While Large Reasoning Models (LRMs) have demonstrated remarkable capabilities through explicit Chain-of-Thought (CoT) generation, they frequently suffer from "overthinking".In this work, we bridge this gap by introducing Token-level Marginal Utility, which quantifies the per-token log-probability gain of the ground-truth answer.Leveraging this dense supervision signal, we propose MUTO (Marginal Utility Guided Thinking Optimization), a unified training framework designed to synthesize concise reasoning chains.Rather than relying only on coarse trajectory-level length control, MUTO identifies tokens that reduce the model's likelihood of the correct answer and penalizes such negative-utility reasoning, yielding concise yet effective CoT trajectories.Experiments on DeepSeek-R1-Distill-Qwen backbones (1.5B and 7B) across six math reasoning benchmarks show that MUTO yields a markedly better efficiency-accuracy Pareto frontier.It reduces average token usage by 87.1% at 1.5B while improving accuracy by 2.3%, and cuts tokens by 80.2% at 7B with only -0.1% accuracy change, achieving the best length-normalized accuracy among baselines.

Xinyu Zhang, Linmei Hu, Luhao Zhang, Wentao Cheng, Yashen Wang, Ge Shi, Chong Feng, Liqiang Nie. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Existing video LLMs typically excel at capturing the overall description of a video but lack the ability to demonstrate an understanding of temporal dynamics and a fine-grained grasp of localized content within the video. In this paper, we propose a Time-Perception Enhanced Video Grounding via Boundary Perception and Temporal Reasoning aimed at mitigating LLMs’ difficulties in understanding the discrepancies between video and text temporality. Specifically, to address the inherent biases in current datasets, we design a series of boundary-perception tasks to enable LLMs to capture accurate video temporality. To tackle LLMs’ insufficient understanding of temporal information, we develop specialized tasks for boundary perception and temporal relationship reasoning to deepen LLMs’ perception of video temporality. Our experimental results show significant improvements across three datasets: ActivityNet, Charades, and DiDeMo (achieving up to 11.2% improvement on [email protected]), demonstrating the effectiveness of our proposed temporal awareness-enhanced data construction method.

Large Language Models(LLMs) have brought significant transformations to various aspects of human life and productivity. However, the heavy reliance on vast amounts of data in developing these models has resulted in a notable disadvantage for low-resource languages, such as Nuosu and others, which lack large datasets. Moreover, many LLMs exhibit significant performance discrepancies between high-and lowresource languages, thereby restricting equitable access to technological advances for all linguistic communities. To address these challenges, this paper propose a low-resource multilingual large language model, termed VEEF-Multi-LLM, constructed through effective vocabulary expansion and parameter-efficient fine-tuning. We introduce a series of innovative methods to address challenges in low-resource languages. First, we adopt Byte-level Byte-Pair Encoding to expand the vocabulary for broader multilingual support. We separate input and output embedding weights to boost performance, and apply RoPE for long-context handling, as well as RMSNorm for efficient training. To generate high-quality supervised fine-tuning (SFT) data, we use self-training and selective translation, and refine the resulting dataset with the assistance of native speakers to ensure cultural and linguistic accuracy. Our model, VEEF-Multi-LLM-8B, is trained on 600 billion tokens across 50 natural and 16 programming languages. Experimental results show that the model excels in multilingual instruction-following tasks, particularly in translation, outperforming competing models in benchmarks such as XCOPA and XStoryCloze. Although it lags slightly behind English-centric models in some tasks (e.g., m-MMLU), it prioritizes safety, reliability, and inclusivity, making it valuable for diverse linguistic communities. We open-source our models on GitHub and Huggingface.

