554 citations · 1.3k across the 62 of their papers we have counts for
63 papers
Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark
Rong-Cheng Tu, Zi-Ao Ma, Tian Lan +3
Driven by the remarkable progress in diffusion models, text-to-image generation has made significant strides, creating a pressing demand for automatic quality evaluation of generat…
Training Language Models to Critique With Multi-agent Feedback
Tian Lan, Wenwei Zhang, Chengqi Lyu +6
Critique ability, a meta-cognitive capability of humans, presents significant challenges for LLMs to improve. Recent works primarily rely on supervised fine-tuning (SFT) using crit…
Beyond Exact Match: Semantically Reassessing Event Extraction by Large Language Models
Yi-Fan Lu, Xian-Ling Mao, Tian Lan +3
Event extraction has gained extensive research attention due to its broad range of applications. However, the current mainstream evaluation method for event extraction relies on to…
EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain
Yi-Fan Lu, Xian-Ling Mao, Bo Wang +2
It is crucial to understand a specific domain by events. Extensive event extraction research has been conducted in many domains such as news, finance, and biology. However, event e…
Mix-Initiative Response Generation with Dynamic Prefix Tuning
Yuxiang Nie, Heyan Huang, Xian-Ling Mao +1
Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather differen…
CriticEval: Evaluating Large Language Model as Critic
Tian Lan, Wenwei Zhang, Chen Xu +4
Critique ability, i.e., the capability of Large Language Models (LLMs) to identify and rectify flaws in responses, is crucial for their applications in self-improvement and scalabl…
Copy Is All You Need
Tian Lan, Deng Cai, Yan Wang +2
The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary. In this paper, we formulate text generation as progressively copying…
SciMRC: Multi-perspective Scientific Machine Reading Comprehension
Xiao Zhang, Heqi Zheng, Yuxiang Nie +2
Scientific machine reading comprehension (SMRC) aims to understand scientific texts through interactions with humans by given questions. As far as we know, there is only one datase…
Measuring Cross-Lingual Transferability of Multilingual Transformers on Sentence Classification
Zewen Chi, Heyan Huang, Xian-Ling Mao
Recent studies have exhibited remarkable capabilities of pre-trained multilingual Transformers, especially cross-lingual transferability. However, current methods do not measure cr…
AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking
Yuxiang Nie, Heyan Huang, Wei Wei +1
Annotating long-document question answering (long-document QA) pairs is time-consuming and expensive. To alleviate the problem, it might be possible to generate long-document QA pa…
Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading Comprehension
Xiao Zhang, Heyan Huang, Zewen Chi +1
Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes. Machines are required to make a decision of "Yes/No/Inqui…
Momentum Decoding: Open-ended Text Generation As Graph Exploration
Tian Lan, Yixuan Su, Shuhang Liu +2
Open-ended text generation with autoregressive language models (LMs) is one of the core tasks in natural language processing. However, maximization-based decoding methods (e.g., gr…
ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension
Xiao Zhang, Heyan Huang, Zewen Chi +1
Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer que…
Unsupervised Question Answering via Answer Diversifying
Yuxiang Nie, Heyan Huang, Zewen Chi +1
Unsupervised question answering is an attractive task due to its independence on labeled data. Previous works usually make use of heuristic rules as well as pre-trained models to c…
Cross-Lingual Phrase Retrieval
Heqi Zheng, Xiao Zhang, Zewen Chi +5
Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representation…
Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
Ding Zou, Wei Wei, Xian-Ling Mao +4
Knowledge graph (KG) plays an increasingly important role in recommender systems. Recently, graph neural networks (GNNs) based model has gradually become the theme of knowledge-awa…
On the Representation Collapse of Sparse Mixture of Experts
Zewen Chi, Li Dong, Shaohan Huang +9
Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-…
BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis
Shuo Liang, Wei Wei, Xian-Ling Mao +2
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to align aspects and corresponding sentiments for aspect-specific sentiment polarity infe…
Hammer PDF: An Intelligent PDF Reader for Scientific Papers
Sheng-Fu Wang, Shu-Hang Liu, Tian-Yi Che +4
It is the most important way for researchers to acquire academic progress via reading scientific papers, most of which are in PDF format. However, existing PDF Readers like Adobe A…
OneRel:Joint Entity and Relation Extraction with One Module in One Step
Yu-Ming Shang, Heyan Huang, Xian-Ling Mao
Joint entity and relation extraction is an essential task in natural language processing and knowledge graph construction. Existing approaches usually decompose the joint extractio…
Multi-view Intent Disentangle Graph Networks for Bundle Recommendation
Sen Zhao, Wei Wei, Ding Zou +1
Bundle recommendation aims to recommend the user a bundle of items as a whole. Nevertheless, they usually neglect the diversity of the user's intents on adopting items and fail to…
Exploring Dense Retrieval for Dialogue Response Selection
Tian Lan, Deng Cai, Yan Wang +3
Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to c…
Cross-Lingual Language Model Meta-Pretraining
Zewen Chi, Heyan Huang, Luyang Liu +2
The success of pretrained cross-lingual language models relies on two essential abilities, i.e., generalization ability for learning downstream tasks in a source language, and cros…
Context-aware Entity Typing in Knowledge Graphs
Weiran Pan, Wei Wei, Xian-Ling Mao
Knowledge graph entity typing aims to infer entities' missing types in knowledge graphs which is an important but under-explored issue. This paper proposes a novel method for this…