Papers with prediction task
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
Vijit Malik, Rishabh Sanjay, Shubham Kumar Nigam, Kripabandhu Ghosh, Shouvik Kumar Guha, Arnab Bhattacharya, Ashutosh Modi
| 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
Zhiheng Lyu, Zhijing Jin, Fernando Gonzalez Adauto, Rada Mihalcea, Bernhard Schölkopf, Mrinmaya Sachan
| 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. |