Text-Centric Visual Question Answering (TEC-VQA) serves as a key benchmark for evaluating AI's ability to reason over text-rich visual scenes.However, most existing TEC-VQA datasets focus on high-resource languages and are susceptible to benchmark contamination due to overlap with pretraining corpora of large models.These limitations severely hinder progress in low-resource language scenarios and compromise the reliability of current evaluations.To address both the underrepresentation of low-resource languages and the contamination issue, we propose TVQACML, the first large-scale TEC-VQA benchmark for multilingual Chinese minority languages, constructed through a scalable, reproducible pipeline.It comprises 8,000 real-world images and 32,000 high-quality QA pairs across eight languages and 30 application scenarios.We conduct comprehensive benchmarking of open-source, closed-source, and text-centric MLLMs, revealing substantial performance gaps from human accuracy, especially in scenetext and document understanding tasks.Furthermore, instruction tuning with TVQACML yields consistent performance gains, in some cases surpassing leading closed models demonstrating the dataset's utility for model alignment.We also introduce a lightweight, extensible evaluation metric for robust multilingual, multi-format answer assessment.The code and dataset for TVQACML are available at https://github.com/Shajiu/TVQACML.

In-Image Machine Translation (IIMT) aims to translate images containing texts from one language to another. Current research of end-to-end IIMT mainly conducts on synthetic data, with simple background, single font, fixed text position, and bilingual translation, which can not fully reflect real world, causing a significant gap between the research and practical conditions. To facilitate research of IIMT in real-world scenarios, we explore Practical In-Image Multilingual Machine Translation (IIMMT). In order to convince the lack of publicly available data, we annotate the PRIM dataset, which contains real-world captured one-line text images with complex background, various fonts, diverse text positions, and supports multilingual translation directions. We propose an end-to-end model VisTrans to handle the challenge of practical conditions in PRIM, which processes visual text and background information in the image separately, ensuring the capability of multilingual translation while improving the visual quality. Experimental results indicate the VisTrans achieves a better translation quality and visual effect compared to other models. The code and dataset are available at: https://github.com/BITHLP/PRIM.

While automated CT report generation (CTRG) systems promise to enhance clinical workflow efficiency, current solutions, even those based on advanced multi-modal large language models (MLLMs), face fundamental challenges in ensuring report quality and reliability. Through systematic analysis of representation dynamics in MLLM-based CTRG models, we discover that existing systems lack robust quality discrimination capabilities, manifesting in two critical limitations: representation entanglement between reports of varying quality levels in the feature space, and quality-insensitive generation due to conventional training paradigms focusing solely on ground-truth reports. To address these limitations, we propose CT-ClearView, a quality-aware cross-modal alignment framework consisting of two key innovations: (1) a systematic methodology for constructing clinically-relevant hard negative examples using GPT-4, which introduces subtle but significant clinical errors while maintaining report structure and plausibility, and (2) a contrastive learning framework that leverages these examples to effectively disentangle representations of varying quality reports and enhance the model's sensitivity to clinical details. Extensive experiments on CTRG-Chest-548K and CTRG-Brain-263K datasets demonstrate significant performance improvements in natural language generation (NLG) metrics compared to existing approaches (e.g., increases of 11% in BLEU-1 and 16% in both BLEU-4 and ROUGE-L, on the CTRG-Chest-548K datasets).

Large language models (LLMs), such as ChatGPT and LLama, have shown remarkable capability in a wide range of natural language tasks. However, the current LLMs are mainly concentrated in resource-rich languages, such as English and Chinese. For low-resource language such as Tibetan, research and applications related to LLMs are still in their infancy. To address the existing gap, we present a method to enhance LLaMA with the ability to understand and generate Tibetan text, as well as to follow instructions. This is achieved by creating large-scale unsupervised pre-training and supervised fine-tuning datasets, which mitigate the limited availability of Tibetan data. Additionally, we expand LLaMA’s vocabulary by incorporating Tibetan tokens through Unigram tokenization, thereby improving both its encoding efficiency and semantic understanding of Tibetan. Furthermore, we conduct secondary pre-training and fine-tune the model using the constructed datasets, thereby enhancing its capability to interpret and execute instructions effectively. To verify the effectiveness of the model, we establish ten evaluation benchmarks for Tibetan. The experimental results indicate that the proposed model significantly enhances the LLaMA’s proficiency in understanding and generating Tibetan content. To promote further research, we release our model and inference resources at https://github.com/Shajiu/Tibetan-LLaMA-2 .

