The ability of large vision-language models (LVLMs) to critique and correct their reasoning is an essential building block towards their self-improvement. However, a systematic analysis of such capabilities in LVLMs is still lacking. We propose VISCO, the first benchmark to extensively analyze the fine-grained critique and correction capabilities of LVLMs. Compared to existing work that uses a single scalar value to critique the entire reasoning [4], VISCO features dense and fine-grained critique, requiring LVLMs to evaluate the correctness of each step in the chain-of-thought and provide natural language explanations to support their judgments. Extensive evaluation of 24 LVLMs demonstrates that human-written critiques significantly enhance the performance after correction, showcasing the potential of the self-improvement strategy. However, the model-generated critiques are less helpful and sometimes detrimental to the performance, suggesting that critique is the crucial bottleneck. We identified three common patterns in critique failures: failure to critique visual perception, reluctance to "say no", and exaggerated assumption of error propagation. To address these issues, we propose an effective LookBack strategy that revisits the image to verify each piece of information in the initial reasoning. LookBack significantly improves critique and correction performance by up to 13.5%.

Humans recognize objects after observing only a few examples, a remarkable capability enabled by their inherent language understanding of the real-world environment. Developing verbalized and interpretable representation can significantly improve model generalization in low-data settings. In this work, we propose Verbalized Representation Learning (VRL), a novel approach for automatically extracting human-interpretable features for object recognition using few-shot data. Our method uniquely captures inter-class differences and intra-class commonalities in the form of natural language by employing a Vision-Language Model (VLM) to identify key discriminative features between different classes and shared characteristics within the same class. These verbalized features are then mapped to numeric vectors through the VLM. The resulting feature vectors can be further utilized to train and infer with downstream classifiers. Experimental results show that, at the same model scale, VRL achieves a 24% absolute improvement over prior state-of-the-art methods while using 95% less data and a smaller mode. Furthermore, compared to human-labeled attributes, the features learned by VRL exhibit a 20% absolute gain when used for downstream classification tasks. Code is available at: https://github.com/joeyy5588/VRL/tree/main.

Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities --- popular text, speech, and video datasets --- from their detailed sourcing trends and use restrictions to their geographical and linguistic representation. Our manual analysis covers nearly 4000 public datasets between 1990-2024, spanning 608 languages, 798 sources, 659 organizations, and 67 countries. We find that multimodal machine learning applications have overwhelmingly turned to web-crawled, synthetic, and social media platforms, such as YouTube, for their training sets, eclipsing all other sources since 2019. Secondly, tracing the chain of dataset derivations we find that while less than 33% of datasets are restrictively licensed, over 80% of the source content in widely-used text, speech, and video datasets, carry non-commercial restrictions. Finally, counter to the rising number of languages and geographies represented in public AI training datasets, our audit demonstrates measures of relative geographical and multilingual representation have failed to significantly improve their coverage since 2013. We believe the breadth of our audit enables us to empirically examine trends in data sourcing, restrictions, and Western-centricity at an ecosystem-level, and that visibility into these questions are essential to progress in responsible AI. As a contribution to ongoing improvements in dataset transparency and responsible use, we release our entire multimodal audit, allowing practitioners to trace data provenance across text, speech, and video.

We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos that align seamlessly with text prompts, with a frame rate of 16 fps and resolution of 768 x 1360 pixels. Previous video generation models often struggled with limited motion and short durations. It is especially difficult to generate videos with coherent narratives based on text. We propose several designs to address these issues. First, we introduce a 3D Variational Autoencoder (VAE) to compress videos across spatial and temporal dimensions, enhancing both the compression rate and video fidelity. Second, to improve text-video alignment, we propose an expert transformer with expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. Third, by employing progressive training and multi-resolution frame packing, CogVideoX excels at generating coherent, long-duration videos with diverse shapes and dynamic movements. In addition, we develop an effective pipeline that includes various pre-processing strategies for text and video data. Our innovative video captioning model significantly improves generation quality and semantic alignment. Results show that CogVideoX achieves state-of-the-art performance in both automated benchmarks and human evaluation. We publish the code and model checkpoints of CogVideoX along with our VAE model and video captioning model at https://github.com/THUDM/CogVideo.

