Multimodal summarization with multimodal output (MSMO) aims to generate coherent textual summaries while selecting the most semantically relevant images to enhance expressiveness. Despite the advancements of large multimodal models like GPT-4o, LLaMA-3, and Grok-3, these models often exhibit hallucination and weak visual-text alignment when applied to MSMO tasks. To address these challenges, we propose ModalSyncSum, a unified framework that enhances semantic consistency and visual faithfulness. It incorporates image-aware information extraction to mitigate visual-text misalignment, QA-based description verification to detect and correct hallucinated image descriptions, and named entity-guided refinement to ensure factual accuracy and entity alignment across modalities. Furthermore, we introduce a new evaluation metric M3AS, which jointly considers image content coverage, text-image alignment, and summary consistency, filling the gap in evaluating multimodal summary quality. Experimental results show that our model outperforms prompt-based baselines across multiple datasets, achieving significant gains on ROUGE, BLEU, and BERTScore, with BLEU improving by 21.95%. In human evaluation, M3AS exhibits stronger correlation with human judgments in consistency, image-summary relevance, and focus, surpassing existing automatic metrics.

Type inference is essential for programming languages, yet complete and global inference quickly becomes undecidable in the presence of rich type systems like System F. Pierce and Turner proposed local type inference (LTI) as a scalable, partially annotated alternative by relying on information local to applications. While LTI has been widely adopted in practice, there are significant gaps between theory and practice, with its theory being underdeveloped and specifications for LTI being complex and restrictive. We propose Local Contextual Type Inference , a principled redesign of LTI grounded in contextual typing—a recent formalism which captures type information flow. We present Contextual System F ( F c ), a variant of System F with implicit and first-class polymorphism. We formalize F c using a declarative type system, prove soundness, completeness, and decidability, and introduce matching subtyping as a bridge between declarative and algorithmic inference. This work offers the first mechanized treatment of LTI, while at the same time removing important practical restrictions and also demonstrating the power of contextual typing in designing robust, extensible and simple to implement type inference algorithms.

The performance of multilingual language models (MLLMs) is notably inferior for low-resource languages (LRL) compared to high-resource ones, primarily due to the limited available corpus during the pre-training phase. This inadequacy stems from the under-representation of low-resource language words in the subword vocabularies of MLLMs, leading to their misidentification as unknown or incorrectly concatenated subwords. Previous approaches are based on frequency sorting to select words for augmenting vocabularies. However, these methods overlook the fundamental disparities between model representation distributions and frequency distributions. To address this gap, we introduce a novel Entropy-Consistency Word Selection (ECWS) method, which integrates semantic and frequency metrics for vocabulary augmentation. Our results indicate an improvement in performance, supporting our approach as a viable means to enrich vocabularies inadequately represented in current MLLMs.

Chinese Semantic Error Recognition (CSER) has always been a weak link in Chinese language processing due to the complexity and obscureness of Chinese semantics. Existing research has gradually focused on leveraging pre-trained models to perform CSER. Although some researchers have attempted to integrate syntax information into the pre-trained language model, it requires training the models from scratch, which is time-consuming and laborious. Furthermore, despite the existence of datasets for CSER, the constrained size of these datasets impairs the performance of the models. Thus, in order to address the difficulty posed by a limited sample set and the need of annotating samples with semantic-level errors, we propose a Pseudo-label Data Construction method for CSER (PDC-CSER), generating pseudo-labels for augmented samples based on perplexity and model respectively, which overcomes the difficulty of constructing pseudo-label data containing semantic-level errors and ensures the quality of pseudo-labels. Moreover, we propose a CSER method with the Dependency Syntactic Attention mechanism (CSER-DSA) to explicitly infuse dependency syntactic information only in the fine-tuning stage, achieving robust performance, and simultaneously reducing substantial computing power and time cost. Results demonstrate that the pseudo-label technology PDC-CSER and the semantic error recognition method CSER-DSA surpass the existing models

Grammatical error correction (GEC) is of great importance in natural language processing (NLP). However, due to limited language resources, research on the Indonesian GEC remains scarce. In this paper, we propose an InDonesian In-cOntext-guided grammaticaL Error CorrecTion (IDIOLECT) method, aimed at enhancing the performance of large language models (LLMs) on Indonesian GEC task. Specifically, we calculate sentence similarity to select suitable in-context learning (ICL) demonstrations for each sample in the training set and test set, thereby aiding the model in more effectively identifying and correcting grammatical errors. This study further investigates the effects of ICL configurations, demonstration ordering, and demonstration quantity on model performance. The results indicate that the proposed method effectively improves the performance of LLMs in Indonesian GEC task.

