Papers with classification task
MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing (2020.coling-main)
Copied to clipboard
| Challenge: | Named entity typing (NET) is a classification task of assigning an entity mention in the context with given semantic types. |
| Approach: | They propose a memory-augmented FNET model to tackle unseen types in a zero-shot manner. |
| Outcome: | The proposed model outperforms the state-of-the-art models with up to 8% gain in Micro-F1 and Macro-F1. |
Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies treat named entity recognition as a sequential labeling problem. |
| Approach: | They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted . |
| Outcome: | The proposed framework outperforms competing models on four benchmark datasets. |
On Efficiently Acquiring Annotations for Multilingual Models (2022.acl-short)
Copied to clipboard
| Challenge: | a recent study shows that joint learning across multiple languages performs better than the aforementioned approaches . traditional approaches to support NLP tasks require a lot of annotations to perform . a new approach is to train a model for each language with annotation budget divided equally among them . |
| Approach: | They propose a method for joint learning across multiple languages using a single model . they show that active learning provides additional, complementary benefits . |
| Outcome: | The proposed method outperforms other models on a diverse set of tasks . it can arbitrate its annotation budget to query languages it is less certain on . |
ALAMBIC : Active Learning Automation Methods to Battle Inefficient Curation (2023.eacl-demo)
Copied to clipboard
| Challenge: | ALAMBIC is an open-source web-based platform for annotating text data through active learning for classification task. |
| Approach: | They present an open-source web-based platform for annotating text data through active learning for classification task. |
| Outcome: | The proposed model can be downloaded and used in downstream tasks and integrates with other types of models, features and active learning strategies. |
Divisive Language and Propaganda Detection using Multi-head Attention Transformers with Deep Learning BERT-based Language Models for Binary Classification (D19-50)
Copied to clipboard
| Challenge: | a team of researchers used a pre-trained BERT language model to train propaganda . the model was based on a cloze comprehension test to answer a question about influence operations . |
| Approach: | team used a BERT language model that was pre-trained on Wikipedia and BookCorpus . they used cloze comprehension tests to train the model to answer a propaganda question . |
| Outcome: | The proposed model was trained on Wikipedia and BookCorpus to answer propaganda questions . the team used a neural network that was pre-trained on the Wikipedia and bookCorpus corpus . |
Benchmarks and models for entity-oriented polarity detection (N18-3)
Copied to clipboard
| Challenge: | a dataset of 17,000 manually labeled documents is large for determining entity-oriented polarity in business news. |
| Approach: | They propose a convolutional neural network-based approach to classify entity-oriented polarity in business news. |
| Outcome: | The proposed model is based on convolutional neural networks and is small on the scale of existing models. |
Speak up, Fight Back! Detection of Social Media Disclosures of Sexual Harassment (N19-3)
Copied to clipboard
| Challenge: | #MeToo movement provides platform to narrate personal experiences of sexual harassment. |
| Approach: | They propose a three-part ULMFiT architecture to tackle text subtleties in a classification task . they propose to annotate a manually annotated real-world dataset to test their approach . |
| Outcome: | The proposed model outperforms existing models that rely on handcrafted stylistic features and is more accurate than generic models. |
Emotion Classification in a Resource Constrained Language Using Transformer-based Approach (2021.naacl-srw)
Copied to clipboard
| Challenge: | Existing methods to classify Bengali text into six basic emotions are infancy for resource-constrained languages like English, Arabic, Chinese and French. |
| Approach: | They propose a transformer-based technique to classify Bengali text into one of the six basic emotions: anger, fear, disgust, sadness, joy, and surprise. |
| Outcome: | The proposed technique outperforms all other techniques by achieving highest weighted f_1-score on the test data. |
Affective and Contextual Embedding for Sarcasm Detection (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to detect sarcasm from text lack vocal intonation or facial gestures in textual data. |
| Approach: | They propose two deep neural network models for sarcasm detection that extend the architecture of BERT by incorporating both affective and contextual features. |
| Outcome: | The proposed models outperform state-of-the-art models on different datasets with significant margins. |
Prompting for Multimodal Hateful Meme Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Hateful meme classification requires complex reasoning and contextual background knowledge. |
| Approach: | They propose a simple yet effective prompt-based model that prompts pre-trained language models for hateful meme classification. |
| Outcome: | The proposed model outperforms state-of-the-art models on hateful meme classification task. |
Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification (2024.acl-long)
Copied to clipboard
| Challenge: | Existing annotation codebook is labor-intensive for coding events from large datasets. |
| Approach: | They propose to use existing annotation codebook to classify political relations without extensive annotations. |
