Papers by Hadi Amiri

20 papers
LingConv: An Interactive Toolkit for Controlled Paraphrase Generation with Linguistic Attribute Control (2025.emnlp-demos)

Copied to clipboard

Challenge: LINGCONV is an interactive toolkit for controllable text generation . it allows fine-grained control over 40 specific linguistic attributes spanning lexical, syntactic, and discourse dimensions.
Approach: They propose a toolkit for paraphrase generation that allows finegrained control over 40 specific linguistic attributes.
Outcome: The toolkit is available at https://mohdelgaar-lingconv.hf.space, with a demo video at https:youtu.be/wRBJEJ6EALQ.
Ling-CL: Understanding NLP Models through Linguistic Curricula (2023.emnlp-main)

Copied to clipboard

Challenge: linguistic complexity is a key component of learning in NLP, according to a new study . linguistic complex is based on lexical diversity, word sophistication, and readability .
Approach: They employ a characterization of linguistic complexity from psycholinguistic and language acquisition research to develop data-driven curricula.
Outcome: The proposed approach will inform future research in all NLP areas . it uses linguistic metrics (indices) that inform the challenges and reasoning required to address each task .
MedDecXtract: A Clinician-Support System for Extracting, Visualizing, and Annotating Medical Decisions in Clinical Narratives (2025.acl-demo)

Copied to clipboard

Challenge: Clinical notes contain important information about medical decisions embedded within unstructured text.
Approach: They propose an open-source interactive system that automatically extracts medical decisions from clinical text.
Outcome: The open-source system extracts and visualizes medical decisions from clinical text.
Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approach (2023.acl-long)

Copied to clipboard

Challenge: Existing curriculum learning approaches often employ a single criterion of difficulty in their training paradigms.
Approach: They propose a new approach that builds on graph complexity formalisms and model competence during training.
Outcome: The proposed approach improves learning efficiency on real-world link prediction and node classification tasks.
LingGen: Scalable Multi-Attribute Linguistic Control via Power-Law Masking (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for controlling coarse attributes are less effective for finer-grained attributes and suffer from inefficiencies when many attributes must be handled jointly.
Approach: They propose a controlled text generation model that allows fine-grained control over a large number of real-valued linguistic attributes.
Outcome: The proposed model achieves the lowest average control error among evaluated methods while remaining efficient at inference and receiving the highest fluency scores in human evaluation.
EqualizeIR: Mitigating Linguistic Biases in Retrieval Models (2025.naacl-short)

Copied to clipboard

Challenge: Existing information retrieval models show significant linguistic biases based on the linguistic complexity of queries.
Approach: They propose a framework to mitigate linguistic biases in IR models by using a linguistically biased weak learner to capture biased queries and then train a robust model by regularizing and refining its predictions.
Outcome: The proposed framework reduces performance disparities across simple and complex queries while improving overall retrieval performance.
Attentive Multiview Text Representation for Differential Diagnosis (2021.acl-short)

Copied to clipboard

Challenge: Using data from the Undiagnosed Diseases Network, we find that NLP algorithms can reproduce the performance of clinical experts in the task of differential diagnosis.
Approach: They propose a text representation approach that can combine different views of the same input to improve ranking.
Outcome: The proposed model outperforms several ranking approaches by effectively prioritizing and combining representations obtained from traditional and recent text representation techniques.
Complexity-Guided Curriculum Learning for Text Graphs (2023.findings-emnlp)

Copied to clipboard

Challenge: Curriculum learning is a systematic approach to training that refines training progressively and tailors training to task requirements.
Approach: They propose a curriculum learning approach that employs "spaced repetition" and complexity formalisms to guide the training process.
Outcome: The proposed model gains more and uses less data, and the best curricula are equally effective.
Serial Recall Effects in Neural Language Modeling (N19-1)

Copied to clipboard

Challenge: Recent studies have shed light on the information encoded by LSTM networks.
Approach: They propose to use serial recall experiments to model human memory of words in the order they occur in the language.
Outcome: The proposed model can learn function words much better than content words and can capture syntactic structures such as subject-verb agreement.
Generic and Trend-aware Curriculum Learning for Relation Extraction (2022.naacl-main)