Modern mainstream programming languages, such as TypeScript, Flow, and Scala, have polymorphic type systems enriched with intersection and union types. These languages implement variants of bidirectional higher-rank polymorphic type inference, which was previously studied mostly in the context of functional programming. However, existing type inference implementations lack solid theoretical foundations when dealing with non-structural subtyping and intersection and union types, which were not studied before. In this paper, we study bidirectional higher-rank polymorphic type inference with explicit type applications, and intersection and union types and demonstrate that these features have non-trivial interactions. We first present a type system, described by a bidirectional specification, with good theoretical properties and a sound, complete, and decidable algorithm. This is helpful to identify a class of types that can always be inferred. We also explore variants incorporating practical features, such as handling records and inferring a larger class of types, which align better with real-world implementations. Though some variants no longer have a complete algorithm, they still enhance the expressiveness of the type system. To ensure rigor, all results are formalized in the Coq proof assistant.

Normalization by evaluation (NbE) based on an untyped domain model is a convenient and powerful way to normalize terms to their β η normal forms. It enables a concise technical setup and simplicity for mechanization. Nevertheless, to date, untyped NbE has only been studied for cumulative universe hierarchies, and its correctness proof critically relies on the cumulativity of the system. Therefore, we are faced with the question: whether untyped NbE applies to a non-cumulative universe hierarchy? Because such a universe hierarchy is also widely used by proof assistants like Agda and Lean, this question is of practical significance. Our work answers this question positively. One important property typically induced from non-cumulativity is uniqueness : every term has a unique type. To faithfully reflect the uniqueness property, we work with a Martin-Löf type theory with explicit universe levels ascribed in the syntactic judgments. On the semantic side, universe levels are also explicitly managed, which leads to more complex semantics compared with a cumulative universe hierarchy. We prove that the NbE algorithm is sound and complete, and confirm that NbE does work with non-cumulativity. Moreover, to better align with common practice, we also show that the explicit annotations of universe levels, though technically useful, are logically redundant: NbE remains applicable without these annotations. As such, we provide a mechanized foundation with NbE for non-cumulativity.

Currently, the majority of research in grammatical error correction (GEC) is concentrated on universal languages, such as English and Chinese. Many low-resource languages lack accessible evaluation corpora. How to efficiently construct high-quality evaluation corpora for GEC in low-resource languages has become a significant challenge. To fill these gaps, in this article, we present a framework for constructing GEC corpora. Specifically, we focus on Indonesian as our research language and construct an evaluation corpus for Indonesian GEC using the proposed framework, addressing the limitations of existing evaluation corpora in Indonesian. Furthermore, we investigate the feasibility of utilizing existing large language models (LLMs), such as GPT-3.5-Turbo and GPT-4, to streamline corpus annotation efforts in GEC tasks. The results demonstrate significant potential for enhancing the performance of LLMs in low-resource language settings. Our code and corpus can be obtained from https://github.com/GKLMIP/GEC-Construction-Framework .