| Outcome: | The proposed methods outperform dictionary-based methods and the existing ontology annotation codebook and improve interpretability and efficiency. |
A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations (2022.findings-naacl)
Copied to clipboard
Md Mosharaf Hossain, Luke Holman, Anusha Kakileti, Tiffany Kao, Nathan Brito, Aaron Mathews, Eduardo Blanco
| Challenge: | Negations carry affirmative meanings, which are difficult to process and understand by humans. |
| Approach: | They propose a question-answer driven approach to reveal affirmative interpretations from verbal negations. |
| Outcome: | The proposed approach is based on a natural language inference task . it shows that state-of-the-art transformers are insufficient to reveal affirmative interpretations . |
Label-Guided Learning for Item Categorization in e-Commerce (2021.naacl-industry)
Copied to clipboard
| Challenge: | a recent study shows that item categorization uses the semantic information of the labels to guide the classification task. |
| Approach: | They investigate whether using the semantic information of the labels can improve item categorization systems in e-commerce. |
| Outcome: | The proposed methods improve item categorization performance on a real data set from a major e-commerce company in Japan. |
Self-supervised Regularization for Text Classification (2021.tacl-1)
Copied to clipboard
| Challenge: | Text classification models are prone to overfitting when limited texts are available for training. |
| Approach: | They propose a data-dependent regularization approach based on self-supervised learning . they define auxiliary tasks on input data without using human-provided labels . |
| Outcome: | Experiments on 17 text classification datasets demonstrate the effectiveness of the proposed method. |
Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution (2020.coling-main)
Copied to clipboard
| Challenge: | Existing Variational autoencoders are limited by the assumed Gaussianity of the underlying probability distributions in the latent space. |
| Approach: | They propose a probabilistic autoencoding framework to deal with a supervised authorship attribution task. |
| Outcome: | The proposed method outperforms existing methods on an Amazon review dataset. |
It’s Better to Teach Fishing than Giving a Fish: An Auto-Augmented Structure-aware Generative Model for Metaphor Detection (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to identify metaphors use contextual information extracted by transformers for classifications directly. |
| Approach: | They propose to use structure information extraction to transform the classification task into a keywords-extraction task and to use it to expand the limited datasets. |
| Outcome: | The proposed model obtains competitive results compared with state-of-the-art methods . |
Speaker Clustering in Textual Dialogue with Pairwise Utterance Relation and Cross-corpus Dialogue Act Supervision (2022.coling-1)
Copied to clipboard
| Challenge: | Existing models for textual dialogues do not include speaker annotations. |
| Approach: | They propose a speaker clustering model for textual dialogues that groups utterances without annotations so that the actual speakers are identical inside each cluster. |
| Outcome: | The proposed model outperforms the sequence classification baseline and benefits from the auxiliary dialogue act classification task. |
Fine-Grained Temporal Orientation and its Relationship with Psycho-Demographic Correlates (N18-1)
Copied to clipboard
| Challenge: | Temporal orientation refers to an individual’s tendency to connect to the psychological concepts of past, present or future and affects personality, motivation, emotion, decision making and stress coping processes. |
| Approach: | They propose to use a minimally supervised method to classify tweets in one of three temporal categories, past, present, and future, and a deep bi-directional long-term memory (BLSTM) to measure correlation between sentiment view of temporal orientation and different psycho-demographic factors. |
| Outcome: | The proposed method achieves 78.27% accuracy on a manually created test set. |
Estimating User Communication Styles for Spoken Dialogue Systems (2020.lrec-1)
Copied to clipboard
| Challenge: | a neural network estimation system for spoken dialogues can be used to estimate the communication style of a user's interaction, but this is rarely implemented in a live system. |
| Approach: | They propose a neural network approach to estimate the communication style of spoken interaction, namely elaborateness and directness. |
| Outcome: | The proposed method can estimate the elaborateness and directness of spoken interaction and improve the results with additional linguistic features. |
Two-Step Classification using Recasted Data for Low Resource Settings (2020.aacl-main)
Copied to clipboard
Shagun Uppal, Vivek Gupta, Avinash Swaminathan, Haimin Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah, Amanda Stent
| Challenge: | Existing studies on NLP models focus on high resource languages like English, but there are only two datasets for Hindi. |
| Approach: | They propose a novel two-step classification method which uses textual-entailment predictions for classification task. |
| Outcome: | The proposed method improves classification performance by using a joint-objective for classification and textual entailment. |
Modeling Temporality of Human Intentions by Domain Adaptation (D18-1)
Copied to clipboard
| Challenge: | Recent research shows that themes and words within a conversation change across time, whereas topics and the patient's attitude towards their willingness to change might shift. |
| Approach: | They propose a method that models the temporal factor by using domain adaptation on clinical dialogue corpora, Motivational Interviewing (MI). |