Jiawei Li, Yizhe Yang, Yu Bai, Xiaofeng Zhou, Yinghao Li, Huashan Sun, Yuhang Liu, Xingpeng Si, Yuhao Ye, Yixiao Wu, Yiguan Lin, Bin Xu, Bowen Ren, Chong Feng, Yang Gao, Heyan Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Move structures have been studied in English for Specific Purposes (ESP) and English for Academic Purposes (EAP) for decades. However, there are few move annotation corpora for Research Article (RA) abstracts. In this paper, we introduce RAAMove, a comprehensive multi-domain corpus dedicated to the annotation of move structures in RA abstracts. The primary objective of RAAMove is to facilitate move analysis and automatic move identification. This paper provides a thorough discussion of the corpus construction process, including the scheme, data collection, annotation guidelines, and annotation procedures. The corpus is constructed through two stages: initially, expert annotators manually annotate high-quality data; subsequently, based on the human-annotated data, a BERT-based model is employed for automatic annotation with the help of experts’ modification. The result is a large-scale and high-quality corpus comprising 33,988 annotated instances. We also conduct preliminary move identification experiments using the BERT-based model to verify the effectiveness of the proposed corpus and model. The annotated corpus is available for academic research purposes and can serve as essential resources for move analysis, English language teaching and writing, as well as move/discourse-related tasks in Natural Language Processing (NLP).

Multimodal Large Language Models (MLLMs) have shown significant potential for chart understanding and generation. However, they are still far from achieving the desired effectiveness in practical applications. This could be due to the limitations of the used training chart data. Existing chart datasets suffer from scarcity of chart types, limited coverage of tasks, and insufficient scalability, making them incapable of effectively enhancing the chart-related capabilities of MLLMs. To tackle these obstacles, we construct NovaChart, a large-scale dataset for chart understanding and generation of MLLMs. NovaChart contains 47K high-resolution chart images and 856K chart-related instructions, covering 18 different chart types and 15 unique tasks of chart understanding and generation. To build NovaChart, we propose a data generation engine for metadata curation, chart visualization and instruction formulation. Chart metadata in NovaChart contains detailed annotations, i.e., data points, visual elements, source data and the visualization code of every chart. This additional information endows NovaChart with considerable scalability, as it can facilitate the extension of chart instruction data to a larger scale and greater diversity. We utilize NovaChart to train several open-source MLLMs. Experimental results demonstrate NovaChart empowers MLLMs with stronger capabilities in 15 chart understanding and generation tasks by a large-margin (35.47%-619.47%), bringing them a step closer to smart chart assistants. Our dataset is now available at https://github.com/Elucidator-V/NovaChart.

Domain adaptation proves to be an effective solution for addressing inadequate translation performance within specific domains. However, the straightforward approach of mixing data from multiple domains to obtain the multi-domain neural machine translation (NMT) model can give rise to the parameter interference between domains problem, resulting in a degradation of overall performance. To address this, we introduce a multi-domain adaptive NMT method aimed at learning domain specific sub-layer latent variable and employ the Gumbel-Softmax reparameterization technique to concurrently train both model parameters and domain specific sub-layer latent variable. This approach facilitates learning private domain-specific knowledge while sharing common domain-invariant knowledge, effectively mitigating the parameter interference problem. The experimental results show that our proposed method significantly improved by up to 7.68 and 3.71 BLEU compared with the baseline model in English-German and Chinese-English public multi-domain datasets, respectively.

Image Emotion Classification (IEC) is an essential research area, offering valuable insights into user emotional states for a wide range of applications, including opinion mining, recommendation systems, and mental health treatment. The challenges associated with IEC are mainly attributed to the complexity and ambiguity of human emotions, the lack of a universally accepted emotion model, and excessive dependence on prior knowledge. To address these challenges, we propose a novel Unified Generative framework for Image Emotion Classification (UGRIE), which is capable of simultaneously modeling various emotion models and capturing intricate semantic relationships between emotion labels. Our approach employs a flexible natural language template, converting the IEC task into a template-filling process that can be easily adapted to accommodate a diverse range of IEC tasks. To further enhance the performance, we devise a mapping mechanism to seamlessly integrate the multimodal pre-training model CLIP with the text generation pre-training model BART, thus leveraging the strengths of both models. A comprehensive set of experiments conducted on multiple public datasets demonstrates that our proposed method consistently outperforms existing approaches to a large margin in supervised settings, exhibits remarkable performance in low-resource scenarios, and unifies distinct emotion models within a single, versatile framework.

