Papers by Yang Kewei
Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs (2022.naacl-main)
Copied to clipboard
| Challenge: | Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCFGs) are widely used structured models. |
| Approach: | They use tensor rank decomposition to reduce computational complexities for a subset of FGGs subsuming HMMs and PCFGs. |
| Outcome: | The proposed model performs better on HMM modeling and unsupervised PCFG parsing than previous work. |
Combining (Second-Order) Graph-Based and Headed-Span-Based Projective Dependency Parsing (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing graph-based methods that score dependency trees do not score dependency arcs at all. |
| Approach: | They propose a headed-span-based method that decomposes the score of a dependency tree into scores of headed spans. |
| Outcome: | The proposed method improves over first-order graph-based methods, but does not score dependency arcs at all. |
Second-Order Unsupervised Neural Dependency Parsing (2020.coling-main)
Copied to clipboard
| Challenge: | supervised dependency parsers can reach a very high accuracy, but they require treebanks for training. |
| Approach: | They propose a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information. |
| Outcome: | The proposed model achieves 10% improvement over the previous state-of-the-art model on the full WSJ dataset. |
Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)
Copied to clipboard
Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang
| Challenge: | Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability. |
| Approach: | They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs . |
| Outcome: | The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks. |
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work shows that probabilistic context-free grammars with neural parameterization can be effective in unsupervised constituency parsing. |
| Approach: | They propose a parameterization form of PCFGs based on tensor decomposition which has at most quadratic computational complexity in the symbol number. |
| Outcome: | The proposed model improves unsupervised constituency parsing performance across ten languages. |
UniKER: A Unified Framework for Combining Embedding and Definite Horn Rule Reasoning for Knowledge Graph Inference (2021.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge graph inference has been studied extensively due to its wide applications. |
| Approach: | They propose a framework that restricts logical rules to be definite Horn rules and can exploit the knowledge in logical rule-based reasoning and KGE in an extremely efficient way. |
| Outcome: | The proposed framework can exploit the knowledge in logical rules and improve KGE in an extremely efficient way. |
Semantic Dependency Parsing with Edge GNNs (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing semantic dependency parsers use factor graphs to generate a tree structure, but they are ill-suited for a more complex semantic relationship representation. |
| Approach: | They propose a second-order neural CRF parser that uses factor graphs to generate a dependency edge and define neighbors in terms of sibling, co-parent, and grandparent relationships. |
| Outcome: | The proposed model outperforms the first-order biaffine parser on English datasets and shows that it is more efficient than the first order. |
Simple Hardware-Efficient PCFGs with Independent Left and Right Productions (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to scaling dense PCFGs to thousands of nonterminals have shown to be beneficial for unsupervised parsing, but they still perform poorly as a language model and as an unsupervised model. |
| Approach: | They propose a simple PCFG formalism with independent left and right productions that scales more effectively as a language model and as an unsupervised parser. |
| Outcome: | The proposed formalism scales better as a language model and as an unsupervised parser despite imposing a stronger independence assumption compared to low-rank approaches. |
Token-Aware Editing of Internal Activations for Large Language Model Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to optimize the behavior of large language models neglect misalignment discrepancies among tokens, resulting in deviant alignment direction and inflexible editing strength. |
| Approach: | They propose a token-aware editing approach to exploit the misalignment discrepancy among tokens to enhance activation probing and facilitate intervention. |
| Outcome: | Extensive experiments on three alignment capabilities demonstrate the efficacy of the proposed approach surpassing baseline by 25.8% on the primary metric of truthfulness with minimal cost. |
Don’t Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span Selection (2023.acl-long)
Copied to clipboard
| Challenge: | Constituency parsing is a fundamental task in natural language processing, having many applications in downstream tasks such as language modeling. |
| Approach: | They propose a simple and unified approach for both continuous and discontinuous constituency parsing via autoregressive span selection. |
| Outcome: | The proposed model can predict all possible continuous and discontinuous constituency trees without sacrificing data coverage and without expensive chart-based parsing algorithms. |
Structured Mean-Field Variational Inference for Higher-Order Span-Based Semantic Role Labeling (2023.findings-acl)
Copied to clipboard
| Challenge: | Span-based semantic role labeling is traditionally tackled by BIObased sequence labeling approaches. |
| Approach: | They propose to decompose the edge from predicate word to argument span into three different edges, enabling higher-order inference. |
| Outcome: | The proposed model outperforms vanilla MFVI on span-based semantic role labeling benchmarks. |
Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks (2022.acl-long)
Copied to clipboard
| Challenge: | Constituency parsing and nested named entity recognition (NER) are similar tasks since they aim to predict a collection of nesting and non-crossing spans. |
| Approach: | They propose a model that uses a pointer network to predict a constituency tree's boundary . constituency parsing is an important task in natural language processing . |
| Outcome: | The proposed model achieves state-of-the-art performance on PTB among all BERT-based models and competitive performance on CTB7 in constituency parsing. |
Neural Bi-Lexicalized PCFG Induction (2021.acl-long)
Copied to clipboard
| Challenge: | Neural lexicalized PCFGs make strong independence assumption on the generation of the child word and thus bilexical dependencies are ignored. |
| Approach: | They propose an approach to parameterize L-PCFGs without making implausible independence assumptions. |
| Outcome: | The proposed approach improves both running speed and unsupervised parsing performance on the English WSJ dataset. |
Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to recognize named entities have been criticized for their performance on flat NER but fail to handle nested entities. |
| Approach: | They propose to use a span-based constituency parser to tackle nested NER . they use lexicalized constituency trees to model nesting entities . |
| Outcome: | The proposed method achieves state-of-the-art performance on ACE2004, ACE2005 and NNE, and competitive performance on the GENIA platform. |
Hallucination Detection in Long-Form Text Generated by LLMs: A Benchmark and a Hyper-Relational Knowledge Graph Approach (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection are coarse-grained and lack long-range consistency checks. |
| Approach: | They propose a benchmark for long-form hallucination detection that incorporates diverse entity types and intricate factual dependencies spanning extended contexts. |
| Outcome: | The proposed framework outperforms baselines and robustly integrates fact-centric hyper-relational knowledge graphs. |
Improving Span Representation by Efficient Span-Level Attention (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating high-quality span representations are limited by subset of tokens . span-span interactions should play an important role in span encoding, authors argue . |
| Approach: | They propose to introduce span-span interactions and more comprehensive span-token interactions to improve span representations. |
| Outcome: | The proposed model outperforms baseline models on span-related tasks and shows superior performance. |
Headed-Span-Based Projective Dependency Parsing (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for dependency parsing based on headed spans are available. |
| Approach: | They propose a method for projective dependency parsing based on headed spans. |
| Outcome: | The proposed method achieves state-of-the-art or competitive results on PTB, CTB, and UD Dependency parsing is an important task in natural language processing. |
Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Entity and Relation Extraction (ERE) is an important task in information extraction. |
| Approach: | They propose a hypergraph neural network for ERE built upon the PL-marker . they use a pruner mechanism to transfer the burden of entity identification to the joint module . |
| Outcome: | The proposed model improves on three widely used benchmarks on ERE task . it uses a pruner mechanism to transfer the burden of entity identification to the joint module . |