| Outcome: | The proposed method improves on a college alcoholism dataset using a bi-LSTM and topic model to learn language usage change across different time sessions. |
FPC: Fine-tuning with Prompt Curriculum for Relation Extraction (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for relation extraction ignore semantics of relation labels . prompt-based fine-tuning has been proposed for RE . |
| Approach: | They propose a method for relation extraction using prompt-based fine-tuning . they use auxiliary prompt-tuned learning task to make the model capture semantics of relation labels . |
| Outcome: | The proposed method outperforms existing methods on four widely used RE benchmarks under fully supervised and low-resource settings. |
Transformation Networks for Target-Oriented Sentiment Classification (P18-1)
Copied to clipboard
| Challenge: | a new model for sentiment classification uses attention instead of attention to classify sentiment polarities over individual opinion targets. |
| Approach: | They propose a model that uses a CNN layer to extract salient features from transformed word representations from a bi-directional RNN layer. |
| Outcome: | The proposed model achieves state-of-the-art on a few benchmarks. |
Antonym vs Synonym Distinction using InterlaCed Encoder NETworks (ICE-NET) (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing research on antonym-synonym distinction is limited by the sparsity of the feature space. |
| Approach: | They propose to capture and model relation-specific properties of antonyms and synonyms pairs . ICE-NET outperforms existing research by a relative score of upto 1.8% in F1-measure . |
| Outcome: | The proposed model outperforms existing models by 1.8% in the F1-measure. |
Enhancing Marker Scoring Accuracy through Ordinal Confidence Modelling in Educational Assessments (2025.acl-industry)
Copied to clipboard
| Challenge: | Automated Essay Scoring (AES) systems aim to evaluate the quality of candidate writing using computational methods. |
| Approach: | They propose a model that assigns a confidence score to each automated score to ensure it meets high reliability standards. |
| Outcome: | The proposed model achieves an F1 score of 0.97 and releases 47% of predicted scores with 100% CEFR agreement and 99% with at least 95% CEFR agreeance compared to the standalone model where all predicted scores are released. |
A Submodular Feature-Aware Framework for Label Subset Selection in Extreme Classification Problems (N19-1)
Copied to clipboard
| Challenge: | Experimental results show that extreme multi-label learning improves label prediction quality by 3% to 5% in three of the 5 tasks and is competitive in the others. |
| Approach: | They propose a submodular maximization framework with linear cost to find informative labels which are most relevant to other labels yet least redundant with each other. |
| Outcome: | The proposed model improves label prediction quality by 3% to 5% in three of the 5 tasks and is competitive in the others. |
RuleBERT: Teaching Soft Rules to Pre-Trained Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are limited in their ability to capture and use common-sense knowledge. |
| Approach: | They propose to teach PLMs how to reason with soft Horn rules by leveraging logical rules to learn how to predict precise probabilities. |
| Outcome: | The proposed model performs well on logical rules that were unseen at training. |
Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations (P18-1)
Copied to clipboard
| Challenge: | Existing methods for paraphrasing nouncompounds lack the ability to generalize and have a hard time interpreting infrequent or new noun-compound. |
| Approach: | They propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrase. |
| Outcome: | The proposed model generalizes better by representing paraphrases in a continuous space, generalizing for unseen noun-compounds and rare paraphrase. |
Fine-Grained Arabic Dialect Identification (C18-1)
Copied to clipboard
| Challenge: | Existing work on Arabic Dialect Identification typically targeted coarse-grained five dialect classes plus Standard Arabic at most (6-way classification). |
| Approach: | They propose to tackle a fine-grained Arabic dialect classification task covering 25 cities from across the Arab World, in addition to Standard Arabic. |
| Outcome: | The proposed task can identify the exact city of a speaker at an accuracy of 67.9% for sentences with an average length of 7 words and reach more than 90% when we consider 16 words. |
Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in NLP have led to the use of pre-trained Transformer models for transfer learning tasks becoming the most common way to solve target tasks. |
| Approach: | They propose a 3-phase technique to adjust a base model for a classification task by adapting the model’s signal to the data distribution and a new data augmentation approach for Supervised Contrastive Learning to correct the unbalanced datasets. |
| Outcome: | The proposed method is compared with other methods and compares it with other approaches. |
Event Extraction as Machine Reading Comprehension (2020.emnlp-main)
Copied to clipboard
| Challenge: | Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. |
| Approach: | They propose a new learning paradigm for event extraction by explicitly casting it as a machine reading comprehension problem. |
| Outcome: | The proposed model achieves state-of-the-art performance on the data-scarce scenario, achieving 49.8% in F1 for event argument extraction with only 1% data, compared with 2.2% of the previous method. |
No Simple Answer to Data Complexity: An Examination of Instance-Level Complexity Metrics for Classification Tasks (2025.naacl-long)
Copied to clipboard
| Challenge: | Understanding data complexity at the instance level has become increasingly important in Natural Language Processing (NLP) and machine learning (ML). |