Language agents have become a promising solution to complex interactive tasks. One of the key ingredients to the success of language agents is the reward model on the trajectory of the agentic workflow, which provides valuable guidance during training or inference. However, due to the lack of annotations of intermediate interactions, most existing works use an outcome reward model to optimize policies across entire trajectories. This may lead to sub-optimal policies and hinder the overall performance. To address this, we propose QLASS (Q-guided Language Agent Stepwise Search), to automatically generate annotations by estimating Q-values in a stepwise manner for open language agents. By introducing a reasoning tree and performing process reward modeling, QLASS provides effective intermediate guidance for each step. With the stepwise guidance, we propose a Q-guided generation strategy to enable language agents to better adapt to long-term value, resulting in significant performance improvement during model inference on complex interactive agent tasks. Notably, even with almost half the annotated data, QLASS retains strong performance, demonstrating its efficiency in handling limited supervision. We also empirically demonstrate that QLASS can lead to more effective decision making through qualitative analysis.

Xuan He, Da Yin, Nanyun Peng. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

AI agents today are mostly siloed — they either retrieve and reason over vast amount of digital information and knowledge obtained online; or interact with the physical world through embodied perception, planning and action — but rarely both. This separation limits their ability to solve tasks that require integrated physical and digital intelligence, such as cooking from online recipes, navigating with dynamic map data, or interpreting real-world landmarks using web knowledge. We introduce \textsc{Embodied Web Agents}, a novel paradigm for AI agents that fluidly bridge embodiment and web-scale reasoning. To operationalize this concept, we first develop the \textsc{Embodied Web Agents} task environments, a unified simulation platform that integrates realistic 3D indoor and outdoor environments with functional web interfaces. Building upon this platform, we construct and release the \textsc{Embodied Web Agents} Benchmark, which encompasses a diverse suite of tasks including cooking, navigation, shopping, tourism, and geolocation — all requiring coordinated reasoning across physical and digital realms for systematic assessment of cross-domain intelligence. Experimental results reveal significant performance gaps between state-of-the-art AI systems and human capabilities, establishing both challenges and opportunities at the intersection of embodied cognition and web-scale knowledge access.

Layered parameter estimation represents a crucial application of ground penetrating radar (GPR), playing a pivotal role in reconstructing the internal structures of media. In situations where adjacent media are similar and multiple reflected waves are present, conventional methods face substantial challenges in detecting weak echoes and accurately extracting time delays. To achieve precise estimation of layered media parameters in the presence of similar materials and multiple reflected waves, this paper presents a modified Orthogonal Matching Pursuit (OMP) parameter estimation method. This method extracts the correct time delays by eliminating multiple reflected waves and integrates the constructed generalized reflection coefficients to recover the signal. Subsequently, a genetic algorithm is utilized to optimize the constructed objective function, enabling the precise estimation of the thicknesses and permittivities of adjacent layers with similar media. This method is particularly applicable to scenarios involving two or more subsurface layers with nearly identical permittivities. Finally, numerical and real experiments have been conducted to validate the accuracy and effectiveness of the proposed method.

Large Language Models (LLMs) have become integral components in various autonomous agent systems.In this study, we present an exploration-based trajectory optimization approach, referred to as ETO.This learning method is designed to enhance the performance of open LLM agents.Contrary to previous studies that exclusively train on successful expert trajectories, our method allows agents to learn from their exploration failures.This leads to improved performance through an iterative optimization framework.During the exploration phase, the agent interacts with the environment while completing given tasks, gathering failure trajectories to create contrastive trajectory pairs.In the subsequent training phase, the agent utilizes these trajectory preference pairs to update its policy using contrastive learning methods like DPO (Rafailov et al., 2023).This iterative cycle of exploration and training fosters continued improvement in the agents.Our experiments on three complex tasks demonstrate that ETO consistently surpasses baseline performance by a large margin.Furthermore, an examination of task-solving efficiency and potential in scenarios lacking expert trajectory underscores the effectiveness of our approach.1

Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, Bill Yuchen Lin. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

We present MIRACLE, a system for online, interpretable visual concept and video action recognition. Through a chat interface, users query the recognition system with an uploaded image or video. For images, MIRACLE returns concept predictions from its structured knowledge base, justifying its predictions with heatmaps and natural language-based attribute detections. For videos, MIRACLE predicts an action and justifies its prediction with time varying entity-entity relations. With its ability to learn new concepts in an online, few-shot manner and its support of dynamic changes to its knowledge base, MIRACLE represents a step forward in interpretable multimodal learning systems.

