Papers by Kevin Chang
Ask To The Point: Open-Domain Entity-Centric Question Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | *entity-centric question generation (ECQG) is a task motivated by real-world applications such as topic-specific learning, assisted reading, and fact-checking. |
| Approach: | They propose a PLM-based framework GenCONE with two modules: content focusing and question verification. |
| Outcome: | The proposed framework outperforms baselines and is effective and complementary in generating high-quality questions. |
Citation: A Key to Building Responsible and Accountable Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) bring transformative benefits alongside unique challenges, including intellectual property (IP) and ethical concerns. |
| Approach: | They propose a new approach to mitigate intellectual property and ethical risks associated with large language models. |
| Outcome: | The proposed approach could enhance content transparency and verifiability . it should account for both non-parametric and parametric content . |
Text Fact Transfer (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing text style transfer models struggle with text fact transfer due to their inability to preserve the specificity and phrasing of the source text and tendency to hallucinate errors. |
| Approach: | They propose a task that seeks to transfer factual content between topics without changing its style. |
| Outcome: | The proposed framework can transfer factual content without sacrificing style without changing the style of the source text. |
Expository Text Generation: Imitate, Retrieve, Paraphrase (2023.emnlp-main)
Copied to clipboard
| Challenge: | Expository documents are vital resources for conveying complex information to readers. |
| Approach: | They propose a task to generate an accurate and stylistically consistent expository text by intelligently searching a knowledge source. |
| Outcome: | The proposed framework overcomes the limitations of retrieval-augmented models and produces factual and organized expository texts that accurately inform readers. |
Abstractive Open Information Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing OpenIE datasets and metrics are ill-suited for this task. |
| Approach: | They propose a new open-domain task that extends OpenIE to include inferred relations . they propose metric to evaluate the effectiveness of open-source OpenIE . |
| Outcome: | The proposed model can extract inferred relations from the extracted relation tuples. |
ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing iterative retrieval-augmented generation approaches struggle to delve deeply into each facet of complex queries. |
| Approach: | They propose a framework that employs a tree-structured retrieval approach to enhance the depth and relevance of retrieved content. |
| Outcome: | The proposed framework outperforms state-of-the-art models on multiple datasets and a newly introduced dataset. |
Meta-Learning Fast Weight Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens. |
| Approach: | They propose a neural component that uses gradient updates as linear attention to improve model performance. |
| Outcome: | The proposed model can be applied at training time and learn to make good use of gradient updates. |
Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage (2024.findings-eacl)
Copied to clipboard
| Challenge: | a new study examines the association capabilities of large language models . as models scale up, their ability to associate entities/information intensifies . however, there is a performance gap when associating commonsense knowledge versus PII, with the latter showing lower accuracy. |
| Approach: | They examine the association capabilities of large language models and identify factors that influence their proficiency in associating information. |
| Outcome: | The proposed models show a performance gap when associating commonsense knowledge versus PII, with the latter showing lower accuracy. |
Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing topic models often lack sufficient word co-occurrence in short texts, resulting in incoherent topics. |
| Approach: | They propose to use large language models to extend short texts into more detailed sequences before applying topic modeling to solve semantic inconsistency problem. |
| Outcome: | The proposed approach significantly outperforms current state-of-the-art topic models on real-world datasets with extreme data sparsity. |
GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing LLM leaderboards often reference scores reported in other papers without consistent settings and prompts, which may encourage cherry-picking favored settings and for better results. |
| Approach: | They propose an open-source and reproducible LLM evaluation suite built on top of OpenAI Evals that systematically evaluates 10+ leading LLMs and OpenAI’s legacy models on 20+ curated benchmarks across 7 capability categories. |
| Outcome: | The evaluation suite is built on top of OpenAI Evals and evaluates 10+ leading LLMs and OpenAI’s legacy models on 20+ curated benchmarks across 7 capability categories. |
Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has shown advantages of generative classifiers in terms of data efficiency and robustness. |
| Approach: | They propose a generative classifier for natural language inference (NLI) they compare it to discriminative models and large-scale pretrained models like BERT . |
| Outcome: | The proposed classifier outperforms discriminative and pretrained baselines across several challenging NLI experimental settings, including small training sets, imbalanced label distributions, and label noise. |
Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to measure fine-grained domain relevance are needed for downstream tasks in natural language processing. |
| Approach: | They propose to measure fine-grained domain relevance, defined as the degree that a term is relevant to a given domain. |
| Outcome: | The proposed method outperforms baselines and surpasses professional human performance. |
Open Relation Modeling: Learning to Define Relations between Entities (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing systems identify related entities but do not provide features for exploring relations between entities. |
| Approach: | They propose to teach machines to generate definition-like relation descriptions by letting them learn from defining entities. |
| Outcome: | The proposed model can generate definition-like relation descriptions that capture the representative characteristics of entities. |
Exploring Semantic Capacity of Terms (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that measure semantic capacity of terms are not all considered equal . a good command of semantic capacity will give us more insight into the granularity of terms . |
| Approach: | They propose a model that evaluates semantic capacity of terms if text corpus can provide enough co-occurrence information of terms. |
| Outcome: | The proposed model can evaluate semantic capacity of terms if the corpus can provide enough co-occurrence information of terms. |
VER: Unifying Verbalizing Entities and Relations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a new model for verbalizing entities and relations is proposed to help understand entities and relationships . a unified model for Verbalizing Entities and Relations is proposed . |
| Approach: | They propose a model that takes any entity or entity set as input and generates a sentence to represent entities and relations. |
| Outcome: | The proposed model can generate sentences describing entities and relations . it can be used to explain entities and relationships, and to perform commonsense reasoning tasks . |
VIEWS: Entity-Aware News Video Captioning (2024.emnlp-main)
Copied to clipboard
Hammad Ayyubi, Tianqi Liu, Arsha Nagrani, Xudong Lin, Mingda Zhang, Anurag Arnab, Feng Han, Yukun Zhu, Xuande Feng, Kevin Zhang, Jialu Liu, Shih-Fu Chang
| Challenge: | Existing video captioning benchmarks and models produce generic captions for videos that lack specific identification of individuals, locations, or organizations. |
| Approach: | They propose a task of directly summarizing news videos into captions that are entity-aware . they validate the effectiveness of their approach across three video captioning models . |
| Outcome: | The proposed approach is effective across three video captioning models. |
When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream Applications (2023.acl-long)
Copied to clipboard
| Challenge: | Existing consensus on which OpenIE model is best for each application is lacking . different assumptions made by different models and datasets have a statistically significant effect on performance, making it important to choose the most appropriate OpenIE system for one’s applications. |
| Approach: | They propose to use OpenIE to extract relation tuples from plain text to compare different models and training sets to find the best model for their applications. |
| Outcome: | The proposed models perform well on a Complex QA application. |
Domain Representative Keywords Selection: A Probabilistic Approach (2022.findings-acl)
Copied to clipboard
| Challenge: | a probabilistic approach to select a subset of a target domain representative keywords is crucial for many downstream tasks in natural language processing. |
| Approach: | They propose a probabilistic approach to select a subset of a target domain representative keywords from a candidate set, contrasting with a context domain. |
| Outcome: | The proposed approach provides more importance to distinctive keywords than common keywords contrasting with the context domain. |