In recent years, researchers have shown an increased interest in recognizing the overlapping entities that have nested structures. However, most existing models ignore the semantic correlation between words under different entity types. Considering words in sentence play different roles under different entity types, we argue that the correlation intensities of pairwise words in sentence for each entity type should be considered. In this paper, we treat named entity recognition as a multi-class classification of word pairs and design a simple neural model to handle this issue. Our model applies a supervised multi-head self-attention mechanism, where each head corresponds to one entity type, to construct the word-level correlations for each type. Our model can flexibly predict the span type by the correlation intensities of its head and tail under the corresponding type. In addition, we fuse entity boundary detection and entity classification by a multitask learning framework, which can capture the dependencies between these two tasks. To verify the performance of our model, we conduct extensive experiments on both nested and flat datasets. The experimental results show that our model can outperform the previous state-of-the-art methods on multiple tasks without any extra NLP tools or human annotations.

While various neural machine translation (NMT) methods have integrated mono-lingual syntax knowledge into the linguistic representation of sequence-to-sequence, no research is available on aligning the syntactic structures of target language with the corresponding source language syntactic structures. This work shows the first attempt of a source-target bilingual syntactic alignment approach SyntAligner by mutual information maximization-based self-supervised neural deep modeling. Building on the word alignment for NMT, our SyntAligner firstly aligns the syntactic structures of source and target sentences and then maximizes their mutual dependency by introducing a lower bound on their mutual information. In SyntAligner, the syntactic structure of span granularity is represented by transforming source or target word hidden state into a source or target syntactic span vector. A border-sensitive span attention mechanism then captures the correlation between the source and target syntactic span vectors, which also captures the self-attention between span border-words as alignment bias. Lastly, a self-supervised bilingual syntactic mutual information maximization-based learning objective dynamically samples the aligned syntactic spans to maximize their mutual dependency. Experiment results on three typical NMT tasks: WMT'14 English to German, IWSLT'14 German to English, and NC'11 English to French show the SyntAligner effectiveness and universality of syntactic alignment.

Multi-head self-attention recently attracts enormous interest owing to its specialized functions, significant parallelizable computation, and flexible extensibility.However, very recent empirical studies show that some selfattention heads make little contribution and can be pruned as redundant heads.This work takes a novel perspective of identifying and then vitalizing redundant heads.We propose a redundant head enlivening (RHE) method to precisely identify redundant heads, and then vitalize their potential by learning syntactic relations and prior knowledge in text without sacrificing the roles of important heads.Two novel syntax-enhanced attention (SEA) mechanisms: a dependency mask bias and a relative local-phrasal position bias, are introduced to revise self-attention distributions for syntactic enhancement in machine translation.The importance of individual heads is dynamically evaluated during the redundant heads identification, on which we apply SEA to vitalize redundant heads while maintaining the strength of important heads.Experimental results on WMT14 and WMT16 English→German and English→Czech language machine translation validate the RHE effectiveness.

While various neural machine translation (NMT) methods have integrated multiple prior knowledge to guide the translation, no research is available on combining with source-target bilingual translation template. In this paper, we firstly propose a maximal-length noun phrase template (MNP-Template), which constructs a novel translation template focusing on the constituency syntactic structure. Secondly, building on the multi-source transformer framework, we design a template-based machine translation (TBMT) model to integrate the syntactic knowledge of the retrieved target template similar to the ground-truth translation in the NMT decoder. Experiment results show the effectiveness of MNP- Template and TBMT on test subsets filtered by the fuzzy match score. Moreover, our method achieves significant improvement in out-of-domain test sets, which well-validated the university across diverse domains.

More and more online resources for computer science are introduced, used and released in scientific literature in recent years. Knowledge about the usage of these online resources can help researchers easily find the applicable resources for their works. However, most existing methods ignore the importance of the content of the online resource citations. To this end, we manually create SciR, a dataset that contains 3,012 annotation sentences for this task, and introduce a multi-task learning framework to automatically extract the entities and relations from the context of online resource citations in scientific papers. Furthermore, considering the words in a sentence usually play different roles under different relations. In this paper, we treat different relations as distinctive sub-spaces and model the correlations between words in sentence for each relation type by a supervised biaffine attention network. Based on this relation-aware attention network, our model can not only effectively obtain the word-level correlations under each relation, but also naturally avoid the problem of overlapping relations. To evaluate the effectiveness of our model, we conduct comprehensive experiments on three datasets and the experimental results demonstrate that our model outperforms other state-of-the-art methods on the two tasks of entity recognition and relation extraction.

