Papers with prediction task

19 papers
Demand-Weighted Completeness Prediction for a Knowledge Base (N18-3)

Copied to clipboard

Challenge: Knowledge Bases (KBs) are widely used for representing information in a structured format.
Approach: They propose a method to measure Demand-Weighted Completeness by defining an entity by its classes and using usage data to predict relation distributions.
Outcome: The proposed method can be used to estimate completeness of knowledge bases based on how they are used and can quantify usage and completeness changes over time.
Zero-Shot On-the-Fly Event Schema Induction (2023.findings-eacl)

Copied to clipboard

Challenge: a new approach to event processing uses large language models to generate source documents that can be curated without manual data collection.
Approach: They propose a framework that generates a graphical representation of events in documents . they show that the model is more complete than previous supervised methods .
Outcome: The proposed model is more complete than human-curated schemas in most scenarios.
Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning (2025.findings-naacl)

Copied to clipboard

Challenge: Existing studies have shown that large language models implicitly embed reasoning trees, but their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations.
Approach: They propose to use circuit analysis and self-influence functions to map the reasoning process of large models.
Outcome: The proposed model is able to map human-interpretable reasoning paths and a model's underlying circuits reveal human-mediated reasoning processes.
Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event (2021.acl-short)

Copied to clipboard

Challenge: Current approaches focus on news articles and expect at least one temporal expressions in each input data to predict TTE.
Approach: They propose a context-sensitive neural model for time to event prediction task . they enrich the model with time difference embeddings to improve accuracy .
Outcome: The proposed model is 1.4 and 3.3 hours more accurate than the current state-of-the-art model on English and Dutch tweets respectively.
Social Media Attributions in the Context of Water Crisis (2020.emnlp-main)

Copied to clipboard

Challenge: In this paper, we analyze social media discussions to identify attribution factors for natural disasters/collective misfortunes.
Approach: They propose a task of attribution tie detection to identify factors held responsible for a water crisis in a social media document.
Outcome: The proposed task can be performed on a dataset constructed from YouTube comments on 2,500 videos relevant to the 2019 Chennai water crisis.
The Road to Success: Assessing the Fate of Linguistic Innovations in Online Communities (C18-1)

Copied to clipboard

Challenge: a longitudinal study of online social networks investigates the birth and spread of lexical innovations.
Approach: They investigate the birth and diffusion of lexical innovations in online communities . they build on sociolinguistic theories and focus on the relationship between the spread of a new term and the social role of the individuals who use it .
Outcome: The proposed method predicts whether an innovation will succeed in a community.
A Multi-Attention based Neural Network with External Knowledge for Story Ending Predicting Task (C18-1)

Copied to clipboard

Challenge: Existing studies on the topic of common sense story understanding focus on generating guesses for a missing event or concentrating on unsupervised learning.
Approach: They propose to extend attention-based neural network with external knowledge resources to understand temporal stories and predict their endings.
Outcome: The proposed model outperforms state-of-the-art models and external knowledge resources.
Should You Mask 15% in Masked Language Modeling? (2023.eacl-main)

Copied to clipboard

Challenge: Masked language models (MLMs) traditionally mask 15% of tokens due to the belief that more masking would leave insufficient context to learn good representations.
Approach: They revisit the 15% masking rate of MLMs to examine the role of masking in linguistic training.
Outcome: The proposed masking rate outperforms BERT-large size models on GLUE and SQUAD while maintaining 95% accuracy.
Predicting Human Activities from User-Generated Content (P19-1)

Copied to clipboard

Challenge: Several studies have applied computational approaches to the understanding and modeling of human behavior at scale and in real time.
Approach: They propose a sentence embedding framework tailored to recognize the semantics of human activities and perform automatic clustering of these activities.
Outcome: The proposed framework can make predictions based on the text of user-generated content and self-description.
What-if I ask you to explain: Explaining the effects of perturbations in procedural text (2020.findings-emnlp)

