Related papers: Modeling Unified Semantic Discourse Structure for …

Timeline Generation aims at summarizing news from different epochs and telling readers how an event evolves. It is a new challenge that combines salience ranking with novelty detection. For long-term public events, the main topic usually…

Over the last few years, machine learning over graph structures has manifested a significant enhancement in text mining applications such as event detection, opinion mining, and news recommendation. One of the primary challenges in this…

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

Recent advances in large language models enable documents to be represented as dense semantic embeddings, supporting similarity-based operations over large text collections. However, many web-scale systems still rely on flat clustering or…

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs…

Headline generation, a key task in abstractive summarization, strives to condense a full-length article into a succinct, single line of text. Notably, while contemporary encoder-decoder models excel based on the ROUGE metric, they often…

Centralized search engines are key for the Internet, but lead to undesirable concentration of power. Decentralized alternatives fail to offer equal document retrieval accuracy and speed. Nevertheless, Semantic Overlay Networks can come…

Extractive text summarization aims at extracting the most representative sentences from a given document as its summary. To extract a good summary from a long text document, sentence embedding plays an important role. Recent studies have…

The growing complexity of legal cases has lead to an increasing interest in legal information retrieval systems that can effectively satisfy user-specific information needs. However, such downstream systems typically require documents to be…

We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a…

Long-document topic segmentation plays an important role in information retrieval and document understanding, yet existing methods still show clear shortcomings in ultra-long text settings. Traditional discriminative models are constrained…

Automatically generating debates is a challenging task that requires an understanding of arguments and how to negate or support them. In this work we define debate trees and paths for generating debates while enforcing a high level…

Session search involves a series of interactive queries and actions to fulfill user's complex information need. Current strategies typically prioritize sequential modeling for deep semantic understanding, overlooking the graph structure in…

We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents. Unlike existing multi-document summarization methods, our framework processes documents telling different stories instead of…

Stylistic headline generation is the task to generate a headline that not only summarizes the content of an article, but also reflects a desired style that attracts users. As style-specific article-headline pairs are scarce, previous…

Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise…

Image paragraph captioning aims to describe a given image with a sequence of coherent sentences. Most existing methods model the coherence through the topic transition that dynamically infers a topic vector from preceding sentences.…

In dyadic speaker-listener interactions, the listener's head reactions along with the speaker's head movements, constitute an important non-verbal semantic expression together. The listener Head generation task aims to synthesize responsive…

We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…

Writers generally rely on plans or sketches to write long stories, but most current language models generate word by word from left to right. We explore coarse-to-fine models for creating narrative texts of several hundred words, and…