| Approach: | They empirically examine the relationship between instance-level complexity scores and metric selection for classification tasks. |
| Outcome: | The results show that storing training loss provides similar complexity rankings to other methods, but not demographic fairness, even in downstream predictions. |
Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas (2026.findings-acl)
Copied to clipboard
Lukas Stähelin, Veronika Solopova, Max Upravitelev, David Kaplan, Premtim Sahitaj, Ariana Sahitaj, Charlott Jakob, Sebastian Möller, Vera Schmitt
| Challenge: | Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. |
| Approach: | They propose a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. |
| Outcome: | The proposed taxonomy outperforms existing models and reveals methodological differences hidden in base models. |
Scientific Statement Classification over arXiv.org (2020.lrec-1)
Copied to clipboard
| Challenge: | a dataset of 1.2 million documents converted from the original submissions is available for supervised learning. |
| Approach: | They propose a new classification task for scientific statements and a large-scale dataset for supervised learning. |
| Outcome: | The proposed task achieves a 0.91 F1 score and a lexeme serialization for mathematical formulas. |
A Hybrid Model of Classification and Generation for Spatial Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies only focus on spatial relations extraction as a classification task . spatial information is one kind of critical information for natural language understanding . |
| Approach: | They propose a hybrid model that generates null-role relations and extracts non-null-rol . they propose varying kinds of schemes to represent spatial relation . |
| Outcome: | The proposed model outperforms the baselines on the spatial relation extraction task on SpaceEval. |
LoRAN: Improved Low-Rank Adaptation by a Non-Linear Transformation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent methods for fine-tuning large language models have shown great improvements on a wide range of NLP tasks. |
| Approach: | They propose to introduce a non-linear transformation to improve performance of adapters by introducing a low-rank adaptation to fit the accumulated weight updates. |
| Outcome: | The proposed method outperforms a baseline on SAMSum and 20 Newsgroups tasks and even improves the classification task by 1.95 points when a lower rank is applied. |
What About the Precedent: An Information-Theoretic Analysis of Common Law (2021.naacl-main)
Copied to clipboard
| Challenge: | In common law, the outcome of a new case is determined mostly by precedent cases, rather than by existing statutes. |
| Approach: | They propose to model the argumentation of precedent cases and compare them to a case out-come classification task to determine how the precedent influences the outcome of a new case. |
| Outcome: | The proposed method compared arguments of two longstanding jurisprudential views on the European Court of Human Rights (ECtHR) and the precedent cases. |
Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods of implicit discourse relation recognition (IDRR) focus on three aspects: enhancing discourse units representation, enhancing semantic interaction, and joint learning with other tasks. |
| Approach: | They propose a joint model to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. |
| Outcome: | The proposed model achieves the best performance against several state-of-the-art systems on Chinese and English datasets. |
Evaluating Evaluation Measures for Ordinal Classification and Ordinal Quantification (2021.acl-long)
Copied to clipboard
| Challenge: | Ordinal Classification (OC) tasks require ordinal classes, not nominal ones, to be evaluated. |
| Approach: | They use data from the SemEval and NTCIR communities to clarify evaluation measures for Ordinal Classification and Ordinal Quantification tasks. |
| Outcome: | The evaluation measures for Ordinal Classification (OC) and Ordinal Quantification (OQ) tasks are ordinal, not nominal. |
Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) face high computational demands at inference time due to high computational costs. |
| Approach: | They propose a cost-effective and high-throughput solution for large language models . PGKD distills the knowledge of LLMs into smaller, task-specific models based on teacher-student knowledge distillation . |
| Outcome: | PGKD outperforms BERT-based models and other knowledge distillation methods on multi-class classification datasets. |
If you’ve seen some, you’ve seen them all: Identifying variants of multiword expressions (C18-1)
Copied to clipboard
| Challenge: | Multiword expressions (VMWEs) show idiosyncratic variability, which is challenging for NLP applications. |
| Approach: | They propose to use a model to identify variants of previously seen VMWEs by comparing VMWAs with morpho-syntactic variations. |
| Outcome: | The proposed approach outperforms a baseline by 4 percent points of F-measure on a French corpus. |
Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for speaker identification in novel dialogues are limited to handling explicit narrative patterns and complex cases. |
| Approach: | They propose a framework which identifies implicit speakers in novels via symbolization, prompt, and classification. |
| Outcome: | The proposed framework outperforms existing methods by 4.8% accuracy on the web novel collection, which reduces 47% of speaker identification errors, and outperfies the emerging ChatGPT. |
FQuAD2.0: French Question Answering and Learning When You Don’t Know (2022.lrec-1)
Copied to clipboard
| Challenge: | Question Answering, including Reading Comprehension, has seen significant scientific breakthroughs over the past few years . but most of these breakthroughs are centered on the English language . |
