.
Outcome: The proposed method outDates ISsue aware deCOding (DISCO) to improve models on reasoning questions.
An Empirical Study of Many-to-Many Summarization with Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that large language models (LLMs) have strong multilingual abilities, giving them the potential to perform M2MS in real applications.
Approach: They propose to use many-to-many summarization (M2MS) to generate a brief summary in any language given a document also in any other language.
Outcome: The proposed model outperforms zero-shot LLMs in terms of automatic evaluations.
Unleashing the Power of Emojis in Texts via Self-supervised Graph Pre-Training (2024.emnlp-main)

Copied to clipboard

Challenge: Emojis have gained immense popularity on social media platforms, serving as a common means to supplement or replace text.
Approach: They propose a graph pre-train framework for text and emoji co-modeling that incorporates two tasks: node-level graph contrastive learning and edge-level link reconstruction learning.
Outcome: The proposed framework improves on the Xiaohongshu and Twitter datasets with two types of downstream tasks.
ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Emotion Support Conversation (ESC) is a crucial application for reducing stress and providing emotional guidance.
Approach: They re-organize 2,801 role-playing cards to define roles of role-players . they train a specific role- playing model called ESC-Role which behaves more like a confused person than GPT-4 .
Outcome: The proposed model behaves more like a confused person than GPT-4, and the model performs better than GPLs.
Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization (2023.acl-long)

Copied to clipboard

Challenge: Existing studies on multimodal abstractive summarization focus on how to use extracted visual features to produce a concise summary given the multimodal data.
Approach: They propose to improve the visual quality of the multimodal abstractive summarization model by capturing summary-oriented visual features.
Outcome: The proposed approach achieves state-of-the-art under 44 languages and is highly effective on high-resource English datasets.
Towards Unifying Reference Expression Generation and Comprehension (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models for REG and REC have distinct inputs and connections between them . a new model for REg and reprehension is needed to solve these problems .
Approach: They propose a unified model for REG and REC that fuses image, region and text . they propose Vision-conditioned Masked Language Modeling and Text-Conditioned Region Prediction .
Outcome: The proposed model outperforms existing models on REG and REC tasks.
MusTQ: A Temporal Knowledge Graph Question Answering Dataset for Multi-Step Temporal Reasoning (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on fact-centered reasoning with limited attention to temporal reasoning.
Approach: They propose a new TKGQA dataset, MusTQ, which contains 666K multi-step temporal reasoning questions and a TKG.
Outcome: The proposed model achieves state-of-the-art multi-step temporal reasoning ability with entity-time attention mechanism and optimized temporal knowledge graph representation.
A Survey on Cross-Lingual Summarization (2022.tacl-1)

Copied to clipboard

Challenge: Cross-lingual summarization is a task of generating a summary in one language for a given document in a different language.
Approach: They present a systematic review of the literature on cross-lingual summarization . they summarize previous efforts and compare them with each other .
Outcome: The proposed approach is compared with previous approaches and summarizes them to provide a deeper analysis.
LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency (2022.coling-1)

Copied to clipboard

Challenge: Existing parameter-efficient methods focus on reducing trainable parameters but neglect the inference speed, which limits the ability to deploy PLMs.
Approach: They propose to use a hypernetwork-assisted inter-layer connector to enhance inference efficiency by tuning parameters inside a linear connector between two Transformer layers.
Outcome: The proposed model reduces model parameters to 11.75% while preserving performance degradation to less than 5%.
Understanding Translationese in Cross-Lingual Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing datasets involve translation, but translationese is distinguished from original text . previous studies have shown that translationeses in CLS are not a problem in training sets .
Approach: They propose to use cross-lingual summarization to generate a concise summary in a target language from a document in . existing datasets typically involve translation in their creation, but the translated text is distinguished from the original written in that language.
Outcome: The proposed method systematically investigates how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries.
ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to building cross-lingual summarization systems on dialogue documents are limited.
Approach: They propose a benchmark dataset for building cross-lingual summarization systems on dialogue documents.
Outcome: The proposed model outperforms pipeline models on ClidSum and mDialBART.
DRT: Deep Reasoning Translation via Long Chain-of-Thought (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies have shown the effectiveness of long chain-of-thought (CoT) in reasoning tasks such as math and coding tasks.
Approach: They propose to use Qwen2.5 and LLama-3.1 as backbones to train long thought models to bring the success of long chain-of-thought (CoT) to neural machine translation.
Outcome: The proposed model outperforms vanilla LLMs and LLM models which are fine-tuning on paired sentences without long thought and outperformed vanilla LRMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations