Papers by Ani Nenkova

26 papers
Temporal Effects on Pre-trained Models for Language Processing Tasks (2022.tacl-1)

Copied to clipboard

Challenge: a recent study shows that language models can be improved as time passes . a number of approaches to solving language tasks have evolved rapidly without a model .
Approach: They examine temporal effects on model performance on downstream language tasks . they also examine the efficacy of two approaches for temporal domain adaptation without human annotations .
Outcome: The proposed methods improve self-labeling and named entity recognition on new data.
Context-aware Information-theoretic Causal De-biasing for Interactive Sequence Labeling (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing deep learning models for sequence labeling are expensive and time-consuming.
Approach: They propose an interactive sequence labeling that allows training directly with the user feedback . they identify context and feedback biases by formulating interactive sequence labels via a Structural Causal Model.
Outcome: The proposed approach can effectively alleviate the biases and can be learnt with the user feedback.
LinkNav: Surfacing Interconnected Information in Scientific Articles (2026.acl-demo)

Copied to clipboard

Challenge: a non-linear reading order of academic literature is recognized by authors who make explicit connections between non-adjacent passages.
Approach: They propose an enhanced reading experience which generates questions and searches for answer-bearing passages in academic papers to form intra-document connections when answers are found.
Outcome: The proposed interface makes connections between related but non-adjacent passages even if the author did not make them explicit.
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution (2021.eacl-main)

Copied to clipboard

Challenge: Existing tools for quantifying incivility online, in news and in congressional debates are inadequate for the analysis of incivility in news.
Approach: They develop a Jigsaw Perspective API to quantify incivility in news . they show that toxicity models are inadequate for the analysis of incivility in news.
Outcome: The Jigsaw Perspective API detects incivility on a corpus of American news articles.
ATLAS: A System for PDF-centric Human Interaction Data Collection (2024.naacl-demo)

Copied to clipboard

Challenge: Recent advances in AI only make the importance of high-quality data more pronounced.
Approach: They propose to use the Portable Document Format (PDF) as a data format to better support researchers in collecting rich PDF-centric datasets from users.
Outcome: The proposed toolkit and extensible schema allows researchers to customize the data collection tasks for a variety of purposes, including annotations, drawing, and reading behavior analytics.
Influence Functions for Sequence Tagging Models (2022.findings-emnlp)

Copied to clipboard

Challenge: Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling are standard tasks in NLP, but there has been little work on interpretability methods for sequence taging.
Approach: They propose to extend influence functions to sequence tagging tasks by identifying noisy annotations in NER corpora.
Outcome: The proposed methods are able to identify noisy annotations in NER corpora and are scalable.
Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction (N19-1)

Copied to clipboard

Challenge: Modern NLP systems require high-quality annotations, but experts are expensive and lay annotators may not have the knowledge to provide high- quality annotations.
Approach: They propose to directly model instance difficulty to improve model performance and to route instances to appropriate annotators.
Outcome: The proposed model improves performance on a biomedical information extraction task using expert and lay annotations.
PDFTriage: Question Answering over Long, Structured Documents (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing approaches to document QA use a pre-retrieval step to retrieve the relevant context from documents, but this is incongruous with the user's mental model of the document.
Approach: They propose an approach called PDFTriage that enables models to retrieve the context based on either structure or content.
Outcome: The proposed approach can retrieve context based on structure or content across several classes of questions where existing retrieval-augmented LLMs fail.
Self-Repetition in Abstractive Neural Summarizers (2022.aacl-short)

Copied to clipboard

Challenge: a quantitative and qualitative analysis of self-repetition in neural summarization systems is needed to improve training.
Approach: They propose a quantitative and qualitative analysis of self-repetition in neural summarization systems . they analyze the behavior of three popular architectures fine-tuned on five datasets .
Outcome: The proposed model produces formulaic repetition in summaries, but not in summarization tasks.
Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning (2024.eacl-long)

Copied to clipboard

Challenge: Existing prompt transfer techniques lack consideration for dialogue-specific information.
Approach: They propose a method which leverages skeleton generation as extra supervision that functions as a medium connecting the distinct source and target task.
Outcome: The proposed method significantly outperforms baselines on two dialogue summarization benchmarks.
Emotion Impacts Speech Recognition Performance (N19-3)

Copied to clipboard

Challenge: Existing studies show that speech recognition systems depend on multiple factors including lexical content, speaker identity and dialect.
Approach: They propose a method that evaluates the impact of emotion on recognition even when manual transcripts are not available.
Outcome: The proposed method allows to evaluate the impact of emotion on recognition even when manual transcripts are not available.
Learning the Visualness of Text Using Large Vision-Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Visual text evokes an image in a person’s mind, while non-visual text fails to do so.
Approach: They propose a method to automatically detect visualness in text to enable text-to-image retrieval and generation models to augment text with relevant images.
Outcome: The proposed method performs better than several baseline models and heuristics for the task.
DocTime: A Document-level Temporal Dependency Graph Parser (2022.naacl-main)