The Graph Convolutional Network (GCN) is a universal relation extraction method that can predict relations of entity pairs by capturing sentences’ syntactic features. However, existing GCN methods often use dependency parsing to generate graph matrices and learn syntactic features. The quality of the dependency parsing will directly affect the accuracy of the graph matrix and change the whole GCN’s performance. Because of the influence of noisy words and sentence length in the distant supervised dataset, using dependency parsing on sentences causes errors and leads to unreliable information. Therefore, it is difficult to obtain credible graph matrices and relational features for some special sentences. In this article, we present a Multi-Graph Cooperative Learning model (MGCL), which focuses on extracting the reliable syntactic features of relations by different graphs and harnessing them to improve the representations of sentences. We conduct experiments on a widely used real-world dataset, and the experimental results show that our model achieves the state-of-the-art performance of relation extraction.

Since the length of microblog texts, such as tweets, is strictly limited to 140 characters, traditional Information Retrieval techniques suffer from the vocabulary mismatch problem severely and cannot yield good performance in the context of microblogosphere. To address this critical challenge, in this paper, we focus on the use of local conceptual word embeddings for enhance microblog retrieval effectiveness. In particular, we propose a novel k-Nearest Neighbor (kNN) based Query Expansion (QE) algorithm to generate words from local word embeddings to expand the original query, which leads to better understanding of the information need. Besides, in order to further satisfy users' real-time information need, we incorporate temporal evidences into the expansion algorithm, which can boost recent tweets in the retrieval results with respect to a given topic. Experimental results on the official TREC Twitter corpora demonstrate the significant superiority of our approach over baseline methods.

Context. The improvements made in the last couple of decades in the requirements engineering (RE) processes and methods have witnessed a rapid rise in effectively using diverse machine learning (ML) techniques to resolve several multifaceted RE issues. One such challenging issue is the effective identification and classification of the software requirements on Stack Overflow (SO) for building quality systems. The appropriateness of ML-based techniques to tackle this issue has revealed quite substantial results, much effective than those produced by the usual available natural language processing (NLP) techniques. Nonetheless, a complete, systematic, and detailed comprehension of these ML based techniques is considerably scarce. Objective. To identify or recognize and classify the kinds of ML algorithms used for software requirements identification primarily on SO. Method. This paper reports a systematic literature review (SLR) collecting empirical evidence published up to May 2020. Results. This SLR study found 2,484 published papers related to RE and SO. The data extraction process of the SLR showed that (1) Latent Dirichlet Allocation (LDA) topic modeling is among the widely used ML algorithm in the selected studies and (2) precision and recall are amongst the most commonly utilized evaluation methods for measuring the performance of these ML algorithms. Conclusion. Our SLR study revealed that while ML algorithms have phenomenal capabilities of identifying the software requirements on SO, they still are confronted with various open problems/issues that will eventually limit their practical applications and performances. Our SLR study calls for the need of close collaboration venture between the RE and ML communities/researchers to handle the open issues confronted in the development of some real world machine learning-based quality systems.

In this paper, we proposed LCX-MAC (local coordination X-MAC) as an extension of X-MAC. X-MAC is an asynchronous duty cycle medium access control (MAC) protocol. X-MAC used one important technique of short preamble which is to allow sender nodes to quickly send their actual data when the corresponding receivers wake up. X-MAC node keeps sending short preamble to wake up its receiver node, which causes energy, increases transmission delay, and makes the channel busy since a lot of short preambles are discarded, as these days Internet of Things (IoT) healthcare with different sensor nodes for the healthcare is time-critical applications and needs a quick response. A possible improvement over X-MAC is that local information of each node will share with its neighbour node. This local information exchanged will cause much less overhead than in the nodes which are synchronized. To calculate the effect of this the local coordination on X-MAC in this paper, we built an analytical model of LCX-MAC that incorporates the local coordination in X-MAC. The analytical results show that LCX-MAC outperformed X-MAC and X-MAC/BEB in terms of throughput, delay, and energy.

