Related papers: BitCoin: Bidirectional Tagging and Supervised Cont…
This work focuses on sign language retrieval-a recently proposed task for sign language understanding. Sign language retrieval consists of two sub-tasks: text-to-sign-video (T2V) retrieval and sign-video-to-text (V2T) retrieval. Different…
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…
Learning the embeddings of knowledge graphs (KG) is vital in artificial intelligence, and can benefit various downstream applications, such as recommendation and question answering. In recent years, many research efforts have been proposed…
Recent work for extracting relations from texts has achieved excellent performance. However, most existing methods pay less attention to the efficiency, making it still challenging to quickly extract relations from massive or streaming text…
As textual attributes like font are core design elements of document format and page style, automatic attributes recognition favor comprehensive practical applications. Existing approaches already yield satisfactory performance in…
Continuous Relation Extraction (CRE) aims to incrementally learn relation knowledge from a non-stationary stream of data. Since the introduction of new relational tasks can overshadow previously learned information, catastrophic forgetting…
Relation extraction (RE) consists in categorizing the relationship between entities in a sentence. A recent paradigm to develop relation extractors is Distant Supervision (DS), which allows the automatic creation of new datasets by taking…
Previous works of negation understanding mainly focus on negation cue detection and scope resolution, without identifying negation subject which is also significant to the downstream tasks. In this paper, we propose a new negation triplet…
Recent relation extraction (RE) works have shown encouraging improvements by conducting contrastive learning on silver labels generated by distant supervision before fine-tuning on gold labels. Existing methods typically assume all these…
In this work we focus on multi-turn passage retrieval as a crucial component of conversational search. One of the key challenges in multi-turn passage retrieval comes from the fact that the current turn query is often underspecified due to…
Entity-relation extraction aims to jointly solve named entity recognition (NER) and relation extraction (RE). Recent approaches use either one-way sequential information propagation in a pipeline manner or two-way implicit interaction with…
We study offline meta-reinforcement learning, a practical reinforcement learning paradigm that learns from offline data to adapt to new tasks. The distribution of offline data is determined jointly by the behavior policy and the task.…
Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be…
Extracting entities and relations is an essential task of information extraction. Triplets extracted from a sentence might overlap with each other. Previous methods either did not address the overlapping issues or solved overlapping issues…
Self-supervised learning (SSL) has achieved remarkable performance in pretraining the models that can be further used in downstream tasks via fine-tuning. However, these self-supervised models may not capture meaningful semantic information…
Although synthetic data has changed various aspects of information retrieval (IR) pipelines, the main training paradigm remains: contrastive learning with binary relevance labels, where one positive document is compared against several…
Large language models (LLMs) struggle in knowledge-intensive tasks, as retrievers often overfit to surface similarity and fail on queries involving complex logical relations. The capacity for logical analysis is inherent in model…
Robust tensor completion (RTC) aims to recover a low-rank tensor from its incomplete observation with outlier corruption. The recently proposed tensor ring (TR) model has demonstrated superiority in solving the RTC problem. However, the…
A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are…
Document-level relation extraction aims to categorize the association between any two entities within a document. We find that previous methods for document-level relation extraction are ineffective in exploiting the full potential of large…