General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data, assembled into corpora such as C4, RefinedWeb, and Dolma. To our knowledge, we conduct the first, large-scale, longitudinal audit of the consent protocols for the web domains underlying AI training corpora. Our audit of 14,000 web domains provides an expansive view of crawlable web data and how codified data use preferences are changing over time. We observe a proliferation of AI-specific clauses to limit use, acute differences in restrictions on AI developers, as well as general inconsistencies between websites' expressed intentions in their Terms of Service and their robots.txt. We diagnose these as symptoms of ineffective web protocols, not designed to cope with the widespread re-purposing of the internet for AI. Our longitudinal analyses show that in a single year (2023-2024) there has been a rapid crescendo of data restrictions from web sources, rendering ~5\%+ of all tokens in C4, or 28%+ of the most actively maintained, critical sources in C4, fully restricted from use. For Terms of Service crawling restrictions, a full 45% of C4 is now restricted. If respected or enforced, these restrictions are rapidly biasing the diversity, freshness, and scaling laws for general-purpose AI systems. We hope to illustrate the emerging crises in data consent, for both developers and creators. The foreclosure of much of the open web will impact not only commercial AI, but also non-commercial AI and academic research.

In the rapidly evolving field of Large Language Models (LLMs), ensuring safety is a crucial and widely discussed topic. However, existing works often overlooks the geo-diversity of cultural and legal standards across the world. To reveal the chal5 lenges posed by geo-diverse safety standards, we introduce SafeWorld, a novel benchmark specifically designed to evaluate LLMs’ ability to generate responses that are not only helpful but also culturally sensitive and legally compliant across diverse global contexts. SafeWorld encompasses 2,775 test user queries, each grounded in high-quality, human-verified cultural norms and legal policies from 50 countries and 493 regions/races. On top of it, we propose a multi-dimensional automatic safety evaluation framework that assesses the contextual appropriateness, accuracy, and comprehensiveness of responses. Our evaluations reveal that current LLMs struggle to meet these criteria effectively. To enhance LLMs’ alignment with geo-diverse safety standards, we synthesize helpful preference pairs for Direct Preference Optimization (DPO) alignment. The preference pair construction aims to encourage LLMs to behave appropriately and provide precise references to relevant cultural norms and policies when necessary. Our trained SafeWorldLM outperforms all competing models, including GPT-4o on all the three evaluation dimensions by a large margin. Global human evaluators also note a nearly 20% higher winning rate in helpfulness and harmfulness evaluation.

A key goal for the advancement of AI is to develop technologies that serve the needs not just of one group but of all communities regardless of their geographical re-gion. In fact, a significant proportion of knowledge is locally shared by people from certain regions but may not apply equally in other regions because of cultural dif-ferences. If a model is unaware of regional character-istics, it may lead to performance disparity across re-gions and result in bias against underrepresented groups. We propose GIVL, a Geographically Inclusive Vision-and-Language Pre-trained model. There are two attributes of geo-diverse visual concepts which can help to learn geo-diverse knowledge: 1) concepts under similar categories have unique knowledge and visual characteristics, 2) concepts with similar visual features may fall in completely different categories. Motivated by the attributes, we de-sign new pre-training objectives Image-Knowledge Matching (IKM) and Image Edit Checking (IEC) to pre-train GIVL. Compared with similar-size models pre-trained with similar scale of data, GIVL achieves state-of-the-art (SOTA) and more balanced performance on geo-diverse V &L tasks. Code and data are released at https://github.com/WadeYin9712/GIVL.