| Approach: | They propose a dataset to train Question Answering models in the French language . they extend the dataset to 17,000+ unanswerable questions annotated adversarially . |
| Outcome: | The proposed dataset makes it possible to train French Question Answering models with the ability to distinguish unanswerable questions from answerable ones. |
Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing supervised methods treat word sense disambiguation as a classification task but ignore uncertainty estimation (UE) in the real-world setting, the data is always noisy and out of distribution. |
| Approach: | They propose to use word sense disambiguation to determine an appropriate sense for a word given its context to determine the most appropriate sense. |
| Outcome: | The proposed model reflects data uncertainty satisfactorily but underestimates model uncertainty. |
Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models (2023.emnlp-main)
Copied to clipboard
Pierre Colombo, Victor Pellegrain, Malik Boudiaf, Myriam Tami, Victor Storchan, Ismail Ayed, Pablo Piantanida
| Challenge: | Proprietary and closed APIs are impacting the practical applications of natural language processing. |
| Approach: | They propose a scenario where a pre-trained model is served through a gated API . they propose 'transductive inference' that leverages statistics of unlabelled data . |
| Outcome: | The proposed model performs a few-shot classification task with unlabelled data using a gated API . the proposed model can be used to perform the task with a handful of classes . |
CE-VDG: Counterfactual Entropy-based Bias Reduction for Video-grounded Dialogue Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to reduce question-related bias in video-grounded dialogue generation (VDG) however, the dataset often contains inherent bias, which can cause VDG models to learn spurious correlations between questions and answers. |
| Approach: | They propose to extend the counterfactual reasoning from the information entropy perspective to the generative task, which can effectively reduce the question-related bias in the auto-regressive generation task. |
| Outcome: | The proposed method can reduce question-related bias in the auto-regressive generation task by using counterfactual entropy as an external loss. |
Learning multiview embeddings for assessing dementia (D18-1)
Copied to clipboard
| Challenge: | In 2017, 5.7 million Americans were living with Alzheimer's disease (AD), and the disease accounted for $11.4 billion in healthcare costs in the United States. |
| Approach: | They leverage the multiview nature of a small AD dataset to learn an embedding that captures different modes of cognitive impairment. |
| Outcome: | The proposed embeddings achieve an F1 score of 0.82 and a mean absolute error of 3.42 in the classification task and predicting clinical scores. |
Learning to Decipher Hate Symbols (N19-1)
Copied to clipboard
| Challenge: | Existing computational models of hate speech focus on a binary or multiclass classification task . a recent study shows an alarming 4.6% increase in hate speech in 2016 . |
| Approach: | They propose a task of deciphering hate symbols using the Urban Dictionary . they propose ciphers using Sequence-to-Sequence models and a Variational Decipher . |
| Outcome: | The proposed model can crack hate symbols based on context and generalize better to unseen symbols in a more challenging testing setting. |
Exploring Discourse Structures for Argument Impact Classification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown that discourse structures influence the persuasiveness of arguments. |
| Approach: | They propose to fuse sentence-level structural discourse information with contextualized features derived from large-scale language models to investigate how discourse relations influence argument impact. |
| Outcome: | The proposed model improves its backbone RoBERTa around 1.67%, compared with other models, but side effects are brought by other models. |
Form2Seq : A Framework for Higher-Order Form Structure Extraction (2020.emnlp-main)
Copied to clipboard
| Challenge: | Document structure extraction is a widely researched area for decades due to image resolution and poor semantics. |
| Approach: | They propose a sequence-to-sequence framework for document structure extraction using text . they use a text-based framework to classify low-level constituent elements into ten types . |
| Outcome: | The proposed framework outperforms existing methods for document structure extraction on ICDAR 2013 dataset. |
Modeling Preconditions in Text with a Crowd-sourced Dataset (2020.findings-emnlp)
Copied to clipboard
Heeyoung Kwon, Mahnaz Koupaee, Pratyush Singh, Gargi Sawhney, Anmol Shukla, Keerthi Kumar Kallur, Nathanael Chambers, Niranjan Balasubramanian
| Challenge: | Existing methods for modeling preconditions in text are limited due to the lack of large scale labeled data grounded in text. |
| Approach: | They propose a crowd-sourced annotation of preconditions between event pairs in newswire that is larger than prior annotations. |
| Outcome: | The proposed model outperforms existing models on two task sets, showing that precondition knowledge is not easily accessible in LM-derived representations alone. |
Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition (2022.lrec-1)
Copied to clipboard
| Challenge: | Anglicisms are a challenge in German speech recognition due to their irregular pronunciation compared to native German words. |
| Approach: | They propose a multitask sequence-to-sequence approach for grapheme-tophoneme conversion to improve the phonetization of Anglicisms. |
