Search Results for author:
Found 57 papers, 7 papers with code
DocTime: A Document-level Temporal Dependency Graph Parser
We introduce DocTime - a novel temporal dependency graph (TDG) parser that takes as input a text document and produces a temporal dependency graph.
Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns
We present a comprehensive study of sparse attention patterns in Transformer models.
Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances
To achieve state-of-the-art performance, one still needs to train NER models on large-scale, high-quality annotated data, an asset that is both costly and time-intensive to accumulate.
AutoDAN: Automatic and Interpretable Adversarial Attacks on Large Language Models
We can also customize the objective of \texttt{AutoDAN} to leak system prompts, beyond the ability to elicit harmful content from the model, demonstrating the versatility of the approach.
PDFTriage: Question Answering over Long, Structured Documents
Representing such structured documents as plain text is incongruous with the user's mental model of these documents with rich structure.
Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness
Academic literature does not give much guidance on how to build the best possible customer-facing summarization system from existing research components.
Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer
In this paper, we focus on improving the prompt transfer from dialogue state tracking to dialogue summarization and propose Skeleton-Assisted Prompt Transfer (SAPT), which leverages skeleton generation as extra supervision that functions as a medium connecting the distinct source and target task and resulting in the model's better consumption of dialogue state information.
Learning the Visualness of Text Using Large Vision-Language Models
Visual text evokes an image in a person's mind, while non-visual text fails to do so.
Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization
Prior work often treated figure caption generation as a vision-to-language task.
MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
In contrast, region-level models attempt to encode regions corresponding to paragraphs or text blocks into a single embedding, but they perform worse with additional word-level features.
Influence Functions for Sequence Tagging Models
We show the practical utility of segment influence by using the method to identify systematic annotation errors in two named entity recognition corpora.
Self-Repetition in Abstractive Neural Summarizers
In a regression analysis, we find that the three architectures have different propensities for repeating content across output summaries for inputs, with BART being particularly prone to self-repetition.
Unified Pretraining Framework for Document Understanding
Document intelligence automates the extraction of information from documents and supports many business applications.
Ranked #6 on
Document Layout Analysis
on PubLayNet val
UniDoc: Unified Pretraining Framework for Document Understanding
Document intelligence automates the extraction of information from documents and supports many business applications.
Temporal Effects on Pre-trained Models for Language Processing Tasks
Keeping the performance of language technologies optimal as time passes is of great practical interest.
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution
The ability to quantify incivility online, in news and in congressional debates, is of great interest to political scientists.
Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relations
Here we consider the end-to-end task of both (a) extracting treatments and outcomes from full-text articles describing clinical trials (entity identification) and, (b) inferring the reported results for the former with respect to the latter (relation extraction).
Trialstreamer: Mapping and Browsing Medical Evidence in Real-Time
We apply the system at scale to all reports of randomized controlled trials indexed in MEDLINE, powering the automatic generation of evidence maps, which provide a global view of the efficacy of different interventions combining data from all relevant clinical trials on a topic.
Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve
We examine these questions by contrasting the performance of several variants of LSTM-CRF architectures for named entity recognition, with some provided only representations of the context as features.
Entity-Switched Datasets: An Approach to Auditing the In-Domain Robustness of Named Entity Recognition Models
We propose a method for auditing the in-domain robustness of systems, focusing specifically on differences in performance due to the national origin of entities.
The Feasibility of Embedding Based Automatic Evaluation for Single Document Summarization
ROUGE is widely used to automatically evaluate summarization systems.
Word Embeddings (Also) Encode Human Personality Stereotypes
Word representations trained on text reproduce human implicit bias related to gender, race and age.
Emotion Impacts Speech Recognition Performance
It has been established that the performance of speech recognition systems depends on multiple factors including the lexical content, speaker identity and dialect.
Browsing Health: Information Extraction to Support New Interfaces for Accessing Medical Evidence
Typical information needs, such as retrieving a full list of medical interventions for a given condition, or finding the reported efficacy of a particular treatment with respect to a specific outcome of interest cannot be straightforwardly posed in typical text-box search.
Evaluation of named entity coreference
It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct entity name.
How to Compare Summarizers without Target Length? Pitfalls, Solutions and Re-Examination of the Neural Summarization Literature
We show that plain ROUGE F1 scores are not ideal for comparing current neural systems which on average produce different lengths.
Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction
Experiments on a complex biomedical information extraction task using expert and lay annotators show that: (i) simply excluding from the training data instances predicted to be difficult yields a small boost in performance; (ii) using difficulty scores to weight instances during training provides further, consistent gains; (iii) assigning instances predicted to be difficult to domain experts is an effective strategy for task routing.
Named Person Coreference in English News
Here, we evaluate two state of the art coreference resolution systems on the subtask of Named Person Coreference, in which we are interested in identifying a person mentioned by name, along with all other mentions of the person, by pronoun or generic noun phrase.
Evaluating Multiple System Summary Lengths: A Case Study
Practical summarization systems are expected to produce summaries of varying lengths, per user needs.
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature
We present a corpus of 5, 000 richly annotated abstracts of medical articles describing clinical randomized controlled trials.
Syntactic Patterns Improve Information Extraction for Medical Search
Medical professionals search the published literature by specifying the type of patients, the medical intervention(s) and the outcome measure(s) of interest.
Aggregating and Predicting Sequence Labels from Crowd Annotations
Despite sequences being core to NLP, scant work has considered how to handle noisy sequence labels from multiple annotators for the same text.
Combining Lexical and Syntactic Features for Detecting Content-dense Texts in News
On manually annotated data, we compare the performance of domain-specific classifiers, trained on data only from a given news domain and a general classifier in which data from all four domains is pooled together.
Detecting (Un)Important Content for Single-Document News Summarization
We present a robust approach for detecting intrinsic sentence importance in news, by training on two corpora of document-summary pairs.
Improving the Annotation of Sentence Specificity
We found that the lack of specificity distributes evenly among immediate prior context, long distance prior context and no prior context.
A Repository of State of the Art and Competitive Baseline Summaries for Generic News Summarization
In the period since 2004, many novel sophisticated approaches for generic multi-document summarization have been developed.
What Makes Writing Great? First Experiments on Article Quality Prediction in the Science Journalism Domain
We show that the distinction between great and typical articles can be detected fairly accurately, and that the entire spectrum of our features contribute to the distinction.
A corpus of general and specific sentences from news
We present a corpus of sentences from news articles that are annotated as general or specific.
