BLADE: Benchmarking Language Model Agents for Data-Driven Science

Data-driven scientific discovery requires the iterative integration of scientific domain knowledge, statistical expertise, and an understanding of data semantics to make nuanced analytical decisions, e.g., about which variables, transformations, and statistical models to consider. LM-based agents equipped with planning, memory, and code execution capabilities have the potential to support data-driven science. However, evaluating agents on such open-ended tasks is challenging due to multiple valid approaches, partially correct steps, and different ways to express the same decisions. To address these challenges, we present BLADE, a benchmark to automatically evaluate agents' multifaceted approaches to open-ended research questions. BLADE consists of 12 datasets and research questions drawn from existing scientific literature, with ground truth collected from independent analyses by expert data scientists and researchers. To automatically evaluate agent responses, we developed corresponding computational methods to match different representations of analyses to this ground truth. Though language models possess considerable world knowledge, our evaluation shows that they are often limited to basic analyses. However, agents capable of interacting with the underlying data demonstrate improved, but still non-optimal, diversity in their analytical decision making. Our work enables the evaluation of agents for data-driven science and provides researchers deeper insights into agents' analysis approaches.

Reflecting the Male Gaze: Quantifying Female Objectification in 19th and 20th Century Novels

Inspired by the concept of the male gaze (Mulvey, 1975) in literature and media studies, this paper proposes a framework for analyzing gender bias in terms of female objectification: the extent to which a text portrays female individuals as objects of visual pleasure. Our framework measures female objectification along two axes. First, we compute an agency bias score that indicates whether male entities are more likely to appear in the text as grammatical agents than female entities. Next, by analyzing the word embedding space induced by a text (Caliskan et al., 2017), we compute an appearance bias score that indicates whether female entities are more closely associated with appearance-related words than male entities. Applying our framework to 19th and 20th century novels reveals evidence of female objectification in literature: we find that novels written from a male perspective systematically objectify female characters, while novels written from a female perspective do not exhibit statistically significant objectification of any gender.

Towards Understanding Underwater Weather Events in Rivers Using Autonomous Surface Vehicles

Climate change has increased the frequency and severity of extreme weather events such as hurricanes and winter storms. The complex interplay of floods with tides, runoff, and sediment creates additional hazards -- including erosion and the undermining of urban infrastructure -- consequently impacting the health of our rivers and ecosystems. Observations of these underwater phenomena are rare, because satellites and sensors mounted on aerial vehicles cannot penetrate the murky waters. Autonomous Surface Vehicles (ASVs) provides a means to track and map these complex and dynamic underwater phenomena. This work highlights preliminary results of high-resolution data gathering with ASVs, equipped with a suite of sensors capable of measuring physical and chemical parameters of the river. Measurements were acquired along the lower Schuylkill River in the Philadelphia area at high-tide and low-tide conditions. The data will be leveraged to improve our understanding of changes in bathymetry due to floods; the dynamics of mixing and stagnation zones and their impact on water quality; and the dynamics of suspension and resuspension of fine sediment. The data will also provide insight into the development of adaptive sampling strategies for ASVs that can maximize the information gain for future field experiments.

Constrained Sequence-to-Tree Generation for Hierarchical Text Classification

Hierarchical Text Classification (HTC) is a challenging task where a document can be assigned to multiple hierarchically structured categories within a taxonomy. The majority of prior studies consider HTC as a flat multi-label classification problem, which inevitably leads to "label inconsistency" problem. In this paper, we formulate HTC as a sequence generation task and introduce a sequence-to-tree framework (Seq2Tree) for modeling the hierarchical label structure. Moreover, we design a constrained decoding strategy with dynamic vocabulary to secure the label consistency of the results. Compared with previous works, the proposed approach achieves significant and consistent improvements on three benchmark datasets.

Hybrid Curriculum Learning for Emotion Recognition in Conversation

Emotion recognition in conversation (ERC) aims to detect the emotion label for each utterance. Motivated by recent studies which have proven that feeding training examples in a meaningful order rather than considering them randomly can boost the performance of models, we propose an ERC-oriented hybrid curriculum learning framework. Our framework consists of two curricula: (1) conversation-level curriculum (CC); and (2) utterance-level curriculum (UC). In CC, we construct a difficulty measurer based on "emotion shift" frequency within a conversation, then the conversations are scheduled in an "easy to hard" schema according to the difficulty score returned by the difficulty measurer. For UC, it is implemented from an emotion-similarity perspective, which progressively strengthens the model's ability in identifying the confusing emotions. With the proposed model-agnostic hybrid curriculum learning strategy, we observe significant performance boosts over a wide range of existing ERC models and we are able to achieve new state-of-the-art results on four public ERC datasets.

A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis

Aspect based sentiment analysis (ABSA) involves three fundamental subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification. Early works only focused on solving one of these subtasks individually. Some recent work focused on solving a combination of two subtasks, e.g., extracting aspect terms along with sentiment polarities or extracting the aspect and opinion terms pair-wisely. More recently, the triple extraction task has been proposed, i.e., extracting the (aspect term, opinion term, sentiment polarity) triples from a sentence. However, previous approaches fail to solve all subtasks in a unified end-to-end framework. In this paper, we propose a complete solution for ABSA. We construct two machine reading comprehension (MRC) problems, and solve all subtasks by joint training two BERT-MRC models with parameters sharing. We conduct experiments on these subtasks and results on several benchmark datasets demonstrate the effectiveness of our proposed framework, which significantly outperforms existing state-of-the-art methods.

Predicting the Popularity of Online Videos via Deep Neural Networks

Predicting the popularity of online videos is important for video streaming content providers. This is a challenging problem because of the following two reasons. First, the problem is both "wide" and "deep". That is, it not only depends on a wide range of features, but also be highly non-linear and complex. Second, multiple competitors may be involved. In this paper, we propose a general prediction model using the multi-task learning (MTL) module and the relation network (RN) module, where MTL can reduce over-fitting and RN can model the relations of multiple competitors. Experimental results show that our proposed approach significantly increases the accuracy on predicting the total view counts of TV series with RN and MTL modules.