Peer review is central to academic publishing, but the growing volume of submissions is straining the process. This motivates the development of computational approaches to support peer review. While each review is tailored to a specific paper, reviewers often make assessments according to certain aspects such as Novelty, which reflect the values of the research community. This alignment creates opportunities for standardizing the reviewing process, improving quality control, and enabling computational support. While prior work has demonstrated the potential of aspect analysis for peer review assistance, the notion of aspect remains poorly formalized. Existing approaches often derive aspects from review forms and guidelines, yet data-driven methods for aspect identification are underexplored. To address this gap, our work takes a bottom-up approach: we propose an operational definition of aspect and develop a data-driven schema for deriving aspects from a corpus of peer reviews. We introduce a dataset of peer reviews augmented with aspects and show how it can be used for community-level review analysis. We further show how the choice of aspects can impact downstream applications, s
In \cite{[NE]} we introduce $α$-expansions a real numbers in $(0,1]$, given by \[ \sum_{i=1}^{\infty}(α-1)^{i-1}α^{-(d_{1}+\dots+d_{i})}\] with $α>1$ and $d_{i}\in\mathbb{N}$ and discuss ergodic theoretical and dimension theoretical aspects of this expansions. In this sequel we study mutifractal aspects of this expansions.
This paper is a continuation of a series of works, devoted to various aspects of the 1908 Tunguska event. In this paper its author would like to draw attention to some geophysical aspects of the 1908 Tunguska event. A review of some geophysical aspects and some minor analysis of the aspects is presented in this paper. Special attention is paid to global seismic events at those times. As the epicenter of the forest-fall was in the center of a paleovolcano, so some info concerning the paleovolcano is presented. An idea was put forward about possible relationship of the geophysical peculiarities with the atmospheric optical anomalies reported at those times.
Different aspects of application of non-Euclidian geometries in architectural compositions are considered. These aspects are illustrated by examples of Armenian (medieval and contemporary) architectural compositions.
Recently, natural language generation (NLG) evaluation has shifted from a single-aspect to a multi-aspect paradigm, allowing for a more accurate assessment. Large language models (LLMs) achieve superior performance on various NLG evaluation tasks. However, current work often employs the LLM to independently evaluate different aspects, which largely ignores the rich correlation between various aspects. To fill this research gap, in this work, we propose an NLG evaluation metric called CoAScore. Powered by LLMs, the CoAScore utilizes multi-aspect knowledge through a CoA (\textbf{C}hain-\textbf{o}f-\textbf{A}spects) prompting framework when assessing the quality of a certain aspect. Specifically, for a given aspect to evaluate, we first prompt the LLM to generate a chain of aspects that are relevant to the target aspect and could be useful for the evaluation. We then collect evaluation scores for each generated aspect, and finally, leverage the knowledge of these aspects to improve the evaluation of the target aspect. We evaluate CoAScore across five NLG evaluation tasks (e.g., summarization, dialog response generation, etc) and nine aspects (e.g., overall quality, relevance, coherenc
Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e.g., consistency and naturalness) to obtain a comprehensive assessment. However, multi-aspect evaluation remains challenging as it may require the evaluator to generalize to any given evaluation aspect even if it's absent during training. In this paper, we introduce X-Eval, a two-stage instruction tuning framework to evaluate the text in both seen and unseen aspects customized by end users. X-Eval consists of two learning stages: the vanilla instruction tuning stage that improves the model's ability to follow evaluation instructions, and an enhanced instruction tuning stage that exploits the connections between fine-grained evaluation aspects to better assess text quality. To support the training of X-Eval, we collect AspectInstruct, the first instruction tuning dataset tailored for multi-aspect NLG evaluation spanning 27 diverse evaluation aspects with 65 tasks. To enhance task diversity, we devise an augmentation strategy that converts human rating annotations into diverse forms of NLG evaluation tasks, including scoring, comparison, ranking, and Boolean question answering. Ext
Aspect-oriented software development builds upon object-oriented development by offering additional abstraction boundaries that help us separate different types of requirements into so-called aspects. Given a legacy OO application, it pays to identify existing aspects to help understand the structure of the application and potentially to extract those aspects into separate software modules that can be maintained and reused individually. We present an approach to extract functional aspects using program slicing. We first characterize what we mean by functional aspect, and explore the extent to which program slicing techniques could improve over existing aspect mining and feature location methods for such aspects. We then describe the results of applying our approach to two medium-sized open source programs. Our preliminary results show that program slicing can yield well-defined functional aspects when the appropriate slicing criteria are used. Finally, we explore the effect of design quality on the candidate functional aspects.
