作者: 的闡明 時(shí)間: 2025-3-21 23:24
Fundamental organization models,pairs. In the interaction layer, we initially fuse the information of the sentence pairs to obtain low-level semantic information; at the same time, we use the bi-directional attention in the machine reading comprehension model and self-attention to obtain the high-level semantic information. We use作者: 反應(yīng) 時(shí)間: 2025-3-22 02:18 作者: 拋媚眼 時(shí)間: 2025-3-22 06:57 作者: 結(jié)合 時(shí)間: 2025-3-22 09:52
Markus F. Peschl,Thomas Fundneider emotion cause into the generation process. To this end, we present an emotion cause extractor using a semi-supervised training method and an empathetic conversation generator using a biased self-attention mechanism to overcome these two issues. Experimental results indicate that our proposed emotio作者: 商品 時(shí)間: 2025-3-22 15:34 作者: 商品 時(shí)間: 2025-3-22 19:53
Quantitative vs. Weighted Automata and design three patient strategies. Thirdly we design a label-aware contrastive learning loss function. Extensive experimental results show that our TempACL effectively adapts contrastive learning to supervised learning tasks which remain a challenge in practice. TempACL achieves new state-of-the-作者: 墊子 時(shí)間: 2025-3-23 00:43 作者: alliance 時(shí)間: 2025-3-23 01:49
Discourse Markers as the Classificatory Factors of Speech Actsse markers . and . are rather efficacious in differentiating distinct speech acts. This paper indicates that quantitative indexes can reflect the characteristics of human speech acts, and more objective and data-based classification schemes might be achieved based on these metrics.作者: Meditative 時(shí)間: 2025-3-23 08:15 作者: Hot-Flash 時(shí)間: 2025-3-23 11:47
ConIsI: A Contrastive Framework with Inter-sentence Interaction for Self-supervised Sentence Represection strategies to explore its effect. We conduct experiments on seven Semantic Textual Similarity (STS) tasks. The experimental results show that our ConIsI models based on . and . achieve state-of-the-art performance, substantially outperforming previous best models SimCSE-. and SimCSE-. by 2.05%作者: Abominate 時(shí)間: 2025-3-23 14:28 作者: Terminal 時(shí)間: 2025-3-23 21:18
Using Extracted Emotion Cause to Improve Content-Relevance for Empathetic Conversation Generation emotion cause into the generation process. To this end, we present an emotion cause extractor using a semi-supervised training method and an empathetic conversation generator using a biased self-attention mechanism to overcome these two issues. Experimental results indicate that our proposed emotio作者: 知識(shí) 時(shí)間: 2025-3-24 01:03
To Adapt or to Fine-Tune: A Case Study on Abstractive Summarizationtuning under extremely low-resource conditions. We further provide insights on multilinguality, model convergence, and robustness, hoping to shed light on the pragmatic choice of fine-tuning or adapters in abstractive summarization.作者: habitat 時(shí)間: 2025-3-24 03:42
Improving Event Temporal Relation Classification via Auxiliary Label-Aware Contrastive Learning and design three patient strategies. Thirdly we design a label-aware contrastive learning loss function. Extensive experimental results show that our TempACL effectively adapts contrastive learning to supervised learning tasks which remain a challenge in practice. TempACL achieves new state-of-the-作者: 炸壞 時(shí)間: 2025-3-24 09:51
Towards Making the Most of Pre-trained Translation Model for Quality Estimationoise to the target side of parallel data, and the model is trained to detect and recover the introduced noise. Both strategies can adapt the pre-trained translation model to the QE-style prediction task. Experimental results show that our model achieves impressive results, significantly outperformin作者: 咽下 時(shí)間: 2025-3-24 12:27 作者: expunge 時(shí)間: 2025-3-24 18:46
DIFM: An Effective Deep Interaction and Fusion Model for Sentence Matchingations in natural language processing tasks such as reading comprehension, question and answer systems. The main approach is to compute the interaction between text representations and sentence pairs through an attention mechanism, which can extract the semantic information between sentence pairs we作者: heterogeneous 時(shí)間: 2025-3-24 21:03
ConIsI: A Contrastive Framework with Inter-sentence Interaction for Self-supervised Sentence Represeined high-quality sentence representation based on contrastive learning from pre-trained models. However, these works suffer the inconsistency of input forms between the pre-training and fine-tuning stages. Also, they typically encode a sentence independently and lack feature interaction between sen作者: oracle 時(shí)間: 2025-3-25 00:02
Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Formsabeled data. In this paper, we propose a data synthesis and iterative refinement framework for neural semantic parsing, which can build semantic parsers without annotated logical forms. We first generate a naive corpus by sampling logic forms from knowledge bases and synthesizing their canonical utt作者: 俗艷 時(shí)間: 2025-3-25 04:59 作者: MILK 時(shí)間: 2025-3-25 09:03 作者: 兩棲動(dòng)物 時(shí)間: 2025-3-25 12:51
