Papers by David Chang

12 papers
Multimodal Conversation Structure Understanding (2026.eacl-long)

Copied to clipboard

Challenge: a new set of tasks is being developed to parse the structure of conversation . female characters are 1.2 times more likely to be cast as an addressee or side-participant .
Approach: They propose a set of tasks and release an annotated dataset for multimodal conversation structure understanding.
Outcome: The proposed model outperforms the baseline model, but performance drops when character identities are anonymized.
Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration (2026.findings-acl)

Copied to clipboard

Challenge: We show that script information is linearly encoded in the activation space of multilingual speech models . modifying activations at inference time induces script change even in unconventional pairings .
Approach: They propose to add script vectors to activations at test time to induce script change . they also show that script information is linearly encoded in the activation space of multilingual speech models .
Outcome: The proposed approach can induce script change even in unconventional language-script pairings.
Memory Augmented Language Models through Mixture of Word Experts (2024.naacl-long)

Copied to clipboard

Challenge: Increasing the parameter count of language models has been a primary driver of improved model quality, but increasing the model size also increases the cost of training and serving the model.
Approach: They propose to decouple learning capacity and FLOPs by using a mixture-of-experts approach with large knowledge-rich vocabulary based routing functions.
Outcome: The proposed model outperforms the T5 family of models with similar number of FLOPs on knowledge intensive tasks and similar performance to memory augmented approaches.
PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs (2023.emnlp-main)

Copied to clipboard

Challenge: PRESTO dataset contains 550K contextual multilingual conversations between humans and virtual assistants.
Approach: They propose to use a dataset of 550K contextual multilingual conversations between humans and virtual assistants to study some of the more challenging aspects of parsing realistic conversations.
Outcome: The dataset contains 550K contextual conversations between humans and virtual assistants.
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation (2021.naacl-demos)

Copied to clipboard

Challenge: a new framework to digest relevant biomedical knowledge is needed to combat COVID-19 . quantity of research results is a bottleneck, and false information promoted in publications .
Approach: a team of researchers has developed a framework to extract multimedia knowledge elements from scientific literature to combat COVID-19.
Outcome: a new framework extracts fine-grained multimedia knowledge elements from scientific literature . it provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence . the framework is based on a case study of drug repurposing .
MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction (2022.coling-1)

Copied to clipboard

Challenge: Relation extraction in the biomedical domain is challenging due to the lack of labeled data and high annotation costs.
Approach: They propose to use distant supervision to pair knowledge graph relationships with raw texts to tackle the scarcity of annotated data and to validate their results.
Outcome: The proposed benchmarks are more accurate and consistent with existing benchmarks and show that there is no train-test leakage.
Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4 (2023.emnlp-main)

Copied to clipboard

Challenge: a recent study has shown that open AI models memorize a wide collection of copyrighted materials . however, these models also present a challenge for establishing the validity of results .
Approach: They propose to use a name cloze membership inference query to infer books that are known to ChatGPT and GPT-4.
Outcome: The proposed model performs better on memorized books than on non-memorized books for downstream tasks.
DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in MT quality and language coverage have shown that language varieties with low baseline performance are more likely to benefit from these approaches.
Approach: They propose a training-time technique for adapting a pretrained model to dialectal data and an inference-time intervention adapting dialectal datasets to the model expertise.
Outcome: The proposed model shows significant performance gains for several dialects from four language families, and modest gains for two other language families.
AutoMixer: Checkpoint Artifacts as Automatic Data Mixers (2025.acl-long)

Copied to clipboard

Challenge: In language model training, it is difficult to obtain the right data mixtures for various tasks as the relationship between data and tasks is difficult.
Approach: They propose to identify checkpoint models based on their respective capabilities and leverage them as data mixers by using their aggregated first-order influence approximation over source data.
Outcome: The proposed framework shows significant improvements on eight reasoning benchmarks, with accuracy increases of up to 1.93%.
Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark (2023.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks of social language are lacking for large language models.
Approach: They propose a new benchmark that measures how well large language models understand social language by grouping 58 tasks into five categories: humor & sarcasm, offensiveness, sentiment & emotion, and trustworthiness.
Outcome: The proposed model performs well at 58 tasks that are divided into five categories: humor & sarcasm, offensiveness, sentiment & emotion, and trustworthiness.
Dramatic Conversation Disentanglement (2023.findings-acl)

Copied to clipboard

Challenge: a new dataset is available for studying conversation disentanglement in movies and TV series . a recent study focused on IRC chatroom dialogues, but movies and television show provide a space for study .
Approach: They propose a dataset for studying conversation disentanglement in movies and TV series . they operationalize a conversational thread and apply the best-performing model to 808 movies .
Outcome: The proposed model disentangles 808 movies from 10,033 dialogue turns . the best-performing model is compared with previous models .

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