Instruction tuning has emerged to enhance the capabilities of large language models (LLMs) to comprehend instructions and generate appropriate responses.Existing methods either manually annotate or employ LLM (e.g., GPTseries) to generate data for instruction tuning.However, they often overlook associating instructions with existing annotated datasets.In this paper, we propose DYNOSAUR, a dynamic growth paradigm for the automatic curation of instruction-tuning data.Based on the metadata of existing datasets, we use LLMs to automatically construct instruction-tuning data by identifying relevant data fields and generating appropriate instructions.By leveraging the existing annotated datasets, DYNOSAUR offers several advantages: 1) it reduces the API cost for generating instructions (e.g., it costs less than $12 USD by calling GPT-3.5-turbo for generating 800K instruction tuning samples; 2) it provides high-quality data for instruction tuning (e.g., it performs better than ALPACA and FLAN on SUPER-NI and LONGFORM with comparable data sizes); and 3) it supports the continuous improvement of models by generating instruction-tuning data when a new annotated dataset becomes available.We further investigate a continual learning scheme for learning with the ever-growing instruction-tuning dataset, and demonstrate that replaying tasks with diverse instruction embeddings not only helps mitigate forgetting issues but generalizes to unseen tasks better.

The fast development of science and technology is accompanied by the booming of cutting edge research. Researchers need to digest more and more recently published publications in order to keep themselves up to date. This becomes tough in particular with the prevalence of preprint publishing such as arXiv, where inspiring works could come out without being peer-reviewed. Is that possible to design an automatic system to help researchers quickly gain a glimpse of a piece of work or gain useful background knowledge for deeply understanding it To this end, we proposed a practical framework called Master Reading Tree (MRT) to trace the evolution of scientific publications. In this framework, we can build annotated evolution roadmaps for publications and identify important previous works or evolution tracks by generating expressive embeddings and clustering them into various groups. With comprehensive evaluations, our proposed framework demonstrates its superior capability in capturing underlying relations behind publications over several baseline algorithms. Finally, we integrated the proposed MRT framework on AMiner, an online academic platform, where users can generate roadmaps using MRT for free and their interactions are further used to refine the model.

Spatial commonsense, the knowledge about spatial position and relationship between objects (like the relative size of a lion and a girl, and the position of a boy relative to a bicycle when cycling), is an important part of commonsense knowledge.Although pretrained language models (PLMs) succeed in many NLP tasks, they are shown to be ineffective in spatial commonsense reasoning.Starting from the observation that images are more likely to exhibit spatial commonsense than texts, we explore whether models with visual signals learn more spatial commonsense than text-based PLMs.We propose a spatial commonsense benchmark that focuses on the relative scales of objects, and the positional relationship between people and objects under different actions.We probe PLMs and models with visual signals, including visionlanguage pretrained models and image synthesis models, on this benchmark, and find that image synthesis models are more capable of learning accurate and consistent spatial knowledge than other models.The spatial knowledge from image synthesis models also helps in natural language understanding tasks that require spatial commonsense.Code and data are available at https://github.com/ xxxiaol/spatial-commonsense.

Text-to-image generative models have achieved unprecedented success in generating highquality images based on natural language descriptions.However, it is shown that these models tend to favor specific social groups when prompted with neutral text descriptions (e.g., 'a photo of a lawyer').Following Zhao et al. (2021), we study the effect on the diversity of the generated images when adding ethical intervention that supports equitable judgment (e.g., 'if all individuals can be a lawyer irrespective of their gender') in the input prompts.To this end, we introduce an Ethical NaTural Language Interventions in Text-to-Image GENeration (ENTIGEN) benchmark dataset to evaluate the change in image generations conditional on ethical interventions across three social axesgender, skin color, and culture.Through ENTI-GEN framework, we find that the generations from minDALL•E, DALL•E-mini and Stable Diffusion cover diverse social groups while preserving the image quality.Preliminary studies indicate that a large change in the model predictions is triggered by certain phrases such as 'irrespective of gender' in the context of gender bias in the ethical interventions.We release code and annotated data at https://github. com/Hritikbansal/entigen_emnlp.