Reinforcement learning (RL) has demonstrated impressive performance in decision-making tasks like embodied control, autonomous driving, and financial trading. In many decision-making tasks, the agents often encounter the problem of executing actions under limited budgets. However, classic RL methods typically overlook the challenges posed by such sparse-executing actions. They operate under the assumption that all actions can be taken for an unlimited number of times, both in the formulation of the problem and in the development of effective algorithms. To tackle the issue of limited action execution in RL, this article first formalizes the problem as a sparse action Markov decision process (SA-MDP), in which specific actions in the action space can only be executed for a limited time. Then, we propose a policy optimization algorithm, Action Sparsity REgularization (ASRE), which adaptively handles each action with a distinct preference. ASRE operates through two steps. First, ASRE evaluates action sparsity by constrained action sampling. Following this, ASRE incorporates the sparsity evaluation into policy learning by way of an action distribution regularization. We provide theoretical identification that validates the convergence of ASRE to a regularized optimal value function. Experiments on tasks with known sparse-executing actions, where classical RL algorithms struggle to train policy efficiently, show that ASRE effectively constrains the action sampling and outperforms baselines. Moreover, we present that ASRE can generally improve the performance in Atari games, demonstrating its broad applicability.

Multimodal abstractive summarization (MAS) is a technique that generates a brief summary by processing input text and images. While preceding investigations on MAS have prioritized the utilization of visual features to amplify the quality of summaries, such advancements have predominantly been realized within high-resource languages, most notably English and Chinese. However, in the case of resource-scarce languages like Indonesian, the research and available resources pertaining to multimodal abstractive summarization remains constrained. In addition, the heterogeneity between visual and textual features may impact the quality of summary generation. Therefore, it is crucial to investigate vision-enhanced generative models to improve summary quality. To address the problem of insufficient resources of Indonesian MAS, we constructed the E-Liputan dataset, which is a summary-guided multimodal generative summarization dataset in Indonesian. We employed a two-stage methodology: first, we utilized a mask strategy to effectively address text denoising, thereby facilitating the pre-training of the visual encoder. Second, we fine-tuned an end-to-end multimodal summarization model and proposed a summary-guided multimodal interactive co-attention learning fusion, which facilitated the seamless integration and fusion of modalities within the model. Through the employment of these methodologies, the proposed multimodal model effectively acquired a richer repertoire of visual feature information oriented towards summarization, ultimately leading to enhanced precision and accuracy in generating summaries. We conducted extensive experiments on the E-Liputan dataset and found that our model outperformed the baseline models. Our findings suggest that investigating vision-enhanced generative models for MAS can significantly improve summary quality, particularly in resource-scarce languages.

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, Energy-guided DIffusion Sampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at https://github.com/liuxhym/EDIS.

When humans need to learn a new skill, we can acquire knowledge through written books, including textbooks, tutorials, etc. However, current research for decision-making, like reinforcement learning (RL), has primarily required numerous real interactions with the target environment to learn a skill, while failing to utilize the existing knowledge already summarized in the text. The success of Large Language Models (LLMs) sheds light on utilizing such knowledge behind the books. In this paper, we discuss a new policy learning problem called Policy Learning from tutorial Books (PLfB) upon the shoulders of LLMs’ systems, which aims to leverage rich resources such as tutorial books to derive a policy network. Inspired by how humans learn from books, we solve the problem via a three-stage framework: Understanding, Rehearsing, and Introspecting (URI). In particular, it first rehearses decision-making trajectories based on the derived knowledge after understanding the books, then introspects in the imaginary dataset to distill a policy network. We build two benchmarks for PLfB~based on Tic-Tac-Toe and Football games. In experiment, URI's policy achieves at least 44% net win rate against GPT-based agents without any real data; In Football game, which is a complex scenario, URI's policy beat the built-in AIs with a 37% while using GPT-based agent can only achieve a 6\% winning rate. The project page: https://plfb-football.github.io.

Abstract Chinese grammatical error correction (CGEC) is a significant challenge in Chinese natural language processing. Deep-learning-based models tend to have tens of millions or even hundreds of millions of parameters since they model the target task as a sequence-to-sequence problem. This may require a vast quantity of annotated corpora for training and parameter tuning. However, there are currently few open-source annotated corpora for the CGEC task; the existing researches mainly concentrate on using data augmentation technology to alleviate the data-hungry problem. In this paper, rather than expanding training data, we propose a competitive CGEC model from a new insight for reducing model parameters. The model contains three main components: a sequence learning module, a grammatical generalization module and a parameter sharing module. Experimental results on two Chinese benchmarks demonstrate that the proposed model could achieve competitive performance over several baselines. Even if the parameter number of our model is reduced by 1/3, it could reach a comparable $F_{0.5}$ value of 30.75%. Furthermore, we utilize English datasets to evaluate the generalization and scalability of the proposed model. This could provide a new feasible research direction for CGEC research.