Copied to clipboard

Challenge: Document dependency graphs (TDGs) are used to understand the temporal relations between events mentioned in a document and to improve downstream tasks such as timeline creation and time-aware summarization.
Approach: They propose a temporal dependency graph parser that takes input from a text document and produces a graph that incorporates longer range dependencies.
Outcome: The proposed framework outperforms existing models on three datasets and improves tasks such as timeline creation, time-aware summarization, and temporal information extraction.
Factual or Contextual? Disentangling Error Types in Entity Description Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing evaluation practices only distinguish between model generated referring expressions being accurate (ground-truth) versus inaccurate (not groundtruth).
Approach: They propose to integrate indicators for factual inconsistencies and contextual incongruities into automated evaluations of language models to assess the differences in error types across familiar vs unfamiliar entities.
Outcome: The proposed evaluation paradigm disentangles factuality and congruity errors in natural contexts.
Self-Cleaning: Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods to train named entity recognition models on noisy data are expensive and time-intensive to accumulate.
Approach: They propose to denoise noisy NER data with guidance from a small set of clean instances.
Outcome: The proposed method can improve on large-scale datasets with a small guidance set.
Trialstreamer: Mapping and Browsing Medical Evidence in Real-Time (2020.acl-demos)

Copied to clipboard

Challenge: Trialstreamer extracts key pieces of information that clinicians need when appraising the literature . the highest-quality evidence to inform healthcare practice comes from randomized controlled trials .
Approach: They propose a system that extracts key pieces of information from biomedical abstracts and combines them into a database of clinical trial reports.
Outcome: The proposed system extracts descriptions of trial participants, treatments compared in each arm, and which outcomes were measured.
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature (P18-1)

Copied to clipboard

Challenge: In 2015 alone, about 100 manuscripts describing randomized controlled trials for medical interventions were published every day.
Approach: They propose a corpus of 5,000 medical articles annotated with demarcations of text spans that describe the Patient population enrolled, the Interventions studied and to what they were Compared, and the Outcomes measured.
Outcome: The proposed corpus includes 5,000 medical articles describing clinical randomized controlled trials.
MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods learn features from word-level or region-level but fail to consider both simultaneously.
Approach: They propose a multi-modal multi-granular pre-training framework that encodes page-level, region-level and word-level information at the same time.
Outcome: The proposed model learns features from word-level and region-level but fails to consider both simultaneously.
Evaluating Multiple System Summary Lengths: A Case Study (D18-1)

Copied to clipboard

Challenge: Practical summarization systems are expected to produce summaries of varying lengths, per user needs.
Approach: They propose to use ROUGE metric to evaluate system summaries of multiple lengths.
Outcome: The evaluation protocol in question is competitive, the authors show . they found that the evaluation protocol is competitive with existing benchmarks.
Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns (2022.findings-acl)

Copied to clipboard

Challenge: Adaptive Axis Attention learns different attention patterns for each task and model layer . sparse attention patterns do not improve the run time of the models but they reduce model memory requirements .
Approach: They propose a method that learns different attention patterns for each Transformer layer . they propose 'adaptive axis attention' method that identifies important tokens .
Outcome: The proposed method does not require pre-training to accommodate sparse attention patterns.
The Feasibility of Embedding Based Automatic Evaluation for Single Document Summarization (D19-1)

Copied to clipboard

Challenge: Existing evaluation methods for summarization systems measure semantic overlap between a system summary and a human reference on word-string level.
Approach: They propose to use distributed representations to evaluate system summary and human reference on word-string level.
Outcome: The proposed representations outperform ROUGE on recent corpora but are less good on test data used in previous studies.
Syntactic Patterns Improve Information Extraction for Medical Search (N18-2)

Copied to clipboard

Challenge: Medical professionals search the literature by specifying the type of patients, the medical intervention(s) and the outcome measure(s).
Approach: They propose to exploit the availability of structured abstracts to extract medically relevant information from syntactic patterns.
Outcome: The proposed models differ from the constituent unigrams in the extracted patterns, suggesting that they capture contextual information that is otherwise lost.
A Critical Analysis of Document Out-of-Distribution Detection (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing document understanding models focus on single-modal inputs such as images or texts.
Approach: They propose to use a spatial-aware adapter to adapt transformer-based language models to document domain to exploit multi-modal information.
Outcome: The proposed model significantly improves the OOD detection performance compared to using a standard language model and to competitive baselines.
SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps (2025.findings-emnlp)

Copied to clipboard

Challenge: SQLSpace is a representation for text-to-SQL examples derived with minimal human intervention.
Approach: They introduce SQLSpace, a human-interpretable, generalizable, compact representation for text-to-SQL examples . they demonstrate that SQLSpace enables analysis that would be difficult with raw examples alone .
Outcome: The proposed representations are human-interpretable and generalizable . they are used to evaluate models with a granularity beyond overall accuracy scores .
The Utility and Interplay of Gazetteers and Entity Segmentation for Named Entity Recognition in English (2021.findings-acl)

Copied to clipboard

Challenge: Recent papers introduce methods to incorporate gazetteer features and entity segmentation techniques in neural named entity recognition models.
Approach: They propose to integrate gazetteer features and entity segmentation techniques into neural named entity recognition models.
Outcome: The proposed methods improve entity segmentation and not just entity typing.
Named Entity Recognition in a Very Homogenous Domain (2023.findings-eacl)

Copied to clipboard

Challenge: Developing models that perform well on several domains is important, but domain is vague and can be adapted to a new domain.
Approach: They find that even news articles from the same newspaper in English can be considered different domains.
Outcome: The proposed model performs better on out-of-domain data than on specialized data.

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