相关论文: Human-Like Decision Making: Document-level Aspect …

Deep reinforcement learning (RL) has been a commonly-used strategy for the abstractive summarization task to address both the exposure bias and non-differentiable task issues. However, the conventional reward Rouge-L simply looks for exact…

We propose a novel document generation process based on hierarchical latent tree models (HLTMs) learned from data. An HLTM has a layer of observed word variables at the bottom and multiple layers of latent variables on top. For each…

This paper concerns a deep learning approach to relevance ranking in information retrieval (IR). Existing deep IR models such as DSSM and CDSSM directly apply neural networks to generate ranking scores, without explicit understandings of…

Sentiment analysis or opinion mining has become an open research domain after proliferation of Internet and Web 2.0 social media. People express their attitudes and opinions on social media including blogs, discussion forums, tweets, etc.…

This paper focuses on two related subtasks of aspect-based sentiment analysis, namely aspect term extraction and aspect sentiment classification, which we call aspect term-polarity co-extraction. The former task is to extract aspects of a…

Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of ``\textit{Small Language Model (SLM) + Classifier}''.…

In this work, we propose a hierarchical reinforcement learning (HRL) structure which is capable of performing autonomous vehicle planning tasks in simulated environments with multiple sub-goals. In this hierarchical structure, the network…

This paper summarizes our contributions to the document-grounded dialog tasks at the 9th and 10th Dialog System Technology Challenges (DSTC9 and DSTC10). In both iterations the task consists of three subtasks: first detect whether the…

Cross-Domain Sequential Recommendation (CDSR) predicts user behavior by leveraging historical interactions across multiple domains, focusing on modeling cross-domain preferences through intra- and inter-sequence item relationships. Inspired…

This paper proposes a novel lifelong learning (LL) approach to sentiment classification. LL mimics the human continuous learning process, i.e., retaining the knowledge learned from past tasks and use it to help future learning. In this…

Documents are composed of smaller pieces - paragraphs, sentences, and tokens - that have complex relationships between one another. Sentiment classification models that take into account the structure inherent in these documents have a…

The joint optimization of representation learning and clustering in the embedding space has experienced a breakthrough in recent years. In spite of the advance, clustering with representation learning has been limited to flat-level…

Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense…

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

Hierarchical Reinforcement Learning (HRL) is a promising approach to solving long-horizon problems with sparse and delayed rewards. Many existing HRL algorithms either use pre-trained low-level skills that are unadaptable, or require…

Cooperative Multi-Agent Reinforcement Learning (MARL) solves complex tasks that require coordination from multiple agents, but is often limited to either local (independent learning) or global (centralized learning) perspectives. In this…

In aspect-based sentiment analysis, extracting aspect terms along with the opinions being expressed from user-generated content is one of the most important subtasks. Previous studies have shown that exploiting connections between aspect…

Answer selection is a task to choose the positive answers from a pool of candidate answers for a given question. In this paper, we propose a novel strategy for answer selection, called hierarchical ranking. We introduce three levels of…

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned…

Reinforcement Learning (RL) is a well-established framework for sequential decision-making in complex environments. However, state-of-the-art Deep RL (DRL) algorithms typically require large training datasets and often struggle to…