Search Results (15)

This paper presents Fic2Bot, an end-to-end framework that automatically transforms raw novel text into in-character chatbots by combining scene-level retrieval with persona profiling. Unlike conventional RAG-based systems that emphasize factual accuracy but neglect stylistic coherence, Fic2Bot ensures both factual grounding and consistent persona expression without any manual intervention. The framework integrates (1) Major Entity Identification (MEI) for robust coreference resolution, (2) scene-structured retrieval for precise contextual grounding, and (3) stylistic and sentiment profiling to capture linguistic and emotional traits of each character. Experiments conducted on novels from diverse genres show that Fic2Bot achieves robust entity resolution, more relevant retrieval, highly accurate speaker attribution, and stronger persona consistency in multi-turn dialogues. These results highlight Fic2Bot as a scalable and domain-agnostic framework for persona-driven chatbot generation, with potential applications in interactive roleplaying, language and literary studies, and entertainment. Full article

Ports and maritime operations generate massive real-time data streams, particularly from Automatic Identification System (AIS) signals, which are challenging to query effectively using natural language. This study proposes a prototype AISStream-MCP, a memory-augmented real-time maritime question-answering (QA) system that integrates live AIS data streaming with a Model Context Protocol (MCP) toolchain to support port operations decision-making. The system combines a large language model (LLM) with four MCP-enabled modules: persistent dialogue memory, live AIS data query, knowledge graph lookup, and result evaluation. We hypothesize that augmenting an LLM with domain-specific tools significantly improves QA performance compared to systems without memory or live data access. To test this hypothesis, we developed two prototype systems (with and without MCP framework) and evaluated them on 30 queries across three task categories: ETA prediction, anomaly detection, and multi-turn route queries. Experimental results demonstrate that AISStream-MCP achieves 88% answer accuracy (vs. 75% baseline), 85% multi-turn coherence (vs. 60%), and 38.7% faster response times (4.6 s vs. 7.5 s), with user satisfaction scores of 4.6/5 (vs. 3.5/5). The improvements are statistically significant (p < 0.01), confirming that memory augmentation and real-time tool integration effectively enhance maritime QA capabilities. Specifically, AISStream-MCP improved ETA prediction accuracy from 80% to 90%, anomaly detection from 70% to 85%, and multi-turn query accuracy from 65% to 88%. This approach shows significant potential for improving maritime situational awareness and operational efficiency. Full article

This paper presents a modular framework for character-coherent, emotion-aware role-playing dialogue with large language models (LLMs), centered on a novel Verifiable Emotion Reward (VER) objective. We introduce VER as a reinforcement-style signal derived from frozen emotion classifiers to provide both turn-level and dialogue-level alignment, effectively mitigating emotional drift across long interactions. To amplify VER’s benefits, we construct Character-Coherent Dialogues (CHARCO), a large-scale multi-turn dataset of over 230,000 dialogues, richly annotated with persona profiles, semantic contexts, and ten emotion labels. Our experiments show that fine-tuning LLMs on CHARCO significantly enhances VER’s impact, driving marked improvements in emotional consistency, role fidelity, and dialogue coherence. Through the evaluation that integrates lexical diversity metrics, automatic scoring with GPT-4, and human assessments, we demonstrate that the collaboration between a purpose-built multi-turn dataset and the VER objective leads to significant advancements in the field of persona-aligned conversational agents. Full article

This paper introduces WaterGPT, a language model designed for complex multimodal tasks in hydrology. WaterGPT is applied in three main areas: (1) processing and analyzing data such as images and text in water resources, (2) supporting intelligent decision-making for hydrological tasks, and (3) enabling interdisciplinary information integration and knowledge-based Q&A. The model has achieved promising results. One core aspect of WaterGPT involves the meticulous segmentation of training data for the supervised fine-tuning phase, sourced from real-world data and annotated with high quality using both manual methods and GPT-series model annotations. These data are carefully categorized into four types: knowledge-based, task-oriented, negative samples, and multi-turn dialogues. Additionally, another key component is the development of a multi-agent framework called Water_Agent, which enables WaterGPT to intelligently invoke various tools to solve complex tasks in the field of water resources. This framework handles multimodal data, including text and images, allowing for deep understanding and analysis of complex hydrological environments. Based on this framework, WaterGPT has achieved over a 90% success rate in tasks such as object detection and waterbody extraction. For the waterbody extraction task, using Dice and mIoU metrics, WaterGPT’s performance on high-resolution images from 2013 to 2022 has remained stable, with accuracy exceeding 90%. Moreover, we have constructed a high-quality water resources evaluation dataset, EvalWater, which covers 21 categories and approximately 10,000 questions. Using this dataset, WaterGPT achieved the highest accuracy to date in the field of water resources, reaching 83.09%, which is about 17.83 points higher than GPT-4. Full article