Copied to clipboard

Challenge: QUARTET constructs explanations from paragraphs using procedural text . qartet achieves 18 points better on explanation accuracy compared to strong baselines on a recent process comprehension benchmark.
Approach: They propose a system that constructs explanations from paragraphs by modeling the explanation task as a multitask learning problem.
Outcome: The proposed system achieves 18 points better on explanation accuracy compared to strong baselines on a process comprehension benchmark.
ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation (2021.acl-long)

Copied to clipboard

Challenge: a system that could assist a judge in predicting the outcome of a case should be explainable.
Approach: They propose to use a corpus of 35k Indian Supreme Court cases annotated with original court decisions to promote research in this area.
Outcome: The proposed system has an accuracy of 78% versus 94% for human legal experts.
Modeling Diagnostic Label Correlation for Automatic ICD Coding (2021.naacl-main)

Copied to clipboard

Challenge: Existing work built a binary prediction for each label independently, ignoring the dependencies between labels.
Approach: They propose a framework to capture the label correlation and train a reranking estimator to rescore the probability of each label set candidate generated by a base predictor.
Outcome: The proposed framework improves on the best-performing predictors on MIMIC datasets.
Corpus-based Identification of Verbs Participating in Verb Alternations Using Classification and Manual Annotation (2020.coling-main)

Copied to clipboard

Challenge: Verb alternations allow verbs to appear in a set of syntactically different constructions whose associated semantic frames are systematically related.
Approach: They use ENCOW and VerbNet data to train classifiers to predict the instrument subject alternation and the causative-inchoative alternation . they use count-based and vector-based features as well as perplexity-based language model features to reflect each alternation’s felicity by simulating it.
Outcome: The proposed approach reduces the required annotation effort by only presenting annotators with the highest-scoring candidates from the previous classification.
Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs (2021.acl-long)

Copied to clipboard

Challenge: Temporal Knowledge Graphs (TKGs) are used in many different areas of research.
Approach: They propose to use a beam search policy to induce multiple clues from historical facts . they propose to adopt a graph convolution network based sequence method to deduce answers from clues .
Outcome: The proposed model can predict future facts in two stages, Clue Searching and Temporal Reasoning.
Topics to Avoid: Demoting Latent Confounds in Text Classification (D19-1)

Copied to clipboard

Challenge: Despite impressive performance on many text classification tasks, deep neural networks tend to learn frequent superficial patterns that are specific to the training data and do not always generalize well.
Approach: They propose a method that represents latent topical confounds and a model which “unlearns” confounding features by predicting both the label of the input text and the confound.
Outcome: The proposed model generalizes better and learns features indicative of the writing style rather than the content.
CoDoNMT: Modeling Cohesion Devices for Document-Level Neural Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to document-level neural machine translation focus on integrating context into translation, but they focus on the way of integrating contextual information into translation.
Approach: They propose a document-level neural machine translation framework that models cohesion devices from two perspectives: Cohesion Device Masking and Cohetion Attention Focusing.
Outcome: The proposed model outperforms state-of-the-art document-level neural machine translation baselines on three benchmark datasets.
Financial Forecasting from Textual and Tabular Time Series (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing models that combine multiple data sources and combine them to form accurate financial predictions are challenging to model without inductive biases.
Approach: They propose to use numerical financial results, macroeconomic states, and long financial documents to model company earnings relative to analyst expectations.
Outcome: The proposed model outperforms existing models in a simulated trading environment and demonstrates that each modality contains unique information.
Sound Signal Processing with Seq2Tree Network (L18-1)

Copied to clipboard

Challenge: Recent LSTM models have been used to model sequential data processing tasks because of their ability to preserve previous information weighted on distance.
Approach: They propose to use a tree-structured tree-based neural network architecture to solve the problem of unbalanced connections between data units inside and outside semantic groups.
Outcome: The proposed model outperforms the state-of-the-art Bidirectional LSTM model on a signal and noise separation task.
Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis (2024.findings-emnlp)

Copied to clipboard

Challenge: Sentiment analysis aims to identify the sentiment expressed in a piece of text, often in the form of a review.
Approach: They propose a causal discovery task that distinguishes whether a review "primes" the sentiment and a traditional prediction task to model the sentiment using the review as input.
Outcome: The proposed model improves by 32.13 F1 points on a zero-shot five-class SA.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations