Abstract

Identifying human values behind arguments is a complex task which requires understanding of premise, stance and conclusion together. We propose a method that uses a pre-trained lan- guage model, DeBERTa, to tokenize and con- catenate the text before feeding it into a fully connected neural network. We also show that leveraging the hierarchy in values improves the performance by .14 F1 score compared to only using level 2 values. Our code is made publicly available here.1

Abstract

This paper describes our system used in the SemEval-2023 Task 11 Learning With Dis- agreements (Le-Wi-Di). This is a subjective task since it deals with detecting hate speech, misogyny and offensive language. Thus, dis- agreement among annotators is expected. We experiment with different settings like loss functions specific for subjective tasks and in- clude anonymized annotator-specific informa- tion to help us understand the level of disagree- ment. We perform an in-depth analysis of the performance discrepancy of these differ- ent modelling choices. Our system achieves a cross-entropy of 0.58, 4.01 and 3.70 on the test sets of HS-Brexit, ArMIS and MD-Agreement, respectively. Our code implementation is pub- licly available.

Abstract

The Clickbait Challenge targets spoiling the clickbaits using short pieces of information known as spoilers to satisfy the curiosity in- duced by a clickbait post. The large context of the article associated with the clickbait and differences in the spoiler forms, make the task challenging. Hence, to tackle the large con- text, we propose an Information Condensation- based approach, which prunes down the unnec- essary context. Given an article, our filtering module optimised with a contrastive learning objective first selects the parapraphs that are the most relevant to the corresponding clickbait. The resulting condensed article is then fed to the two downstream tasks of spoiler type clas- sification and spoiler generation. We demon- strate and analyze the gains from this approach on both the tasks. Overall, we win the task of spoiler type classification and achieve competi- tive results on spoiler generation

Abstract

Clickbait is the text or a thumbnail image that entices the user to click the accompanying link. Clickbaits employ strategies while deliberately hiding the critical elements of the article and revealing partial information in the title, which arouses sufficient curiosity and motivates the user to click the link. In this work, we identify the kind of spoiler given a clickbait title. We formulate this as a text classification problem. We finetune pretrained transformer models on the title of the post and build models for theclickbait-spoiler classification. We achieve a balanced accuracy of 0.70 which is close to the baselin

Abstract

In this work, we introduce the problem of scenic routes among points in R d . The key development is the nature of the problem in terms of both defining the concept of scenic points and scenic routes and then coming up with algorithms that meet different criteria for the generated scenic routes. The scenic routes problem provides a visual trajectory for a user to comprehend the layout of high-dimensional points. The nature of this trajectory and the visual layout of the points have applications in comprehending the results of machine learning supervised and unsupervised learning techniques. We study the problem in 2D and 3D (with two color points) before exploring the issues in R d . The red/blue points in our examples could be to be in a class or not to be in a class. The applications could include landscape design to adhere to the scenic beauty of the artifacts on the ground. The generation of equally separated layouts for designing composite hardware where interference could be an issue. Keywords: sce

Abstract

Self-supervised speech based models have been found to be successful in predicting brain recordings of subjects experiencing naturalistic story listening. Inspired by the recent progress on deep learning models for various speech-processing tasks, existing literature has leveraged pretrained speech Transformer models for brain encoding. However, there is no work on exploring the efficacy of task-specific finetuned Transformer representations for this task. Hence, in this paper, we explore transfer learning from representations finetuned for eight different tasks from Speech processing Universal PERformance Benchmark (SUPERB) for predicting brain responses. Encoding models based on task features are used to predict activity in different regions across the whole brain, and also in language and auditory brain regions. Our experiments on finetuning the Wav2Vec2.0 model for these eight tasks show that the model finetuned on automatic speech recognition (ASR) yields the best encoding performance for the whole brain, language and auditory regions.

Abstract

How does the brain represent different modes of information? Can we design a system that automatically understands what the user is thinking? Such questions can be answered by studying brain recordings like functional magnetic resonance imaging (fMRI). As a first step, the neuroscience community has contributed several large cognitive neuroscience datasets related to passive reading/listening/viewing of concept words, narratives, pictures and movies. Encoding and decoding models using these datasets have also been proposed in the past two decades. These models serve as additional tools for basic research in cognitive science and neuroscience. Encoding models aim at generating fMRI brain representations given a stimulus automatically. They have several practical applications in evaluating and diagnosing neurological conditions and thus also help design therapies for brain damage. Decoding models solve the inverse problem of reconstructing the stimuli given the fMRI. They are useful for designing brain-machine or brain-computer interfaces. Inspired by the effectiveness of deep learning models for natural language processing, computer vision, and speech, recently several neural encoding and decoding models have been proposed. In this survey, we will first discuss popular representations of language, vision and speech stimuli, and present a summary of neuroscience datasets. Further, we will review popular deep learning based encoding and decoding architectures and note their benefits and limitations. Finally, we will conclude with a brief summary and discussion about future trends

Abstract

Syntactic parsing is the task of assigning a syntactic structure to a sentence. There are two popular syntactic parsing methods: constituency and dependency parsing. Recent works have used syntactic embeddings based on constituency trees, incremental top-down parsing, and other word syntactic features for brain activity prediction given the text stimuli to study how the syntax structure is represented in the brain’s language network. However, the effectiveness of dependency parse trees or the relative predictive power of the various syntax parsers across brain areas, especially for the listening task, is yet unexplored. In this study, we investigate the predictive power of the brain encoding models in three settings: (i) individual performance of the constituency and dependency syntactic parsing based embedding methods, (ii) efficacy of these syntactic parsing based embedding methods when controlling for basic syntactic signals, (iii) relative effectiveness of each of the syntactic embedding methods when controlling for the other. Further, we explore the relative importance of syntactic information (from these syntactic embedding methods) versus semantic information using BERT embeddings. We find that constituency parsers help explain activations in the temporal lobe and middle-frontal gyrus, while dependency parsers better encode syntactic structure in the angular gyrus and posterior cingulate cortex. Although semantic signals from BERT are more effective compared to any of the syntactic features or embedding methods, syntactic embedding methods explain additional v

Abstract

Deep Reinforcement learning is beginning to be useful for studying neural representations in the brain because of its ability to combine decision-making and representation. Here, we use it to study a dot motion perceptual decision-making task in a high-dimensional setting where the inputs are akin to those used in psychological experiments. This end-to-end model gives a unique insight into how these networks solve the task providing a background on how the brain could solve this task. We find that the network can show properties similar to the middle temporal visual area (MT) in the brain, which code for direction and motion strength. We find the emergence of direction selectivity purely through reward-based training and graded firing coding motion strength and make a testable prediction that the MT population would also have coherence-selective neurons.

Abstract

One of the challenges in stroke rehabilitation is to identify bio-markers that correlate with amelioratory changes in the recovery of brain function that can be verified by a clinician. For strokes related to upper extremity, clinicians use Fugl Meyer Assessment - Upper Extremity (FMA-UE) score for verification. We hypothesize that even before clinical measures of function recovery (FMA-UE) show facilitatory changes, structural and functional changes in the brain connectome indicate early changes in stroke patients. Toward establishing such early bio-markers of rehabilitation related changes in the brain plasticity, we propose to use graph theoretic measures on the structural (SC) and functional connectivity (FC) matrices. We used longitudinal multi-modal neuroimaging data acquired within 1 to 6 months of the onset of stroke and after 3 months of rehabilitation for 15 acute ischemic stroke subjects with deficit in motor