Copied to clipboard

Challenge: Existing curriculum learning approaches for relation extraction are lacking in text graphs.
Approach: They propose a generic and trend-aware curriculum learning approach that integrates textual and structural information in text graphs for relation extraction between entities.
Outcome: The proposed model shows improvement over state-of-the-art methods across several datasets.
MedDec: A Dataset for Extracting Medical Decisions from Discharge Summaries (2024.findings-acl)

Copied to clipboard

Challenge: Medical decisions directly impact individuals’ health and well-being.
Approach: They propose to use a dataset to jointly extract and classify medical decisions within clinical notes.
Outcome: The proposed dataset contains clinical notes of eleven different phenotypes (diseases) annotated by ten types of medical decisions.
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.
Neural Self-Training through Spaced Repetition (N19-1)

Copied to clipboard

Challenge: Existing methods for self-training rely on predetermined policies to sample unlabeled data.
Approach: They propose a semi-supervised learning approach that uses spaced repetition to dynamically sample informative and diverse unlabeled instances with respect to individual learner and instance characteristics.
Outcome: The proposed model outperforms existing semi-supervised learning approaches on publicly-available datasets.
HuCurl: Human-induced Curriculum Discovery (2023.acl-long)

Copied to clipboard

Challenge: Existing curriculum learning frameworks can be used to discover effective curricula for NLP tasks based on prior knowledge about sample difficulty.
Approach: They propose a framework for curriculum learning based on prior knowledge about sample difficulty.
Outcome: The proposed framework outperforms existing curriculum learning approaches on several NLP tasks and can prune and weight samples for better learning.
Spotting Spurious Data with Neural Networks (N18-1)

Copied to clipboard

Challenge: Existing methods to identify spurious instances require either annotations generated by each individual annotator or both task-specific and instance-type annotations.
Approach: They propose an approach that discriminates instances based on their "difficulty to learn" they use queueing theory and psychology of learning to improve annotations .
Outcome: The proposed methods outperform state-of-the-art baselines and have a MAP of 0.85 and 0.22 in identifying spurious instances in synthetic and carefully-crowdsourced real-world datasets respectively.
Linguistically-Controlled Paraphrase Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Controlled paraphrase generation produces paraphrases that preserve meaning while allowing precise control over linguistic attributes of output.
Approach: They introduce an encoder-decoder framework that enables fine-grained control over 40 linguistic attributes in English.
Outcome: The proposed framework reduces attribute error by up to 34% over existing models .
A Mechanistic Perspective and Difficulty Metric for Unlearning (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies show that machine unlearning success varies across samples . easy-to-unlearn samples are associated with shorter, shallower interactions . hard-to unlear rely on longer and deeper pathways closer to late-stage computation.
Approach: They propose a pre-unlearning metric that assigns each sample a continuous difficulty score . they show that CUD reliably separates intrinsically easy and hard samples .
Outcome: The proposed method reliably separates intrinsically easy and hard samples and remains stable across unlearning methods.
Controlled Transformation of Text-Attributed Graphs (2024.findings-emnlp)

Copied to clipboard

Challenge: Graph generation is the process of generating new graphs with similar attributes to real world graphs.
Approach: They propose a controllable multi-objective translation model for text-attributed graphs that can translate a given source graph to a target graph while satisfying multiple desired graph attributes at granular level.
Outcome: The proposed model can translate a given source graph to a target graph while satisfying multiple desired graph attributes at granular level.
FairFlow: Mitigating Dataset Biases through Undecided Learning for Natural Language Understanding (2024.emnlp-main)

Copied to clipboard

Challenge: Existing debiasing frameworks can detect known dataset biases and spurious correlations in data.
Approach: They propose a framework that learns to be undecided in its predictions for data samples . they propose 'contrary' objective that learn debiased and robust representations from biased views .
Outcome: The proposed framework outperforms existing methods against out-of-domain and hard test samples without compromising performance.
Vector of Locally Aggregated Embeddings for Text Representation (N19-1)

Copied to clipboard

Challenge: Existing models for text classification use word embeddings, weighted averaging, and deepening networks.
Approach: They propose a vector-based locally averaging model that encodes each input text by effectively identifying and integrating its semantically-relevant parts.
Outcome: The proposed model outperforms RNNs and CNNs in text classification while taking only a fraction of their training time.

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