Pre-trained language models (PLMs) are proficient at understanding context in plain text but often struggle with the nuanced linguistics of task-oriented dialogues. The information exchanges in dialogues and the dynamic role-shifting of speakers contribute to complex coreference and interlinking phenomena across multi-turn interactions. To address these challenges, we propose Coreference-Enhanced Contrastive Pre-training (CECPT), an innovative pre-training framework specifically designed to enhance dialogue modeling. CECPT utilizes unsupervised dialogue datasets to capture both semantic richness and structural coherence. Our experimental results demonstrate that the CECPT model significantly outperforms established baselines in three critical applications: intent recognition, dialogue act prediction, and dialogue state tracking. These findings suggest that CECPT is more adept at following the information flow within dialogues and accurately linking statuses to their respective references. Full article

In the multi-turn dialogue scenario, users commonly encounter challenges with pronoun referents and information omission, leading to semantically incomplete representations. These issues contribute to textual incoherence, as unclear referents and missing components hinder the semantic understanding of the spoken representations of text by machines. Currently, scholars frequently resort to multiple rounds of dialogue rewriting to address the semantic challenges posed by the machine comprehension of semantically missing texts with pronoun referents and information omissions. However, existing dialogue-rewriting methods often suffer from low precision and high latency in handling such texts. To mitigate these shortcomings, this paper proposes a Transformer-based dialogue-rewriting model that utilizes pointer extraction. The method leverages a Transformer pre-training model to effectively extract the potential semantic features of text and extract the key information of text by a pointer address. By extracting keywords and appropriately replacing or inserting text, the model restores referents and missing information. The experimental findings on an open-source Chinese multi-turn dialogue-rewriting dataset demonstrate the effectiveness of the proposed method in improving both the accuracy and efficiency of rewriting compared with existing methods. Specifically, the ROUGR-1 value increased by 2.9%, while the time consumption decreased by 50% compared with the benchmark method. Full article

Syntactic priming in dialogue occurs when exposure to a particular syntactic structure implicitly induces a speaker’s subsequent preference for the same syntactic structures in their own speech. Here, we asked whether this priming effect is boosted when individuals are primed by several different speakers as opposed to one. In an initial baseline session involving a picture description task, we assessed adult participants’ production of double object/DO (vs. prepositional/PO) dative and passive (vs. active) transitive structures. Subsequently, participants played a picture description and verification game, in turns, with six other players (confederates). During verification turns, confederates primed participants by using DO and passive utterances. Crucially, participants were primed either by a single confederate (single-speaker priming condition, SSP) or by five confederates (multi-speaker priming condition, MSP). Across conditions, the same priming stimuli were presented in the same order, leaving speaker source/variation as the only different feature. The degree to which participants were primed for the target structures compared to baseline was measured. Results indicated a robust priming effect in both conditions. Nevertheless, the increase in the target structures’ use did not differ significantly between the SSP and MSP conditions, suggesting that speaker variation did not promote stronger priming. Full article

In recent years, emotional dialogue generation garnered widespread attention and made significant progress in the English-speaking domain. However, research on emotional dialogue generation in Chinese still faces two critical issues: firstly, the lack of high-quality datasets with emotional characteristics makes it difficult for models to fully utilize emotional information for emotional intervention; secondly, there is a lack of effective neural network models for extracting and integrating inherent logical information in the context to fully understand dialogues. To address these issues, this paper presented a Chinese dialogue dataset called LifeDialog, which was annotated with sentiment features. Additionally, it proposed DialogCIN, a contextual inference network that aims to understand dialogues based on a cognitive perspective. Firstly, the proposed model acquired contextual representations at both the global and speaker levels. Secondly, different levels of contextual vectors were separately inputted into the understanding unit, which consists of multiple inference modules. These modules iteratively performed reasoning and retrieval to delve into the inherent logical information of the dialogue context. Subsequently, appropriate emotions were predicted for feedback. Finally, an emotion-aware decoder was employed to generate a response. Experimental results on our manually annotated dataset, LifeDialog, demonstrated that DialogCIN can effectively simulate human cognitive inference processes, enabling a better understanding of dialogue context and improving the quality of generated dialogues. Full article