Named entity recognition (NER) is a key component of many natural language processing (NLP) applications. The majority of advanced research, however, has not been widely applied to low-resource languages represented by Malay due to the data-hungry problem. In this paper, we present a system for building a Malay NER dataset (MS-NER) of 20,146 sentences through labelled datasets of homologous languages and iterative optimisation. Additionally, we propose a Multi-Task framework, namely MTBR, to integrate boundary information more effectively for NER. Specifically, boundary detection is treated as an auxiliary task and an enhanced Bidirectional Revision module with a gated ignoring mechanism is proposed to undertake conditional label transfer. This can reduce error propagation by the auxiliary task. We conduct extensive experiments on Malay, Indonesian, and English. Experimental results show that MTBR could achieve competitive performance and tends to outperform multiple baselines. The constructed dataset and model would be made available to the public as a new, reliable benchmark for Malay NER.

Mainstream object-oriented programming languages such as Java, Scala, C#, or TypeScript have polymorphic type systems with subtyping and bounded quantification. Bounded quantification, despite being a pervasive and widely used feature, has attracted little research work on type-inference algorithms to support it. A notable exception is local type inference, which is the basis of most current implementations of type inference for mainstream languages. However, support for bounded quantification in local type inference has important restrictions, and its non-algorithmic specification is complex. In this paper, we present a variant of kernel F ≤ , which is the canonical calculus with bounded quantification, with implicit polymorphism. Our variant, called F ≤ b , comes with a declarative and an algorithmic formulation of the type system. The declarative type system is based on previous work on bidirectional typing for predicative higher-rank polymorphism and a greedy approach to implicit instantiation. This allows for a clear declarative specification where programs require few type annotations and enables implicit polymorphism where applications omit type parameters. Just as local type inference, explicit type applications are also available in F ≤ b if desired. This is useful to deal with impredicative instantiations, which would not be allowed otherwise in F ≤ b . Due to the support for impredicative instantiations, we can obtain a completeness result with respect to kernel F ≤ , showing that all the well-typed kernel F ≤ programs can type-check in F ≤ b . The corresponding algorithmic version of the type system is shown to be sound, complete, and decidable. All the results have been mechanically formalized in the Abella theorem prover.

Previous works on cross-lingual Named Entity Recognition (NER) have achieved great success. However, few of them consider the effect of language families between the source and target languages. In this study, we find that the cross-lingual NER performance of a target language would decrease when its source language is changed from the same (homogenous) into a different (heterogenous) language family with that target language. To improve the NER performance in this situation, we propose a novel cross-lingual NER framework based on self-distillation mechanism and Bilateral-Branch Network (SD-BBN). SD-BBN learns source-language NER knowledge from supervised datasets and obtains target-language knowledge from weakly supervised datasets. These two kinds of knowledge are then fused based on self-distillation mechanism for better identifying entities in the target language. We evaluate SD-BBN on 9 language datasets from 4 different language families. Results show that SD-BBN tends to outperform baseline methods. Remarkably, when the target and source languages are heterogenous, SD-BBN can achieve a greater boost. Our results might suggest that obtaining language-specific knowledge from the target language is essential for improving cross-lingual NER when the source and target languages are heterogenous. This finding could provide a novel insight into further research.

Named Entity Recognition (NER) is fundamental to multiple downstream natural language processing (NLP) tasks, but most advanced NER methods heavily rely on massive labeled data with high cost. In this paper, we explore the effectiveness of self-training for low-resource NER. It is one of the semi-supervised approaches to reduce the reliance on manual annotation. However, random pseudo sample selection in standard self-training framework may cause serious error propagation, especially for token-level tasks. To that end, this paper focuses on pseudo sample selection and proposes a new self-training framework with double selectors, namely auxiliary judge task and entropy-based confidence measurement. Specifically, the auxiliary judge task is proposed to filter out the pseudo samples with wrong predictions. The entropy-based confidence measurement is introduced to select pseudo samples with high quality. In addition, to make full use of all pseudo samples, we propose a cumulative function based on the idea of curriculum learning to prompt the model to learn from easy samples to hard ones. Samples with low quality are filtered out through the double selectors, which is more conducive to the training of student models. Experimental results on five NER benchmark datasets from different languages indicate the effectiveness of the proposed framework over several advanced baselines.