Abstains from Prediction: Towards Robust Relation Extraction in Real Worldredictions when exposed to samples of unseen relations. In this work, we propose a relation extraction method with rejection option to improve robustness to unseen relations. To enable the classifier to reject unseen relations, we introduce contrastive learning techniques and carefully design a set 作者: Synthesize 時(shí)間: 2025-3-25 16:46 作者: 我不死扛 時(shí)間: 2025-3-25 21:16 作者: 壓迫 時(shí)間: 2025-3-26 00:24 作者: 毗鄰 時(shí)間: 2025-3-26 05:30
A Multi-Gate Encoder for Joint Entity and Relation Extractionnt decoding to create interaction between these two tasks. However, ensuring the specificity of task-specific traits while the two tasks interact properly is a huge difficulty. We propose a multi-gate encoder that models bidirectional task interaction while keeping sufficient feature specificity bas作者: achlorhydria 時(shí)間: 2025-3-26 08:44 作者: Acumen 時(shí)間: 2025-3-26 14:31 作者: intrigue 時(shí)間: 2025-3-26 20:42
https://doi.org/10.1007/978-3-540-33273-2ficient to meet the needs of artificial intelligence for identifying and even understanding speech acts. To facilitate the automatic identification of the communicative intentions in human dialogs, scholars have tried some data-driven methods based on speech-act annotated corpora. However, few studi作者: 招募 時(shí)間: 2025-3-27 00:40
Fundamental organization models,ations in natural language processing tasks such as reading comprehension, question and answer systems. The main approach is to compute the interaction between text representations and sentence pairs through an attention mechanism, which can extract the semantic information between sentence pairs we作者: engrossed 時(shí)間: 2025-3-27 01:34 作者: ORBIT 時(shí)間: 2025-3-27 06:57
Markus F. Peschl,Thomas Fundneiderabeled data. In this paper, we propose a data synthesis and iterative refinement framework for neural semantic parsing, which can build semantic parsers without annotated logical forms. We first generate a naive corpus by sampling logic forms from knowledge bases and synthesizing their canonical utt作者: Osteoporosis 時(shí)間: 2025-3-27 13:18 作者: Fracture 時(shí)間: 2025-3-27 16:32
Management – Culture – Interpretation, the mainstream two-tower zero-shot methods usually rely on large-scale and in-domain labeled data of predefined relations. In this work, we view zero-shot relation extraction as a semantic matching task optimized by prompt-tuning, which still maintains superior generalization performance when the 作者: BIDE 時(shí)間: 2025-3-27 21:50 作者: vertebrate 時(shí)間: 2025-3-28 00:52
Markus F. Peschl,Thomas Fundneidersing emotion. Humans express not only their emotional state but also the stimulus that caused the emotion, i.e., emotion cause, during a conversation. Most existing approaches focus on emotion modeling, emotion recognition and prediction, and emotion fusion generation, ignoring the critical aspect o作者: bourgeois 時(shí)間: 2025-3-28 05:29
https://doi.org/10.1007/978-94-6300-821-1odels are sluggish to train and accompanied by a massive overhead. Researchers have proposed a few lightweight alternatives such as smaller adapters to mitigate the drawbacks. Nonetheless, it remains uncertain whether using adapters benefits the task of summarization, in terms of improved efficiency作者: 河流 時(shí)間: 2025-3-28 09:29
Joseph Livesey,Dominik Wojtczakical question answering, and automatic medical record analysis, etc. Compared with named entities (NEs) in general domain, medical named entities are usually more complex and prone to be nested. To cope with both flat NEs and nested NEs, we propose a MRC-based approach with multi-task learning and m作者: atopic-rhinitis 時(shí)間: 2025-3-28 13:53
Paul C. Bell,Patrick Totzke,Igor Potapovnt decoding to create interaction between these two tasks. However, ensuring the specificity of task-specific traits while the two tasks interact properly is a huge difficulty. We propose a multi-gate encoder that models bidirectional task interaction while keeping sufficient feature specificity bas作者: 難取悅 時(shí)間: 2025-3-28 17:11 作者: 案發(fā)地點(diǎn) 時(shí)間: 2025-3-28 19:34
Graph Games with Reachability Objectives,mmon practice is applying the translation model as a feature extractor. However, there exist several discrepancies between the translation model and the QE model. The translation model is trained in an autoregressive manner, while the QE model is performed in a non-autoregressive manner. Besides, th作者: 提煉 時(shí)間: 2025-3-29 02:22
Chinese Computational Linguistics978-3-031-18315-7Series ISSN 0302-9743 Series E-ISSN 1611-3349 作者: MINT 時(shí)間: 2025-3-29 06:18 作者: WAG 時(shí)間: 2025-3-29 10:30
https://doi.org/10.1007/978-3-031-18315-7artificial intelligence; computational linguistics; computer systems; computer vision; data mining; image作者: Carbon-Monoxide 時(shí)間: 2025-3-29 12:23 作者: 凹室 時(shí)間: 2025-3-29 17:30
Conference proceedings 2022r 2022..The 22 full English-language papers in this volume were carefully reviewed and selected from?293 Chinese and English submissions..The conference papers are categorized into the following topical sub-headings:?Linguistics and Cognitive Science;?Fundamental Theory and Methods of Computational 作者: 眨眼 時(shí)間: 2025-3-29 22:35 作者: defenses 時(shí)間: 2025-3-30 00:04 作者: 假設(shè) 時(shí)間: 2025-3-30 06:01