Task-oriented dialogue systems depend on dialogue state tracking to keep track of the intentions of users in the course of conversations. Although recent models in dialogue state tracking exhibit good performance, the errors in predicting the value of each slot at the current dialogue turn of these models are easily carried over to the next turn, and unlikely to be revised in the next turn, resulting in error propagation. In this paper, we propose a revisable state prediction for dialogue state tracking, which constructs a two-stage slot value prediction process composed of an original prediction and a revising prediction. The original prediction process jointly models the previous dialogue state and dialogue context to predict the original dialogue state of the current dialogue turn. Then, in order to avoid the errors existing in the original dialogue state continuing to the next dialogue turn, a revising prediction process utilizes the dialogue context to revise errors, alleviating the error propagation. Experiments are conducted on MultiWOZ 2.0, MultiWOZ 2.1, and MultiWOZ 2.4 and results indicate that our model outperforms previous state-of-the-art works, achieving new state-of-the-art performances with 56.35, 58.09, and 75.65% joint goal accuracy, respectively, which has a significant improvement (2.15, 1.73, and 2.03%) over the previous best results. Full article

Semantic co-reference and ellipsis always lead to information deficiency when parsing natural language utterances with SQL in a multi-turn dialogue (i.e., conversational text-to-SQL task). The methodology of dividing a dialogue understanding task into dialogue utterance rewriting and language understanding is feasible to tackle this problem. To this end, we present a two-stage framework to complete conversational text-to-SQL tasks. To construct an efficient rewriting model in the first stage, we provide a large-scale dialogue rewrite dataset (DIR), which is extended from two cross-domain conversational text-to-SQL datasets, SParC and CoSQL. The dataset contains 5908 dialogues involving 160 domains. Therefore, it not only focuses on conversational text-to-SQL tasks, but is also a valuable corpus for dialogue rewrite study. In experiments, we validate the efficiency of our annotations with a popular text-to-SQL parser, RAT-SQL. The experiment results illustrate 11.81 and 27.17 QEM accuracy improvement on SParC and CoSQL, respectively, when we eliminate the semantic incomplete representations problem by directly parsing the golden rewrite utterances. The experiment results of evaluating the performance of the two-stage frameworks using different rewrite models show that the efficiency of rewrite models is important and still needs improvement. Additionally, as a new benchmark of the dialogue rewrite task, we also report the performance results of different baselines for related studies. Our dataset will be publicly available once this paper is accepted. Full article

Integration of environmental, economic, and social approaches to development is crucial to achieve the United Nations Sustainable Development Goals. Global evidence reflects that this integration is often imbalanced, with development policies and programs in many low- and middle-income countries placing greater emphasis on economic needs than environmental vulnerabilities. Drawing on qualitative research undertaken in mid-2021, this article explores how limited integration of environmental, economic, and social aspects has affected the development of Rohingya refugee adolescents who were forcibly displaced from Myanmar to the Cox’s Bazar district of Bangladesh. Cox’s Bazar is one of the most climate-vulnerable areas in Bangladesh and is subject to extreme rainfall, landslides, and flash floods. The article highlights the ways in which Rohingya adolescents are highly vulnerable to both the direct and indirect consequences of these environmental conditions due to poverty, and inadequate housing infrastructure and water, sanitation, and hygiene facilities. It discusses the ways in which these environmental challenges intersect with socioeconomic disadvantage, especially limited education, skills development, and livelihood opportunities for young people, which are in turn compounded by limited voice and agency, and a dearth of security and protection measures. For some Rohingya adolescent girls and boys, the findings suggests that these multi-dimensional vulnerabilities place them at risk of exploitation by traffickers, smugglers, extremist groups, and criminals. The article concludes by highlighting the importance of explicitly integrating environmental aspects into policy and programs that support Rohingya adolescents to develop their full capabilities, and encouraging their meaningful participation in policy dialogues and accountability processes. Full article