Aspect-based sentiment analysis (ABSA), an extensively researched area in the field of natural language processing (NLP), predicts the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most languages lack sufficient annotation resources; thus, an increasing number of recent researchers have focused on cross-lingual aspect-based sentiment analysis (XABSA). However, most recent studies focus only on cross-lingual data alignment instead of model alignment. Therefore, we propose a novel framework, CL-XABSA: contrastive learning for cross-lingual aspect-based sentiment analysis. Based on contrastive learning, we close the distance between samples with the same label in different semantic spaces, achieving convergence of semantic spaces of different languages. Specifically, we design two contrastive objectives, token-level contrastive learning of token embeddings (TL-CTE) and sentiment-level contrastive learning of token embeddings (SL-CTE), to unify the semantic space of source and target languages. Since CL-XABSA can receive datasets in multiple languages during training, it can be further extended to multilingual aspect-based sentiment analysis (MABSA). To further improve the model performance, we perform knowledge distillation with target-language unlabeled data. In the distillation XABSA task, we further explore the effectiveness of different data (source dataset, translated dataset, and code-switched dataset). The results demonstrate that the proposed method has a certain improvement in the three XABSA tasks, distillation XABSA and MABSA. The source code of this paper is publicly available athttps://github.com/GKLMIP/CL-XABSA.

Dealing with real-world reinforcement learning (RL) tasks, we shall be aware that the environment may have sudden changes. We expect that a robust policy is able to handle such changes and adapt to the new environment rapidly. Context-based meta reinforcement learning aims at learning environment adaptable policies. These methods adopt a context encoder to perceive the environment on-the-fly, following which a contextual policy makes environment adaptive decisions according to the context. However, previous methods show lagged and unstable context extraction, which are hard to handle sudden changes well. This paper proposes an environment sensitive contextual policy learning (ESCP) approach, in order to improve both the sensitivity and the robustness of context encoding. ESCP is composed of three key components: variance minimization that forces a rapid and stable encoding of the environment context, relational matrix determinant maximization that avoids trivial solutions, and a history-truncated recurrent neural network model that avoids old memory interference. We use a grid-world task and 5 locomotion controlling tasks with changing parameters to empirically assess our algorithm. Experiment results show that in environments with both in-distribution and out-of-distribution parameter changes, ESCP can not only better recover the environment encoding, but also adapt more rapidly to the post-change environment (10x faster in the grid-world) while the return performance is kept or improved, compared with state-of-the-art meta RL methods.

Good representations can help RL agents perform concise modeling of their surroundings, and thus support effective decision-making in complex environments. Previous methods learn good representations by imposing extra constraints on dynamics. However, in the causal perspective, the causation between the action and its effect is not fully considered in those methods, which leads to the ignorance of the underlying relations among the action effects on the transitions. Based on the intuition that the same action always causes similar effects among different states, we induce such causation by taking the invariance of action effects among states as the relation. By explicitly utilizing such invariance, in this paper, we show that a better representation can be learned and potentially improves the sample efficiency and the generalization ability of the learned policy. We propose Invariant Action Effect Model (IAEM) to capture the invariance in action effects, where the effect of an action is represented as the residual of representations from neighboring states. IAEM is composed of two parts: (1) a new contrastive-based loss to capture the underlying invariance of action effects; (2) an individual action effect and provides a self-adapted weighting strategy to tackle the corner cases where the invariance does not hold. The extensive experiments on two benchmarks, i.e. Grid-World and Atari, show that the representations learned by IAEM preserve the invariance of action effects. Moreover, with the invariant action effect, IAEM can accelerate the learning process by 1.6x, rapidly generalize to new environments by fine-tuning on a few components, and outperform other dynamics-based representation methods by 1.4x in limited steps.

