Search Results for author:
Found 95 papers, 40 papers with code
Can Question Generation Debias Question Answering Models? A Case Study on Question–Context Lexical Overlap
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question–context lexical overlap.
Virtual Citation Proximity (VCP): Empowering Document Recommender Systems by Learning a Hypothetical In-Text Citation-Proximity Metric for Uncited Documents
The prediction can be used in the same way as real citation proximity to calculate document relatedness, even for uncited documents.
Incorporating the Rhetoric of Scientific Language into Sentence Embeddings using Phrase-guided Distant Supervision and Metric Learning
Communicative functions are an important rhetorical feature of scientific writing.
Building Dataset for Grounding of Formulae — Annotating Coreference Relations Among Math Identifiers
Therefore, coreference relations between symbols need to be identified for grounding, and the task has aspects of both description alignment and coreference analysis.
Predicting Numerals in Natural Language Text Using a Language Model Considering the Quantitative Aspects of Numerals
In this task, we use two evaluation metrics to evaluate the language models in terms of the symbolic and quantitative aspects of the numerals, respectively.
Towards Grounding of Formulae
Our results indicate that it is worthwhile to grow the techniques for the proposed task to contribute to the further progress of mathematical language processing.
Neural Media Bias Detection Using Distant Supervision With BABE - Bias Annotations By Experts
Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0. 804, outperforming existing methods.
A Simple Yet Effective Corpus Construction Method for Chinese Sentence Compression
To remedy this shortcoming, we present a dependency-tree-based method to construct a Chinese corpus with 151k pairs of sentences and compression based on Chinese language-specific characteristics.
Eigenpruning
We introduce eigenpruning, a method that removes singular values from weight matrices in an LLM to improve its performance in a particular task.
Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange
In this study, we adopted a two-step approach for investigating the proficiency of LLMs in answering mathematical questions.
TWOLAR: a TWO-step LLM-Augmented distillation method for passage Reranking
In this paper, we present TWOLAR: a two-stage pipeline for passage reranking based on the distillation of knowledge from Large Language Models (LLM).
MAGPIE: Multi-Task Media-Bias Analysis Generalization for Pre-Trained Identification of Expressions
MAGPIE confirms that MTL is a promising approach for addressing media bias detection, enhancing the accuracy and efficiency of existing models.
SKT5SciSumm - A Hybrid Generative Approach for Multi-Document Scientific Summarization
Summarization for scientific text has shown significant benefits both for the research community and human society.
A Survey of Pre-trained Language Models for Processing Scientific Text
The number of Language Models (LMs) dedicated to processing scientific text is on the rise.
Taxonomy of Mathematical Plagiarism
Second, we analyze the best-performing approaches to detect plagiarism and mathematical content similarity on the newly established taxonomy.
Solving Label Variation in Scientific Information Extraction via Multi-Task Learning
The complexity of this task is compounded by the necessity for domain-specific knowledge and the limited availability of annotated data.
Probing Physical Reasoning with Counter-Commonsense Context
In this study, we create a CConS (Counter-commonsense Contextual Size comparison) dataset to investigate how physical commonsense affects the contextualized size comparison task; the proposed dataset consists of both contexts that fit physical commonsense and those that do not.
TEIMMA: The First Content Reuse Annotator for Text, Images, and Math
This demo paper presents the first tool to annotate the reuse of text, images, and mathematical formulae in a document pair -- TEIMMA.
SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation
In this paper, we provide a feasible definition of dialogue segmentation points with the help of document-grounded dialogues and release a large-scale supervised dataset called SuperDialseg, containing 9, 478 dialogues based on two prevalent document-grounded dialogue corpora, and also inherit their useful dialogue-related annotations.
Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection
A unified benchmark encourages the development of more robust systems and shifts the current paradigm in media bias detection evaluation towards solutions that tackle not one but multiple media bias types simultaneously.
Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering
To explain the predicted answers and evaluate the reasoning abilities of models, several studies have utilized underlying reasoning (UR) tasks in multi-hop question answering (QA) datasets.
Multi-hop Question Answering
Open-Ended Question Answering
+1
Cross-Modal Similarity-Based Curriculum Learning for Image Captioning
Moreover, the higher model performance on difficult examples and unseen data also demonstrates the generalization ability.
Which Shortcut Solution Do Question Answering Models Prefer to Learn?
We assume that the learnability of shortcuts, i. e., how easy it is to learn a shortcut, is useful to mitigate the problem.
Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering
Contrary to our expectations, although models become sensitive to the four types of perturbations, we find that the OOD generalization is not improved.
Caching and Reproducibility: Making Data Science experiments faster and FAIRer
In that case, the overall effort to iteratively improve the software and rerun the experiments creates significant time pressure on the researchers.
