Related papers: A Two-Stream AMR-enhanced Model for Document-level…
We introduce MemSum (Multi-step Episodic Markov decision process extractive SUMmarizer), a reinforcement-learning-based extractive summarizer enriched at each step with information on the current extraction history. When MemSum iteratively…
Events describe the state changes of entities. In a document, multiple events are connected by various relations (e.g., Coreference, Temporal, Causal, and Subevent). Therefore, obtaining the connections between events through Event-Event…
Document-level Relation Extraction (DocRE) involves identifying relations between entities across multiple sentences in a document. Evidence sentences, crucial for precise entity pair relationships identification, enhance focus on essential…
Abstractive text summarization aims at compressing the information of a long source document into a rephrased, condensed summary. Despite advances in modeling techniques, abstractive summarization models still suffer from several key…
Extracting the reported events from text is one of the key research themes in natural language processing. This process includes several tasks such as event detection, argument extraction, role labeling. As one of the most important topics…
Generating a text abstract from a set of documents remains a challenging task. The neural encoder-decoder framework has recently been exploited to summarize single documents, but its success can in part be attributed to the availability of…
Narratives are key interpretative devices by which humans make sense of political reality. As the significance of narratives for understanding current societal issues such as polarization and misinformation becomes increasingly evident,…
Multi-document summarization is a challenging task due to its inherent subjective bias, highlighted by the low inter-annotator ROUGE-1 score of 0.4 among DUC-2004 reference summaries. In this work, we aim to enhance the objectivity of news…
Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document…
Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity,…
Generative document retrieval, an emerging paradigm in information retrieval, learns to build connections between documents and identifiers within a single model, garnering significant attention. However, there are still two challenges: (1)…
Recent large vision-language models have achieved strong performance on short- and medium-length video understanding, yet they remain inadequate for ultra-long or even infinite video reasoning, where models must preserve coherent memory…
Automatic assessment of the quality of arguments has been recognized as a challenging task with significant implications for misinformation and targeted speech. While real-world arguments are tightly anchored in context, existing…
This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern…
State-of-the-art (SOTA) Automatic Speech Recognition (ASR) systems primarily rely on acoustic information while disregarding additional multi-modal context. However, visual information are essential in disambiguation and adaptation. While…
In complex reasoning tasks, as expressible by Answer Set Programming (ASP), problems often permit for multiple solutions. In dynamic environments, where knowledge is continuously changing, the question arises how a given model can be…
Extracting relations across large text spans has been relatively underexplored in NLP, but it is particularly important for high-value domains such as biomedicine, where obtaining high recall of the latest findings is crucial for practical…
We develop a novel technique to parse English sentences into Abstract Meaning Representation (AMR) using SEARN, a Learning to Search approach, by modeling the concept and the relation learning in a unified framework. We evaluate our parser…
Video event extraction aims to detect salient events from a video and identify the arguments for each event as well as their semantic roles. Existing methods focus on capturing the overall visual scene of each frame, ignoring fine-grained…
In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM). SAAM works on top of traditional neural networks and is designed to address the problem of multi-aspect sentiment classification and…