During multi-turn dialogue, with the increase in dialogue turns, the difficulty of intention recognition and the generation of the following sentence reply become more and more difficult. This paper mainly optimizes the context information extraction ability of the Seq2Seq Encoder in multi-turn dialogue modeling. We fuse the historical dialogue information and the current input statement information in the encoder to capture the context dialogue information better. Therefore, we propose a BERT-based fusion encoder ProBERT-To-GUR (PBTG) and an enhanced ELMO model 3-ELMO-Attention-GRU (3EAG). The two models mainly enhance the contextual information extraction capability of multi-turn dialogue. To verify the effectiveness of the two proposed models, we demonstrate the effectiveness of our model by combining data based on the LCCC-large multi-turn dialogue dataset and the Naturalconv multi-turn dataset. The experimental comparison results show that, in the multi-turn dialogue experiments of the open domain and fixed topic, the two Seq2Seq coding models proposed are significantly improved compared with the current state-of-the-art models. For specified topic multi-turn dialogue, the 3EAG model has the average BLEU value reaches the optimal 32.4, which achieves the best language generation effect, and the BLEU value in the actual dialogue verification experiment also surpasses 31.8. for open-domain multi-turn dialogue. The average BLEU value of the PBTG model reaches 31.8, the optimal 31.8 achieves the best language generation effect, and the BLEU value in the actual dialogue verification experiment surpasses 31.2. So, the 3EAG model is more suitable for fixed-topic multi-turn dialogues for the two tasks. The PBTG model is more muscular in open-domain multi-turn dialogue tasks; therefore, our model is significant for promoting multi-turn dialogue research. Full article

The task of dialogue generation has attracted increasing attention due to its diverse downstream applications, such as question-answering systems and chatbots. Recently, the deep neural network (DNN)-based dialogue generation models have achieved superior performance against conventional models utilizing statistical machine learning methods. However, despite that an enormous number of state-of-the-art DNN-based models have been proposed, there lacks detailed empirical comparative analysis for them on the open Chinese corpus. As a result, relevant researchers and engineers might find it hard to get an intuitive understanding of the current research progress. To address this challenge, we conducted an empirical study for state-of-the-art DNN-based dialogue generation models in various Chinese corpora. Specifically, extensive experiments were performed on several well-known single-turn and multi-turn dialogue corpora, including KdConv, Weibo, and Douban, to evaluate a wide range of dialogue generation models that are based on the symmetrical architecture of Seq2Seq, RNNSearch, transformer, generative adversarial nets, and reinforcement learning respectively. Moreover, we paid special attention to the prevalent pre-trained model for the quality of dialogue generation. Their performances were evaluated by four widely-used metrics in this area: BLEU, pseudo, distinct, and rouge. Finally, we report a case study to show example responses generated by these models separately. Full article

Conversational agents are gaining huge popularity in industrial applications such as digital assistants, chatbots, and particularly systems for natural language understanding (NLU). However, a major drawback is the unavailability of a common metric to evaluate the replies against human judgement for conversational agents. In this paper, we develop a benchmark dataset with human annotations and diverse replies that can be used to develop such metric for conversational agents. The paper introduces a high-quality human annotated movie dialogue dataset, HUMOD, that is developed from the Cornell movie dialogues dataset. This new dataset comprises 28,500 human responses from 9500 multi-turn dialogue history-reply pairs. Human responses include: (i) ratings of the dialogue reply in relevance to the dialogue history; and (ii) unique dialogue replies for each dialogue history from the users. Such unique dialogue replies enable researchers in evaluating their models against six unique human responses for each given history. Detailed analysis on how dialogues are structured and human perception on dialogue score in comparison with existing models are also presented. Full article

To generate proper responses to user queries, multi-turn chatbot models should selectively consider dialogue histories. However, previous chatbot models have simply concatenated or averaged vector representations of all previous utterances without considering contextual importance. To mitigate this problem, we propose a multi-turn chatbot model in which previous utterances participate in response generation using different weights. The proposed model calculates the contextual importance of previous utterances by using an attention mechanism. In addition, we propose a training method that uses two types of Wasserstein generative adversarial networks to improve the quality of responses. In experiments with the DailyDialog dataset, the proposed model outperformed the previous state-of-the-art models based on various performance measures. Full article