Recent work has shown that Pre-trained Language Models (PLMs) store the relational knowledge learned from data and utilize it for performing downstream tasks.However, commonsense knowledge across different regions may vary.For instance, the color of bridal dress is white in American weddings whereas it is red in Chinese weddings.In this paper, we introduce a benchmark dataset, Geo-diverse Commonsense Multilingual Language Models Analysis (GEOMLAMA), for probing the diversity of the relational knowledge in multilingual PLMs.GEOMLAMA contains 3,125 prompts in English, Chinese, Hindi, Persian, and Swahili, with a wide coverage of concepts shared by people from American, Chinese, Indian, Iranian and Kenyan cultures.We benchmark 11 standard multilingual PLMs on GE-OMLAMA.Interestingly, we find that 1) larger multilingual PLMs variants do not necessarily store geo-diverse concepts better than its smaller variant; 2) multilingual PLMs are not intrinsically biased towards knowledge from the Western countries (the United States); 3) the native language of a country may not be the best language to probe its knowledge and 4) a language may better probe knowledge about a nonnative country than its native country.

Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency.However, automatic evaluation in NLG is still dominated by similarity-based metrics, and we lack a reliable framework for a more comprehensive evaluation of advanced models.In this paper, we propose a unified multi-dimensional evaluator UNIEVAL for NLG.We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.Furthermore, thanks to the unified Boolean QA format, we are able to introduce an intermediate learning phase that enables UNIEVAL to incorporate external knowledge from multiple related tasks and gain further improvement.Experiments on three typical NLG tasks show that UNIEVAL correlates substantially better with human judgments than existing metrics.Specifically, compared to the top-performing unified evaluators, UNIEVAL achieves a 23% higher correlation on text summarization, and over 43% on dialogue response generation.Also, UNIEVAL demonstrates a strong zero-shot learning ability for unseen evaluation dimensions and tasks.Source code, data and all pre-trained evaluators are available on our GitHub repository 1 . Generated Summary:Harry Kane is nominated for both the PFA player and young player of the season.The Spurs striker has been released from the awards ceremony on Sunday.The Tottenham striker features in a new animation.Reference Summary: Harry Kane has been in superb form for Tottenham this season.The 21-year-old has scored 30 goals in all competitions for Spurs.Kane also made his England debut and scored within two minutes.Document: Harry Kane's celebrations this season have always shown him to be an animated young man . . .Similarity-based Evaluators ROUGE-1: 0.44 ROUGE-2: 0.25 ROUGE-L: 0.42 BERTScore: 0.24 Single-dimensional Evaluators (predicted by two different evaluators (Deng et al., 2021)) Consistency: 0.87 Relevance: 0.74 Unified Evaluator (predicted by BARTScore, and the scoring range is negative infinity to 0) Precision: -5.45 Recall: -4.93 F1: -5.19

Academic Knowledge Services have substantially facilitated the development of human science and technology, providing a plenitude of useful research tools. However, many applications highly depend on ad-hoc models and expensive human labeling to understand professional contents, hindering deployments in real world. To create a unified backbone language model for various knowledge-intensive academic knowledge mining challenges, based on the world's largest public academic graph Open Academic Graph (OAG), we pre-train an academic language model, namely OAG-BERT, to integrate massive heterogeneous entity knowledge beyond scientific corpora. We develop novel pre-training strategies along with zero-shot inference techniques. OAG-BERT's superior performance on 9 knowledge-intensive academic tasks (including 2 demo applications) demonstrates its qualification to serve as a foundation for academic knowledge services. Its zero-shot capability also offers great potential to mitigate the need of costly annotations. OAG-BERT has been deployed to multiple real-world applications, such as reviewer recommendations for NSFC (National Nature Science Foundation of China) and paper tagging in the AMiner system. All codes and pre-trained models are available via the CogDL.