Exploiting Transformer-based Multitask Learning for the Detection of Media Bias in News Articles
Media has a substantial impact on the public perception of events.
Debiasing Masks: A New Framework for Shortcut Mitigation in NLU
We propose a new debiasing method in which we identify debiased pruning masks that can be applied to a finetuned model.
Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering
Specifically, we find that when the relative positions in a training set are biased, the performance on examples with relative positions unseen during training is significantly degraded.
How Well Do Multi-hop Reading Comprehension Models Understand Date Information?
Other results reveal that our probing questions can help to improve the performance of the models (e. g., by +10. 3 F1) on the main QA task and our dataset can be used for data augmentation to improve the robustness of the models.
Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts
Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F1-score of 0. 804, outperforming existing methods.
A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension
The issue of shortcut learning is widely known in NLP and has been an important research focus in recent years.
Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruning
We implement our framework by pruning the model while fine-tuning it on the debiasing objective.
Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs
We develop task pages with and without page transitions and propose a BERT extension for the framework.
Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question-context lexical overlap.
Keyphrase Generation for Scientific Document Retrieval
Sequence-to-sequence models have lead to significant progress in keyphrase generation, but it remains unknown whether they are reliable enough to be beneficial for document retrieval.
Embracing Ambiguity: Shifting the Training Target of NLI Models
Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels.
Maintaining Common Ground in Dynamic Environments
Common grounding is the process of creating and maintaining mutual understandings, which is a critical aspect of sophisticated human communication.
End-To-End Dialogue Modelling
Goal-Oriented Dialogue Systems
+1
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
A method for creating a vision-and-language (V&L) model is to extend a language model through structural modifications and V&L pre-training.
Attention-based Relational Graph Convolutional Network for Target-Oriented Opinion Words Extraction
It aims to extract the corresponding opinion words for a given opinion target in a review sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database
In this study, we considered a fully automated construction of a CF-labelled FE database using the top{--}down approach, in which the CF labels are first assigned to sentences, and then the FEs are extracted.
Multi-sense embeddings through a word sense disambiguation process
Natural Language Understanding has seen an increasing number of publications in the last few years, especially after robust word embeddings models became prominent, when they proved themselves able to capture and represent semantic relationships from massive amounts of data.
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
The evidence information has two benefits: (i) providing a comprehensive explanation for predictions and (ii) evaluating the reasoning skills of a model.
Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems
For instance, specificity is mandatory in a food-ordering dialogue task, whereas fluency is preferred in a language-teaching dialogue system.
Language-Conditioned Feature Pyramids for Visual Selection Tasks
However, few models consider the fusion of linguistic features with multiple visual features with different sizes of receptive fields, though the proper size of the receptive field of visual features intuitively varies depending on expressions.
A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions
Recent models achieve promising results in visually grounded dialogues.
A System for Worldwide COVID-19 Information Aggregation
The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education.
Extraction and Evaluation of Formulaic Expressions Used in Scholarly Papers
We also propose a new extraction method that utilises named entities and dependency structures to remove the non-formulaic part from a sentence.
An Evaluation Dataset for Identifying Communicative Functions of Sentences in English Scholarly Papers
Formulaic expressions, such as {`}in this paper we propose{'}, are used by authors of scholarly papers to perform communicative functions; the communicative function of the present example is {`}stating the aim of the paper{'}.
Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation
While most existing QAG methods aim to improve the quality of synthetic examples, we conjecture that diversity-promoting QAG can mitigate the sparsity of training sets and lead to better robustness.
Benchmarking Machine Reading Comprehension: A Psychological Perspective
Machine reading comprehension (MRC) has received considerable attention as a benchmark for natural language understanding.
Discovering Mathematical Objects of Interest -- A Study of Mathematical Notations
The contributions of our presented research are as follows: (1) we present the first distributional analysis of mathematical formulae on arXiv and zbMATH; (2) we retrieve relevant mathematical objects for given textual search queries (e. g., linking $P_{n}^{(\alpha, \beta)}\!\left(x\right)$ with `Jacobi polynomial'); (3) we extend zbMATH's search engine by providing relevant mathematical formulae; and (4) we exemplify the applicability of the results by presenting auto-completion for math inputs as the first contribution to math recommendation systems.
From Natural Language Instructions to Complex Processes: Issues in Chaining Trigger Action Rules
A natural language interface for such automation is expected as an elemental technology for the IPA realization.
Assessing the Benchmarking Capacity of Machine Reading Comprehension Datasets
Existing analysis work in machine reading comprehension (MRC) is largely concerned with evaluating the capabilities of systems.