Food recommender systems play an important role in assisting users to identify the desired food to eat. Deciding what food to eat is a complex and multi-faceted process, which is influenced by many factors such as the ingredients, appearance of the recipe, the user's personal preference on food, and various contexts like what had been eaten in the past meals. This work formulates the food recommendation problem as predicting user preference on recipes based on three key factors that determine a user's choice on food, namely, 1) the user's (and other users') history; 2) the ingredients of a recipe; and 3) the descriptive image of a recipe. To address this challenging problem, this work develops a dedicated neural network-based solution Hierarchical Attention based Food Recommendation (HAFR) which is capable of: 1) capturing the collaborative filtering effect like what similar users tend to eat; 2) inferring a user's preference at the ingredient level; and 3) learning user preference from the recipe's visual images. To evaluate our proposed method, this work constructs a large-scale dataset consisting of millions of ratings from AllRecipes.com. Extensive experiments show that our method outperforms several competing recommender solutions like Factorization Machine and Visual Bayesian Personalized Ranking with an average improvement of 12%, offering promising results in predicting user preference on food.

Distant supervision for relation extraction is an efficient method to reduce labor costs and has been widely used to seek novel relational facts in large corpora, which can be identified as a multi-instance multi-label problem. However, existing distant supervision methods suffer from selecting important words in the sentence and extracting valid sentences in the bag. Towards this end, we propose a novel approach to address these problems in this paper. Firstly, we propose a linear attenuation simulation to reflect the importance of words in the sentence with respect to the distances between entities and words. Secondly, we propose a non-independent and identically distributed (non-IID) relevance embedding to capture the relevance of sentences in the bag. Our method can not only capture complex information of words about hidden relations, but also express the mutual information of instances in the bag. Extensive experiments on a benchmark dataset have well-validated the effectiveness of the proposed method.

He Zhao, Zhunchen Luo, Chong Feng, Anqing Zheng, Xiaopeng Liu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Targeted sentiment classification aims to identify the sentiment expressed towards some targets given context sentences, having great application value in social media, ecommerce platform and other fields. Most of the previous methods model context and target words with RNN and attention mechanism, which primarily do not use any external knowledge. In this paper, we utilize external knowledge from knowledge bases to reinforce the semantic representation of context and target. We propose a new model called Knowledge Powered Attention Network (KPAN), which uses the multi-head attention mechanism to represent target and context and to fuse with conceptual knowledge extracted from external knowledge bases. The experiments on three public datasets revealed that our proposed model outperforms the state-of-the-art methods, which signify the validity of our model.

Sequential labeling-based named entity recognition approaches restrict each word belonging to at most one entity region, which will have a problem when recognizing the nested named entities. Various models for nested named entity recognition are designed explicitly and usually do not perform well on non-overlapping named entity recognition compared to sequence labeling models. To tackle the aforementioned problem, we propose a novel model named Attention-Based Entity Region Networks (AERNs) for multi-grained entity recognition where multiple entities in a sentence could be non-overlapping or nested. AERNs consist of an entity region recognizer that examines all possible entity regions and an entity region classifier for classifying the regions. Context information is incorporated to improve the performance of named entity recognition by using an attention mechanism that helps the model focus on entity-related context information. Experiments show that AERNs can effectively recognize both nested and non-overlapping entities, and improves the state-of-the-art result by around 3% on several benchmarks datasets.

Network representation learning (NRL) is a crucial method to learn low-dimensional vertex representations to capture network information. However, conventional NRL models only regard each edge as a binary or continuous value while neglecting the rich semantic information on edges. To enhance network representation for Social Relation Extraction (SRE) task, we present a novel deep neural network based model, EsiNet, by learning the structure and semantic information of edges simultaneously. Compared with previous work, EsiNet focuses on further learning the interactions between vertices and capturing the correlations between labels. By jointly optimizing the objective function of these two components, EsiNet can preserve both the semantic and structural information of edges. Extensive experiments on several public datasets demonstrate that EsiNet outperforms other baselines significantly, by around 3% to 5% on hits@10 absolutely.