Many web-search queries serve as the beginning of an exploration of an unknown space of information, rather than looking for a specific web page. To answer such queries effec- tively, the search engine should attempt to organize the space of relevant information in a way that facilitates exploration. We describe the Aspector system that computes aspects for a given query. Each aspect is a set of search queries that together represent a distinct information need relevant to the original search query. To serve as an effective means to explore the space, Aspector computes aspects that are orthogonal to each other and to have high combined coverage. Aspector combines two sources of information to compute aspects. We discover candidate aspects by analyzing query logs, and cluster them to eliminate redundancies. We then use a mass-collaboration knowledge base (e.g., Wikipedia) to compute candidate aspects for queries that occur less frequently and to group together aspects that are likely to be "semantically" related. We present a user study that indicates that the aspects we compute are rated favorably against three competing alternatives -related searches proposed by Google, cluster la
In this study recent drawings made by physics students are investigated. These drawings are part of reports made during experimenting. Aspects of drawings are chosen for investigation that are linked to basic physical notions like plasticity and spatiality. Also the aspects are required to link to the motor recognition experience during drawing, of the one who made the drawing. In this way the aim is to clarify the individual notions of space and time that are basic to performing the experiments. These are called the attitude with which the experiment is performed. Some aspects of these drawings tend to be correlated in several trends. Polanyi's theory of consciousness is generalised to explain why this correlation of aspects occurs. The correlation trends and attitudes can be related to each other. The results are presented in a schematic way to facilitate interpretation of the concepts introduced and of the correlation results.
In this thesis, we explore the aspects of symmetry, topology and anomalies in quantum matter with entanglement from both condensed matter and high energy theory viewpoints. The focus of our research is on the gapped many-body quantum systems including symmetry-protected topological states and topologically ordered states. Chapter 1. Introduction. Chapter 2. Geometric phase, wavefunction overlap, spacetime path integral and topological invariants. Chapter 3. Aspects of Symmetry. Chapter 4. Aspects of Topology. Chapter 5. Aspects of Anomalies. Chapter 6. Quantum Statistics and Spacetime Surgery. Chapter 7. Conclusion: Finale and A New View of Emergence-Reductionism. (Thesis supervisor: Prof. Xiao-Gang Wen)
Aspects ([aspε], "ASsociation PositionnellE/ProbabilistE de CaTalogues de Sources" in French) is a Fortran 95 code for the cross-identification of astrophysical sources. Its source files are freely available. Given the coordinates and positional uncertainties of all the sources in two catalogs K and K', Aspects computes the probability that an object in K and one in K' are the same or that they have no counterpart. Three exclusive assumptions are considered: (1) Several-to-one associations: a K-source has at most one counterpart in K', but a K'-source may have several counterparts in K; (2) One-to-several associations: the same with K and K' swapped; (3) One-to-one associations: a K-source has at most one counterpart in K' and vice versa. To compute the probabilities of association, Aspects needs the a priori (i.e. ignoring positions) probability that an object has a counterpart. The code obtains estimates of this quantity by maximizing the likelihood to observe all the sources at their effective positions under each assumption. The likelihood may also be used to determine the most appropriate model, given the data, or to estimate the typical positional uncertainty if unknown.
Aspects of small x physics at HERA are discussed in honor of the work of Lev Lipatov, who influenced and motivated a whole generation of physicists to investigate this new region of phase space. The introduction of transverse momentum dependent parton densities is one of the essential aspects of small x and BFKL physics, and its extension to all flavors with application to various processes marks a new milestone.
We present a model for aggregation of product review snippets by joint aspect identification and sentiment analysis. Our model simultaneously identifies an underlying set of ratable aspects presented in the reviews of a product (e.g., sushi and miso for a Japanese restaurant) and determines the corresponding sentiment of each aspect. This approach directly enables discovery of highly-rated or inconsistent aspects of a product. Our generative model admits an efficient variational mean-field inference algorithm. It is also easily extensible, and we describe several modifications and their effects on model structure and inference. We test our model on two tasks, joint aspect identification and sentiment analysis on a set of Yelp reviews and aspect identification alone on a set of medical summaries. We evaluate the performance of the model on aspect identification, sentiment analysis, and per-word labeling accuracy. We demonstrate that our model outperforms applicable baselines by a considerable margin, yielding up to 32% relative error reduction on aspect identification and up to 20% relative error reduction on sentiment analysis.
Lectures at the 1998 Les Houches Summer School: Topological Aspects of Low Dimensional Systems. These lectures contain an introduction to various aspects of Chern-Simons gauge theory: (i) basics of planar field theory, (ii) canonical quantization of Chern-Simons theory, (iii) Chern-Simons vortices, and (iv) radiatively induced Chern-Simons terms.