An Annotated Corpus of Reference Resolution for Interpreting Common Grounding
Common grounding is the process of creating, repairing and updating mutual understandings, which is a fundamental aspect of natural language conversation.
A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context
Finally, we evaluate and analyze baseline neural models on a simple subtask that requires recognition of the created common ground.
Unsupervised Rewriter for Multi-Sentence Compression
First, the word graph approach that simply concatenates fragments from multiple sentences may yield non-fluent or ungrammatical compression.
Why Machines Cannot Learn Mathematics, Yet
Nowadays, Machine Learning (ML) is seen as the universal solution to improve the effectiveness of information retrieval (IR) methods.
The Architecture of Mr. DLib's Scientific Recommender-System API
In this paper, we introduce Mr. DLib's "Recommendations as-a-Service" (RaaS) API that allows operators of academic products to easily integrate a scientific recommender system into their products.
Context-Patch Face Hallucination Based on Thresholding Locality-constrained Representation and Reproducing Learning
To this end, this study incorporates the contextual information of image patch and proposes a powerful and efficient context-patch based face hallucination approach, namely Thresholding Locality-constrained Representation and Reproducing learning (TLcR-RL).
What Makes Reading Comprehension Questions Easier?
From this study, we observed that (i) the baseline performances for the hard subsets remarkably degrade compared to those of entire datasets, (ii) hard questions require knowledge inference and multiple-sentence reasoning in comparison with easy questions, and (iii) multiple-choice questions tend to require a broader range of reasoning skills than answer extraction and description questions.
Using Formulaic Expressions in Writing Assistance Systems
Formulaic expressions (FEs) used in scholarly papers, such as {`}there has been little discussion about{'}, are helpful for non-native English speakers.
A Language Model based Evaluator for Sentence Compression
We herein present a language-model-based evaluator for deletion-based sentence compression and view this task as a series of deletion-and-evaluation operations using the evaluator.
Ranked #2 on
Sentence Compression
on Google Dataset
UC3M-NII Team at SemEval-2018 Task 7: Semantic Relation Classification in Scientific Papers via Convolutional Neural Network
This paper reports our participation for SemEval-2018 Task 7 on extraction and classification of relationships between entities in scientific papers.
Category-Based Deep CCA for Fine-Grained Venue Discovery from Multimodal Data
Given a photo as input, this model performs (i) exact venue search (find the venue where the photo was taken), and (ii) group venue search (find relevant venues with the same category as that of the photo), by the cross-modal correlation between the input photo and textual description of venues.
A Study of Position Bias in Digital Library Recommender Systems
We conduct a study in a real-world recommender system that delivered ten million related-article recommendations to the users of the digital library Sowiport, and the reference manager JabRef.
Evaluation Metrics for Machine Reading Comprehension: Prerequisite Skills and Readability
Knowing the quality of reading comprehension (RC) datasets is important for the development of natural-language understanding systems.
A Conditional Variational Framework for Dialog Generation
Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems.
Learning Succinct Models: Pipelined Compression with L1-Regularization, Hashing, Elias-Fano Indices, and Quantization
The recent proliferation of smart devices necessitates methods to learn small-sized models.
SideNoter: Scholarly Paper Browsing System based on PDF Restructuring and Text Annotation
In this paper, we discuss our ongoing efforts to construct a scientific paper browsing system that helps users to read and understand advanced technical content distributed in PDF.
English-to-Japanese Translation vs. Dictation vs. Post-editing: Comparing Translation Modes in a Multilingual Setting
Speech-enabled interfaces have the potential to become one of the most efficient and ergonomic environments for human-computer interaction and for text production.
Typed Entity and Relation Annotation on Computer Science Papers
In our scheme, mentions of entities are annotated with ontology-based types, and the roles of the entities are annotated as relations with other entities described in the text.
Leveraging Monolingual Data for Crosslingual Compositional Word Representations
In this work, we present a novel neural network based architecture for inducing compositional crosslingual word representations.
Annotation of Computer Science Papers for Semantic Relation Extrac-tion
We designed a new annotation scheme for formalising relation structures in research papers, through the investigation of computer science papers.
Corpus for Coreference Resolution on Scientific Papers
Through these comparisons, we have demonstrated quantitatively that our manually annotated corpus differs from a general-domain corpus, which suggests deep differences between general-domain texts and scientific texts and which shows that different approaches can be made to tackle coreference resolution for general texts and scientific texts.
Building Japanese Predicate-argument Structure Corpus using Lexical Conceptual Structure
In this paper, we report our framework for creating the corpus and the current status of creating an LCS dictionary for Japanese predicates.
Automatic Translation of Scholarly Terms into Patent Terms Using Synonym Extraction Techniques
Retrieving research papers and patents is important for any researcher assessing the scope of a field with high industrial relevance.