Trained on the large corpus, pre-trained language models (PLMs) can capture different levels of concepts in context and hence generate universal language representations. They can benefit from multiple downstream natural language processing (NLP) tasks. Although PTMs have been widely used in most NLP applications, especially for high-resource languages such as English, it is under-represented in Lao NLP research. Previous work on Lao has been hampered by the lack of annotated datasets and the sparsity of language resources. In this work, we construct a text classification dataset to alleviate the resource-scarce situation of the Lao language. In addition, we present the first transformer-based PTMs for Lao with four versions: BERT-Small , BERT-Base , ELECTRA-Small , and ELECTRA-Base . Furthermore, we evaluate them on two downstream tasks: part-of-speech (POS) tagging and text classification. Experiments demonstrate the effectiveness of our Lao models. We release our models and datasets to the community, hoping to facilitate the future development of Lao NLP applications.

Automatic text summarisation (ATS) (therein two main approaches–abstractive summarisation and extractive summarisation are involved) is an automatic procedure for extracting critical information from the text using a specific algorithm or method. Due to the scarcity of corpus, abstractive summarisation achieves poor performance for low-resource language ATS tasks. That’s why it is common for researchers to apply extractive summarisation to low-resource language instead of using abstractive summarisation. As an emerging branch of extraction-based summarisation, methods based on feature analysis quantitate the significance of information by calculating utility scores of each sentence in the article. In this study, we propose a simple but effective extractive method based on the Light Gradient Boosting Machine regression model for Indonesian documents. Four features are extracted, namely PositionScore, TitleScore, the semantic representation similarity between the sentence and the title of document, the semantic representation similarity between the sentence and sentence’s cluster center. We define a formula for calculating the sentence score as the objective function of the linear regression. Considering the characteristics of Indonesian, we use Indonesian lemmatisation technology to improve the calculation of sentence score. The results show that our method is more applicable.

Inthis paper, we take Indonesian as the research object, and propose a multiple filter correction framework (MFCF). The main idea of MFCF is to remove noise from candidate words to increase the probability of correct words being selected. In MFCF, we use window search algorithm (WSA) to filter the candidate words in the dictionary. When searching for candidate words whose Levenshtein distance is 1, WSA reduces the candidate word search space by an average of 71%. When searching for candidate words whose Levenshtein distance is 2, the search space is reduced by an average of 55%. The reduction in search space has brought about an increase in search speed. When WSA searches for candidate words with Levenshtein distance equal to 1 and 2, the speed exceeds the current advanced search algorithm. A character vector-based candidate word scoring model (CWSM-CV) is also introduced in this paper. CWSM-CV is a simple but unsupervised method. In MFCF, we use CWSM-CV to filter the correct word in the candidate word list. Through exploring the feasibility of using word vector-based candidate word scoring model to score candidate words (CWSM-WV), we find the necessity of denoising the candidate word list and verified it with experiments. In order to apply this finding to the text correction, a new set of evaluation indicators are proposed to replace accuracy. Finally, we recommend that researchers who correct text in low-resource languages ​​make the model an open system and publish it for users to use. The system receives user feedback as new data to gradually reduce the negative impact of data volume.

Meta-Reinforcement Learning (meta-RL) algorithms enable agents to adapt to new tasks from small amounts of exploration, based on the experience of similar tasks. Recent studies have pointed out that a good representation of a task is key to the success of off-policy context-based meta-RL. Inspired by contrastive methods in unsupervised representation learning, we propose a new method to learn the task representation based on the mutual information between transition tuples in a trajectory and the task embedding. We also propose a new estimation for task similarity based on Q-function, which can be used to form a constraint on the distribution of the encoded task variables, making the task encoder encode the task variables more effective on new tasks. Experiments on meta-RL tasks show that the newly proposed method outperforms existing meta-RL algorithms.