We study homological and homotopical aspects of Gorenstein flat modules over a ring with respect to a duality pair $(\mathcal{L,A})$. These modules are defined as cycles of exact chain complexes with components in $\mathcal{L}$ which remain exact after tensoring by objects in $\mathcal{A} \cap {}^\perp\mathcal{A} = \mathcal{A} \cap \Big( \bigcap_{i \in \mathbb{Z}_{> 0}} {\rm Ker}({\rm Ext}^i_{R^{\rm o}}(-,\mathcal{A})) \Big)$. In the case where $(\mathcal{L,A})$ is product closed and bicomplete (meaning in addition that $\mathcal{L}$ is closed under extensions, (co)products, $R \in \mathcal{L}$, $(\mathcal{A,L})$ is also a duality pair, and $\mathcal{A}$ is the right half of a hereditary complete cotorsion pair) we prove that these relative Gorenstein flat modules are closed under extensions, and that the corresponding Gorenstein flat dimension is well behaved in the sense that it recovers many of the properties and characterizations of its (absolute) Gorenstein flat counterpart (for instance, it can be described in terms of torsion functors). The latter in turn is a consequence of a Pontryagin duality relation that we show between these relative Gorenstein flat modules and cert
Aspect-based recommendation methods extract aspect terms from reviews, such as price, to model fine-grained user preferences on items, making them a critical approach in personalized recommender systems. Existing methods utilize graphs to represent the relationships among users, items, and aspect terms, modeling user preferences based on graph neural networks. However, they overlook the dynamic nature of user interests - users may temporarily focus on aspects they previously paid little attention to - making it difficult to assign accurate weights to aspect terms for each user-item interaction. In this paper, we propose a long-short-term aspect interest Transformer (LSA) for aspect-based recommendation, which effectively captures the dynamic nature of user preferences by integrating both long-term and short-term aspect interests. Specifically, the short-term interests model the temporal changes in the importance of recently interacted aspect terms, while the long-term interests consider global behavioral patterns, including aspects that users have not interacted with recently. Finally, LSA combines long- and short-term interests to evaluate the importance of aspects within the unio
Multimodal aspect-based sentiment analysis (MABSA) aims to extract aspects from text-image pairs and recognize their sentiments. Existing methods make great efforts to align the whole image to corresponding aspects. However, different regions of the image may relate to different aspects in the same sentence, and coarsely establishing image-aspect alignment will introduce noise to aspect-based sentiment analysis (i.e., visual noise). Besides, the sentiment of a specific aspect can also be interfered by descriptions of other aspects (i.e., textual noise). Considering the aforementioned noises, this paper proposes an Aspect-oriented Method (AoM) to detect aspect-relevant semantic and sentiment information. Specifically, an aspect-aware attention module is designed to simultaneously select textual tokens and image blocks that are semantically related to the aspects. To accurately aggregate sentiment information, we explicitly introduce sentiment embedding into AoM, and use a graph convolutional network to model the vision-text and text-text interaction. Extensive experiments demonstrate the superiority of AoM to existing methods. The source code is publicly released at https://github.c
Multi-aspect dense retrieval aims to incorporate aspect information (e.g., brand and category) into dual encoders to facilitate relevance matching. As an early and representative multi-aspect dense retriever, MADRAL learns several extra aspect embeddings and fuses the explicit aspects with an implicit aspect "OTHER" for final representation. MADRAL was evaluated on proprietary data and its code was not released, making it challenging to validate its effectiveness on other datasets. We failed to reproduce its effectiveness on the public MA-Amazon data, motivating us to probe the reasons and re-examine its components. We propose several component alternatives for comparisons, including replacing "OTHER" with "CLS" and representing aspects with the first several content tokens. Through extensive experiments, we confirm that learning "OTHER" from scratch in aspect fusion is harmful. In contrast, our proposed variants can greatly enhance the retrieval performance. Our research not only sheds light on the limitations of MADRAL but also provides valuable insights for future studies on more powerful multi-aspect dense retrieval models. Code will be released at: https://github.com/sunxiaoji
Dense retrieval methods have been mostly focused on unstructured text and less attention has been drawn to structured data with various aspects, e.g., products with aspects such as category and brand. Recent work has proposed two approaches to incorporate the aspect information into item representations for effective retrieval by predicting the values associated with the item aspects. Despite their efficacy, they treat the values as isolated classes (e.g., "Smart Homes", "Home, Garden & Tools", and "Beauty & Health") and ignore their fine-grained semantic relation. Furthermore, they either enforce the learning of aspects into the CLS token, which could confuse it from its designated use for representing the entire content semantics, or learn extra aspect embeddings only with the value prediction objective, which could be insufficient especially when there are no annotated values for an item aspect. Aware of these limitations, we propose a MUlti-granulaRity-aware Aspect Learning model (MURAL) for multi-aspect dense retrieval. It leverages aspect information across various granularities to capture both coarse and fine-grained semantic relations between values. Moreover, MURAL
Information Retrieval evaluation has traditionally focused on defining principled ways of assessing the relevance of a ranked list of documents with respect to a query. Several methods extend this type of evaluation beyond relevance, making it possible to evaluate different aspects of a document ranking (e.g., relevance, usefulness, or credibility) using a single measure (multi-aspect evaluation). However, these methods either are (i) tailor-made for specific aspects and do not extend to other types or numbers of aspects, or (ii) have theoretical anomalies, e.g. assign maximum score to a ranking where all documents are labelled with the lowest grade with respect to all aspects (e.g., not relevant, not credible, etc.). We present a theoretically principled multi-aspect evaluation method that can be used for any number, and any type, of aspects. A thorough empirical evaluation using up to 5 aspects and a total of 425 runs officially submitted to 10 TREC tracks shows that our method is more discriminative than the state-of-the-art and overcomes theoretical limitations of the state-of-the-art.