| Outcome: | The proposed model reduces the word error rate by 1 % and the Anglicism error rate, while still maintaining the accuracy of the baseline model. |
Modeling the Differential Prevalence of Online Supportive Interactions in Private Instant Messages of Adolescents (2025.findings-naacl)
Copied to clipboard
| Challenge: | Approximately two-thirds (68%) of American teenagers aged 13-17 have reported that social media make them feel as though they have people who will support them during challenging times. |
| Approach: | They propose to use the Social Support Behavioral Code to detect and model gender-based and pair-or-group disparities in online supportive interactions among adolescents. |
| Outcome: | The proposed model can be used to model gender-based and pair-or-group disparities in supportive interactions among adolescents. |
Finding the Optimal Vocabulary Size for Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Class imbalance is said to exist when one or more classes are not of approximately equal frequency in data. |
| Approach: | They cast neural machine translation (NMT) as a classification task in an autoregressive setting and examine its limitations. |
| Outcome: | The proposed model performs better on multiple languages with large data sizes with different vocabulary sizes. |
EFSA: Towards Event-Level Financial Sentiment Analysis (2024.acl-long)
Copied to clipboard
| Challenge: | a large-scale Chinese dataset contains 12,160 news articles and 13,725 quintuples . a four-hop Chain-of-Thought LLM-based approach is devised for this task . |
| Approach: | They propose to extend financial sentiment analysis to event-level since events usually serve as the subject of the sentiment in financial text. |
| Outcome: | The proposed method can reach the current state-of-the-art on a large-scale Chinese dataset. |
A Knowledge-Guided Framework for Frame Identification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing frameworks for frame identification are limited to only a few types of frame knowledge. |
| Approach: | They propose a Knowledge-Guided Frame Identification framework that integrates frame knowledge to learn better frame representation. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on two benchmark datasets. |
Weakly-Supervised Modeling of Contextualized Event Embedding for Discourse Relations (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Structured knowledge representations capture temporal relations between events to describe human-level representations of common scenarios. |
| Approach: | They propose to represent narrative graphs and learn contextualized event representations over them using a relational graph neural network model. |
| Outcome: | The proposed model improves performance when learning script knowledge without supervision and provides a better representation for the implicit discourse sense classification task. |
Preparing Data from Psychotherapy for Natural Language Processing (L18-1)
Copied to clipboard
| Challenge: | mental health care is a demanding occupation, resulting in a severe gap in patient-centered care . a recent study shows that natural language processing can extract certain aspects of human-human communication. |
| Approach: | They propose to use data from psychotherapy sessions to help improve quality of care . they use feedback and cooperation annotations to assess quality of therapy sessions . |
| Outcome: | The proposed method aims to analyse psychotherapy data and assess its quality . it aims at identifying what qualifies for good feedback or cooperation in therapy sessions . |
Adaptive Cross-lingual Text Classification through In-Context One-Shot Demonstrations (2024.naacl-long)
Copied to clipboard
| Challenge: | Zero-Shot Cross-lingual transfer (ZS-XLT) uses a model trained in a source language to make predictions in another language, often with a performance loss. |
| Approach: | They propose a new approach that uses In-Context Tuning to train a model to learn from context examples and adapt it to a target language by prepending a One-Shot context demonstration. |
| Outcome: | The proposed approach outperforms prompt-based models in Zero-Shot and Few-shot scenarios with target-language examples. |
How Can We Accelerate Progress Towards Human-like Linguistic Generalization? (2020.acl-main)
Copied to clipboard
| Challenge: | a new evaluation paradigm, Pretraining-Agnostic Identically Distributed evaluation, is needed . authors argue that it rewards models that can be trained on massive amounts of data, several orders of magnitude more than a human can expect to be exposed to. |
| Approach: | a position paper describes and critiques the Pretraining-Agnostic Identically Distributed evaluation paradigm . paradigm favors simple, low-bias architectures that can be scaled to process vast amounts of data . authors advocate for supplementing or replacing PAID with paradigms that reward architectures . |
| Outcome: | a new evaluation paradigm favors simple, low-bias architectures that can be scaled to process vast amounts of data. a san francisco-based study finds that the paradigm rewards architectures which generalize as quickly and robustly as humans. |
Close or Cloze? Assessing the Robustness of Large Language Models to Adversarial Perturbations via Word Recovery (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models implicitly recover the original text, but it is unclear when they rely on context and when they implicitly do so. |
| Approach: | They propose to use a dictionary to recover adversarial words by using a phonetic, typo, and visual attack to study word recovery performance. |
| Outcome: | The proposed model outperforms open-source models on hateful, offensive, and toxic classification tasks. |
HYDRA: A Multi-Head Encoder-only Architecture for Hierarchical Text Classification (2025.emnlp-main)
Copied to clipboard