Commonsense is defined as the knowledge that is shared by everyone.However, certain types of commonsense knowledge are correlated with culture and geographic locations and they are only shared locally.For example, the scenarios of wedding ceremonies vary across regions due to different customs influenced by historical and religious factors.Such regional characteristics, however, are generally omitted in prior work.In this paper, we construct a Geo-Diverse Visual Commonsense Reasoning dataset (GD-VCR) to test vision-and-language models' ability to understand cultural and geo-location-specific commonsense.In particular, we study two state-of-the-art Vision-and-Language models, VisualBERT and ViLBERT trained on VCR, a standard multimodal commonsense benchmark with images primarily from Western regions.We then evaluate how well the trained models can generalize to answering the questions in GD-VCR.We find that the performance of both models for non-Western regions including East Asia, South Asia, and Africa is significantly lower than that for Western region.We analyze the reasons behind the performance disparity and find that the performance gap is larger on QA pairs that: 1) are concerned with culture-related scenarios, e.g., weddings, religious activities, and festivals; 2) require high-level geo-diverse commonsense reasoning rather than low-order perception and recognition.Dataset and code are released at https://github.com/ WadeYin9712/GD-VCR.

Large-scale pre-trained language models have demonstrated strong capabilities of generating realistic texts. However, it remains challenging to control the generation results. Previous approaches such as prompting are far from sufficient, and lack of controllability limits the usage of language models. To tackle this challenge, we propose an innovative method, inverse prompting, to better control text generation. The core idea of inverse prompting is to use generated text to inversely predict the prompt during beam search, which enhances the relevance between the prompt and the generated text and thus improves controllability. Empirically, we pre-train a large-scale Chinese language model to perform a systematic study using human evaluation on the tasks of open-domain poem generation and open-domain long-form question answering. Results demonstrate that our proposed method substantially outperforms the baselines and that our generation quality is close to human performance on some of the tasks.

Xiao Liu, Da Yin, Yansong Feng, Yuting Wu, Dongyan Zhao. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir Radev. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e.g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e.g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a recent similar work DALL-E.

Aspect term extraction is a fundamental task for aspect-level sentiment analysis. Previous methods tend to extract noun aspect terms due to the large quantities of them, and perform badly on extracting aspect terms containing words with other POS tags, according to experimental results. In addition, few works focus on the POS tags of adjacent words which are critical to aspect term extraction. We propose a novel model which combines POS and word features in an interactive way, and makes full use of the POS tags of adjacent words by POS window. We conduct experiments on two datasets, and prove the effectiveness of our model.

Pre-trained visually grounded language models such as ViLBERT, LXMERT, and UNITER have achieved significant performance improvement on vision-and-language tasks but what they learn during pre-training remains unclear. In this work, we demonstrate that certain attention heads of a visually grounded language model actively ground elements of language to image regions. Specifically, some heads can map entities to image regions, performing the task known as entity grounding. Some heads can even detect the syntactic relations between non-entity words and image regions, tracking, for example, associations between verbs and regions corresponding to their arguments. We denote this ability as syntactic grounding. We verify grounding both quantitatively and qualitatively, using Flickr30K Entities as a testbed.

We propose SentiBERT, a variant of BERT that effectively captures compositional sentiment semantics.The model incorporates contextualized representation with binary constituency parse tree to capture semantic composition.Comprehensive experiments demonstrate that SentiBERT achieves competitive performance on phrase-level sentiment classification.We further demonstrate that the sentiment composition learned from the phrase-level annotations on SST can be transferred to other sentiment analysis tasks as well as related tasks, such as emotion classification tasks.Moreover, we conduct ablation studies and design visualization methods to understand SentiBERT.We show that SentiBERT is better than baseline approaches in capturing negation and the contrastive relation and model the compositional sentiment semantics.

In this paper, we propose an interactive multi-grained joint model for targeted sentiment analysis. Firstly, different from previous works, we leverage the correlation between target and sentiment clues and deeply strengthen interaction between them because targets are highly related to the sentiment clues in a sentence. Moreover, we apply a multi-layer structure to consider multi-grained target and sentiment tagging information more comprehensively. Also, we design two specific loss functions to prevent a word from being both part of a target and a sentiment clue simultaneously, and to align the boundary information of two labeling subsystems. We conduct experiments on English and Spanish datasets and the experimental results show that our approach substantially outperforms a variety of previous models and achieves new state-of-the-art results on these datasets.