In visual-input sim-to-real scenarios, to overcome the reality gap between images rendered in simulators and those from the real world, domain adaptation, i.e., learning an aligned representation space between simulators and the real world, then training and deploying policies in the aligned representation, is a promising direction. Previous methods focus on same-modal domain adaptation. However, those methods require building and running simulators that render high-quality images, which can be difficult and costly. In this paper, we consider a more cost-efficient setting of visual-input sim-to-real where only low-dimensional states are simulated. We first point out that the objective of learning mapping functions in previous methods that align the representation spaces is ill-posed, prone to yield an incorrect mapping. When the mapping crosses modalities, previous methods are easier to fail. Our algorithm, Cross-mOdal Domain Adaptation with Sequential structure (CODAS), mitigates the ill-posedness by utilizing the sequential nature of the data sampling process in RL tasks. Experiments on MuJoCo and Hand Manipulation Suite tasks show that the agents deployed with our method achieve similar performance as it has in the source domain, while those deployed with previous methods designed for same-modal domain adaptation suffer a larger performance gap.

In reinforcement learning, experience replay stores past samples for further reuse. Prioritized sampling is a promising technique to better utilize these samples. Previous criteria of prioritization include TD error, recentness and corrective feedback, which are mostly heuristically designed. In this work, we start from the regret minimization objective, and obtain an optimal prioritization strategy for Bellman update that can directly maximize the return of the policy. The theory suggests that data with higher hindsight TD error, better on-policiness and more accurate Q value should be assigned with higher weights during sampling. Thus most previous criteria only consider this strategy partially. We not only provide theoretical justifications for previous criteria, but also propose two new methods to compute the prioritization weight, namely ReMERN and ReMERT. ReMERN learns an error network, while ReMERT exploits the temporal ordering of states. Both methods outperform previous prioritized sampling algorithms in challenging RL benchmarks, including MuJoCo, Atari and Meta-World.

Grammatical Error Correction (GEC) is a challenge in Natural Language Processing research. Although many researchers have been focusing on GEC in universal languages such as English or Chinese, few studies focus on Indonesian, which is a low-resource language. In this article, we proposed a GEC framework that has the potential to be a baseline method for Indonesian GEC tasks. This framework treats GEC as a multi-classification task. It integrates different language embedding models and deep learning models to correct 10 types of Part of Speech (POS) error in Indonesian text. In addition, we constructed an Indonesian corpus that can be utilized as an evaluation dataset for Indonesian GEC research. Our framework was evaluated on this dataset. Results showed that the Long Short-Term Memory model based on word-embedding achieved the best performance. Its overall macro-average F 0.5 in correcting 10 POS error types reached 0.551. Results also showed that the framework can be trained on a low-resource dataset.

In real-world decision-making tasks, learning an optimal policy without a trial-and-error process is an appealing challenge. When expert demonstrations are available, imitation learning that mimics expert actions can learn a good policy efficiently. Learning in simulators is another commonly adopted approach to avoid real-world trials-and-errors. However, neither sufficient expert demonstrations nor high-fidelity simulators are easy to obtain. In this work, we investigate policy learning in the condition of a few expert demonstrations and a simulator with misspecified dynamics. Under a mild assumption that local states shall still be partially aligned under a dynamics mismatch, we propose imitation learning with horizon-adaptive inverse dynamics (HIDIL) that matches the simulator states with expert states in a $H$-step horizon and accurately recovers actions based on inverse dynamics policies. In the real environment, HIDIL can effectively derive adapted actions from the matched states. Experiments are conducted in four MuJoCo locomotion environments with modified friction, gravity, and density configurations. Experiment results show that HIDIL achieves significant improvement in terms of performance and stability in all of the real environments, compared with imitation learning methods and transferring methods in reinforcement learning.

The concept of entropy of interval-valued intuitionistic fuzzy set (IvIFS) is first introduced. The close relationships between entropy and the similarity measure of interval-valued intuitionistic fuzzy sets are discussed in detail. We also obtain some important theorems by which entropy and similarity measure of IvIFSs can be transformed into each other based on their axiomatic definitions. Simultaneously, some formulae to calculate entropy and similarity measure of IvIFSs are put forward. © 2010 Wiley Periodicals, Inc.