| Challenge: | State-of-the-art approaches rely on complex components like graph encoders, label semantics, and autoregressive decoders. |
| Approach: | They propose a multi-head encoder-only architecture for hierarchical text classification that treats each level as a separate classification task with its own label space. |
| Outcome: | The proposed architecture matches or exceeds state-of-the-art methods on four benchmarks. |
A New Dataset for Topic-Based Paragraph Classification in Genocide-Related Court Transcripts (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have lowered the barriers for people outside the NLP community to tap into the tools and resources applied to a variety of domain-specific applications. |
| Approach: | They propose to annotate court transcripts from genocide-related cases using transformer-based approaches and to establish benchmarks for the task of paragraph identification of violence-related witness statements. |
| Outcome: | The first annotated corpus of genocide-related court transcripts is aimed at providing a first reference corpus for the community and to establish benchmark performances using state-of-the-art transformer-based approaches. |
Implicit Sense-labeled Connective Recognition as Text Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for identifying implicit discourse relations are limited by the number of possible categories and sense labels. |
| Approach: | They propose a method for identifying the sense label of an implicit connective between adjacent text spans by using an encoder-decoder model. |
| Outcome: | The proposed method outperforms the conventional classification-based method on a shallow discourse parsing dataset. |
Leveraging Medical Literature for Section Prediction in Electronic Health Records (D19-1)
Copied to clipboard
| Challenge: | Prior approaches to section prediction have only used text data from EHRs and required significant manual annotation. |
| Approach: | They propose to use sections from medical literature to train models to predict sections in EHRs. |
| Outcome: | The proposed model uses sections from medical literature that contain similar content to those found in EHR sections. |
Native-like Expression Identification by Contrasting Native and Proficient Second Language Speakers (2020.coling-main)
Copied to clipboard
| Challenge: | a novel task of native-like expression identification is proposed by contrasting texts written by native speakers and those by proficient second language speakers. |
| Approach: | They propose a task of native-like expression identification by contrasting texts written by native speakers and those by proficient second language speakers. |
| Outcome: | The proposed method uncovers linguistically interesting usages distinctive of native speech. |
A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature (D19-1)
Copied to clipboard
| Challenge: | Existing academic search engines cannot detect relevant papers where a resource is mentioned. |
| Approach: | They propose a framework to model the role and function of on-line resource citations . they construct a dataset SciRes, which includes 3,088 manually annotated resource contexts based on a multi-task framework . |
| Outcome: | The proposed model achieves the best results on both the classification task and recommendation task. |
Enhancing Writing Proficiency Classification in Developmental Education: The Quest for Accuracy (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing literature raises concerns about automated assessment tools like Accuplacer’s narrow representation of the writing process. |
| Approach: | They propose to use machine-learning to annotate college essays for machine/deep learning. |
| Outcome: | The proposed method improves the classification accuracy of 100 college-intending students’ essays against human raters. |
Can Large Language Models perform Relation-based Argument Mining? (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for RbAM fail to perform satisfactorily across different datasets. |
| Approach: | They propose to use relation-based argument mining to determine agreement (support) and disagreement (attack) relations amongst textual arguments in binary and ternary settings. |
| Outcome: | The proposed method outperforms the best performing (RoBERTa-based) baseline on two open-source LLMs and with GPT-3.5-turbo on several datasets for (binary and ternary) RbAM. |
When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | In-context learning is a method for adapting large language models to tasks with instructions or examples. |
| Approach: | They propose a method to decompose the output of large language models into components . they propose component reweighting, which learns to linearly re-scale component activations from a few labeled examples. |
| Outcome: | The proposed method improves by 6.0% accuracy points over 24 examples given 24 examples on Llama-2-7B. |
FastGAS: Fast Graph-based Annotation Selection for In-Context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to select unlabeled examples for annotation require a long time due to their complexity, hindering their practical viability. |
| Approach: | They propose a graph-based selection method to efficiently identify high-quality instances while minimizing computational overhead. |
| Outcome: | The proposed method significantly reduces selection time and improves performance on different tasks. |
Detect and Classify – Joint Span Detection and Classification for Health Outcomes (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting health outcomes from text ignore global structural correspondences between sentence-level and word-level information present in a given text. |
| Approach: | They propose a method that uses both word-level and sentence-level information to perform outcome span detection and outcome type classification. |