In this paper, we introduce the task of resource citation classification for scientific literature using a context-based framework. This task is to analyze the purpose of citing an on-line resource in scientific text by modeling the role and function of each resource citation. It can be incorporated into resource indexing and recommendation systems to help better understand and classify on-line resources in scientific literature. We propose a new annotation scheme for this task and develop a dataset of 3,088 manually annotated resource citations. We adopt a neural-based model to build the classifiers and apply them on the large ARC dataset to examine the revolution of scientific resources from trends in their function over time.

Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions.Previous studies address this problem by discovering a shared space across genres using manually crafted features, which requires great human effort.To effectively automate this process, we design a genre-separation network, which applies two encoders, one genreindependent and one genre-shared, to explicitly extract genre-specific and genre-agnostic features.Then we train a relation classifier using the genre-agnostic features on the source genre and directly apply to the target genre.Experiment results on three distinct genres of the ACE dataset show that our approach achieves up to 6.1% absolute F1-score gain compared to previous methods.By incorporating a set of external linguistic features, our approach outperforms the state-of-the-art by 1.7% absolute F1 gain.We make all programs of our model publicly available for research purpose 1 .

Most short-text embedding models typically represent each short-text only using the literal meanings of the words, which makes these models indiscriminative for the ubiquitous polysemy. In order to enhance the semantic representation capability of the short-texts, we (i) propose a novel short-text conceptualization algorithm to assign the associated concepts for each short-text, and then (ii) introduce the conceptualization results into learning the conceptual short-text embeddings. Hence, this semantic representation is more expressive than some widely-used text representation models such as the latent topic model. Wherein, the short-text conceptualization algorithm used here is based on a novel co-ranking framework, enabling the signals (i.e., the words and the concepts) to fully interplay to derive the solid conceptualization for the short-texts. Afterwards, we further extend the conceptual short-text embedding models by utilizing an attention-based model that selects the relevant words within the context to make more efficient prediction. The experiments on the real-world datasets demonstrate that the proposed conceptual short-text embedding model and short-text conceptualization algorithm are more effective than the state-of-the-art methods.

We tackle the problem of improving microblog retrieval algorithms by proposing a Feedback Concept Model for query expansion. In particular, we expand the query using knowledge information derived from Probase so that the expanded one could better reflect users' search intent, which allows for microblog retrieval at a concept-level, rather than term-level. In the proposed feedback concept model: (i) we mine the concept information implicit in short-texts based on the external knowledge bases; (ii) with the relevant concepts associated with short-texts, a mixture model is generated to estimate a concept language model; (iii) finally, we utilize the concept language model for query expansion. Moreover, we incorporate temporal prior into the proposed query expansion method to satisfy real-time information need. Finally, we test the generalization power of the feedback concept model on the TREC Microblog corpora. The experimental results demonstrate that the proposed model outperforms the previous methods for microblog retrieval significantly.

The string-to-tree model is one of the most successful syntax-based statistical machine translation (SMT) models. It models the grammaticality of the output via target-side syntax. However, it does not use any semantic information and tends to produce translations containing semantic role confusions and error chunk sequences. In this paper, we propose two methods to use semantic roles to improve the performance of the string-to-tree translation model: (1) adding role labels in the syntax tree; (2) constructing a semantic role tree, and then incorporating the syntax information into it. We then perform string-to-tree machine translation using the newly generated trees. Our methods enable the system to train and choose better translation rules using semantic information. Our experiments showed significant improvements over the state-of-the-art string-to-tree translation system on both spoken and news corpora, and the two proposed methods surpass the phrase-based system on large-scale training data.

Most sentence embedding models typically represent each sentence only using word surface, which makes these models indiscriminative for ubiquitous homonymy and polysemy.In order to enhance representation capability of sentence, we employ conceptualization model to assign associated concepts for each sentence in the text corpus, and then learn conceptual sentence embedding (CSE).Hence, this semantic representation is more expressive than some widely-used text representation models such as latent topic model, especially for short-text.Moreover, we further extend CSE models by utilizing a local attention-based model that select relevant words within the context to make more efficient prediction.In the experiments, we evaluate the CSE models on two tasks, text classification and information retrieval.The experimental results show that the proposed models outperform typical sentence embed-ding models.