papers

Publications (13)

cs.CV2025

Train a Unified Multimodal Data Quality Classifier with Synthetic Data

Weizhi Wang, Rongmei Lin, Shiyang Li +7

The Multimodal Large Language Models (MLLMs) are continually pre-trained on a mixture of image-text caption data and interleaved document data, while the high-quality data filterin…

cs.LG2026

CoMem: Context Management with A Decoupled Long-Context Model

Yuwei Zhang, Chengyu Dong, Shuowei Jin +11

Context management enables agentic models to solve long-horizon tasks through iterative summarization of previous interaction histories. However, this process typically incurs subs…

cs.AI2018

CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web

Colin Lockard, Xin Luna Dong, Arash Einolghozati +1

The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases. Existing methods for extracting relations from the DO…

cs.CL2020

ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages

Colin Lockard, Prashant Shiralkar, Xin Luna Dong +1

In many documents, such as semi-structured webpages, textual semantics are augmented with additional information conveyed using visual elements including layout, font size, and col…

cs.IR2022

Label-Efficient Self-Training for Attribute Extraction from Semi-Structured Web Documents

Ritesh Sarkhel, Binxuan Huang, Colin Lockard +1

Extracting structured information from HTML documents is a long-studied problem with a broad range of applications, including knowledge base construction, faceted search, and perso…

cs.IR2021

TCN: Table Convolutional Network for Web Table Interpretation

Daheng Wang, Prashant Shiralkar, Colin Lockard +3

Information extraction from semi-structured webpages provides valuable long-tailed facts for augmenting knowledge graph. Relational Web tables are a critical component containing a…

cs.CL2025

DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities

Jing Yang Lee, Hamed Bonab, Nasser Zalmout +6

Large Language Models (LLMs) are increasingly employed in multi-turn conversational tasks, yet their pre-training data predominantly consists of continuous prose, creating a potent…

cs.IR2019

OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference

Dongxu Zhang, Subhabrata Mukherjee, Colin Lockard +2

In this paper, we consider advancing web-scale knowledge extraction and alignment by integrating OpenIE extractions in the form of (subject, predicate, object) triples with Knowled…

cs.CL2023

PLAtE: A Large-scale Dataset for List Page Web Extraction

Aidan San, Yuan Zhuang, Jan Bakus +6

Recently, neural models have been leveraged to significantly improve the performance of information extraction from semi-structured websites. However, a barrier for continued progr…

cs.CL2022

DOM-LM: Learning Generalizable Representations for HTML Documents

Xiang Deng, Prashant Shiralkar, Colin Lockard +2

HTML documents are an important medium for disseminating information on the Web for human consumption. An HTML document presents information in multiple text formats including unst…

cs.IR2023

Extracting Shopping Interest-Related Product Types from the Web

Yinghao Li, Colin Lockard, Prashant Shiralkar +1

Recommending a diversity of product types (PTs) is important for a good shopping experience when customers are looking for products around their high-level shopping interests (SIs)…

cs.CL2018

Semi-Supervised Event Extraction with Paraphrase Clusters

James Ferguson, Colin Lockard, Daniel S. Weld +1

Supervised event extraction systems are limited in their accuracy due to the lack of available training data. We present a method for self-training event extraction systems by boot…

cs.CL2026

ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer

Chunyuan Deng, Sanket Lokegaonkar, Colin Lockard +3

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often…