| Outcome: | The proposed method consistently outperforms decoupled methods, reporting competitive results. |
Inferring Social Media Users’ Mental Health Status from Multimodal Information (2020.lrec-1)
Copied to clipboard
| Challenge: | In the United States alone, one in every four adults suffers from a mental health condition, making mental health a pressing concern. |
| Approach: | They propose to use multimodal cues present in social media posts to predict mental health status by analyzing language, visual, and metadata cue data. |
| Outcome: | The proposed approach improves the performance of the classification task compared to using one modality at a time and can provide important cues into a user’s mental status. |
Text and Speech-based Tunisian Arabic Sub-Dialects Identification (2020.lrec-1)
Copied to clipboard
| Challenge: | Dialect IDentification is a difficult task when it is about the identification of dialects belonging to the same country. |
| Approach: | They present results on a dialect classification task covering four sub-dialects spoken in Tunisia using a spoken corpus of 1673 utterances. |
| Outcome: | The proposed system achieves an F-1 score of 93.75% while the F-1 is limited to 54.16% using text-based DID on the same test set. |
Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection are expensive and outdated . despite the popularity of LLMs, the issue of hallucinosity poses significant concerns for downstream users. |
| Approach: | They propose an approach that automatically generates both faithful and hallucinated outputs by rewriting system responses. |
| Outcome: | The proposed model outperforms state-of-the-art zero-shot detectors and existing synthetic generation methods in accuracy and latency. |
Directions for NLP Practices Applied to Online Hate Speech Detection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to address hate speech in online spaces have relied on conventions and practices from NLP. |
| Approach: | They argue that many conventions in NLP are poorly suited for the problem and encourage researchers to develop methods that are more appropriate for the task. |
| Outcome: | The proposed methods are poorly suited for the problem and should be adapted to address the propagation of online harms. |
Token Prediction as Implicit Classification to Identify LLM-Generated Text (2023.emnlp-main)
Copied to clipboard
| Challenge: | a novel approach for identifying large language models (LLMs) involved in text generation is proposed . instead of adding an additional classification layer, we reframe the classification task as a next-token prediction task . |
| Approach: | They propose a novel approach for identifying large language models involved in text generation . instead of adding an additional classification layer, they reframe the task as a next-token prediction task . |
| Outcome: | The proposed method performs exceptionally well in the text classification task . it can distinguish distinctive writing styles among various LLMs even without an explicit classifier. |
Multi-Task Learning of Query Generation and Classification for Generative Conversational Question Rewriting (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to identifying ambiguous questions as part of a conversation have not addressed this challenge. |
| Approach: | They propose a multi-task learning approach that uses a text generation model for question rewriting and classification. |
| Outcome: | The proposed approach outperforms single-task learning baselines on three LIF test sets. |
IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Intent-related tasks are typically modeled as separate tasks, but a unified approach is proposed . INTENDD uses an entirely unsupervised contrastive learning strategy for representation learning . |
| Approach: | They propose a unified approach to identifying intents from dialogue utterances . they propose an unsupervised contrastive learning strategy for representation learning . |
| Outcome: | The proposed approach outperforms baselines on three intent-related tasks on multiple datasets. |
Pater Incertus? There Is a Solution: Automatic Discrimination between Cognates and Borrowings for Romance Languages (2024.lrec-main)
Copied to clipboard
Liviu P. Dinu, Ana Sabina Uban, Ioan-Bogdan Iordache, Alina Maria Cristea, Simona Georgescu, Laurentiu Zoicas
| Challenge: | Existing methods for discriminating between cognates and borrowings are difficult, but they provide a deeper insight into the history of a language and allow for a better characterization of language relatedness. |
| Approach: | They propose a computational approach for discriminating between cognates and borrowings based on a comprehensive database of Romance cognates. |
| Outcome: | The proposed approach is the most comprehensive in terms of covered languages. |
Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues (2024.emnlp-main)
Copied to clipboard
| Challenge: | Current research treats personality recognition as a classification task, failing to reveal the supporting evidence for the recognized personality. |
| Approach: | They propose a task that aims to reveal the reasoning process as supporting evidence of the personality trait. |
| Outcome: | The proposed task reveals the reasoning process as supporting evidence of the personality trait. |
Prompt Tuning for Few-shot Relation Extraction via Modeling Global and Local Graphs (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent studies show that prompt-tuning is effective for few-shot relation extraction tasks. |
| Approach: | They propose to incorporate the knowledge in relation labels into prompt-tuning by inserting prompt templates into the input. |
| Outcome: | The proposed method improves on four datasets under low-resource conditions. |