Search Results for author:
Found 85 papers, 44 papers with code
Does BERT Know that the IS-A Relation Is Transitive?
The success of a natural language processing (NLP) system on a task does not amount to fully understanding the complexity of the task, typified by many deep learning models.
Frustratingly Easy System Combination for Grammatical Error Correction
In this paper, we formulate system combination for grammatical error correction (GEC) as a simple machine learning task: binary classification.
Ranked #3 on
Grammatical Error Correction
on BEA-2019 (test)
Domain Generalization for Text Classification with Memory-Based Supervised Contrastive Learning
While there is much research on cross-domain text classification, most existing approaches focus on one-to-one or many-to-one domain adaptation.
Grammatical Error Correction: Are We There Yet?
There has been much recent progress in natural language processing, and grammatical error correction (GEC) is no exception.
Grammatical Error Correction with Contrastive Learning in Low Error Density Domains
Although grammatical error correction (GEC) has achieved good performance on texts written by learners of English as a second language, performance on low error density domains where texts are written by English speakers of varying levels of proficiency can still be improved.
Improved Word Sense Disambiguation with Enhanced Sense Representations
Current state-of-the-art supervised word sense disambiguation (WSD) systems (such as GlossBERT and bi-encoder model) yield surprisingly good results by purely leveraging pre-trained language models and short dictionary definitions (or glosses) of the different word senses.
Ranked #2 on
Word Sense Disambiguation
on Supervised:
Efficient and Interpretable Grammatical Error Correction with Mixture of Experts
Error type information has been widely used to improve the performance of grammatical error correction (GEC) models, whether for generating corrections, re-ranking them, or combining GEC models.
Self-Judge: Selective Instruction Following with Alignment Self-Evaluation
To enhance the reliability of LLMs in following instructions, we propose the study of selective instruction following, whereby the system declines to execute instructions if the anticipated response quality is low.
Preference-Guided Reflective Sampling for Aligning Language Models
The process of data sampling is crucial, as it significantly influences the success of policy improvement.
Unsupervised Grammatical Error Correction Rivaling Supervised Methods
Empirical results show that our GEC system outperforms previous unsupervised GEC systems, and achieves performance comparable to supervised GEC systems without ensemble.
Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
Therefore, it is crucial for LLMs to understand the concept of temporal knowledge.
On the Robustness of Question Rewriting Systems to Questions of Varying Hardness
In conversational question answering (CQA), the task of question rewriting~(QR) in context aims to rewrite a context-dependent question into an equivalent self-contained question that gives the same answer.
System Combination via Quality Estimation for Grammatical Error Correction
However, we found that existing GEC quality estimation models are not good enough in differentiating good corrections from bad ones, resulting in a low F0. 5 score when used for system combination.
Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data
We conducted experiments on document-level and biomedical relation extraction datasets, and the results showed that our proposed self-training framework consistently outperforms existing competitive methods on the Re-DocRED and ChemDisgene datasets when the training data are incompletely annotated.
Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
In this paper, we introduce a comprehensive probing dataset \tempreason to evaluate the temporal reasoning capability of large language models.
Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation.
Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic
The temporal aspect is a significant dimension of our reality.
Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
To answer this question, we evaluate test-time adaptation (TTA) to improve a model after deployment.
Grammatical Error Correction: A Survey of the State of the Art
Grammatical Error Correction (GEC) is the task of automatically detecting and correcting errors in text.
Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction
We analyze the causes and effects of the overwhelming false negative problem in the DocRED dataset.
Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation
Our model consistently outperforms strong baselines and its performance exceeds the previous SOTA by 1. 36 F1 and 1. 46 Ign_F1 score on the DocRED leaderboard.
Ranked #2 on
Relation Extraction
on DocRED
Document-level Relation Extraction
Knowledge Distillation
+2
A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues
We leverage unlabeled data to improve classification in student training where we employ two teachers to refine the labeling of unlabeled data through teacher-student learning in a bootstrapping manner.
System Combination for Grammatical Error Correction Based on Integer Programming
In this paper, we propose a system combination method for grammatical error correction (GEC), based on nonlinear integer programming (IP).
Diversity-Driven Combination for Grammatical Error Correction
However, most existing state-of-the-art GEC approaches are based on similar sequence-to-sequence neural networks, so the gains are limited from combining the outputs of component systems similar to one another.
Translating from Morphologically Complex Languages: A Paraphrase-Based Approach
We propose a novel approach to translating from a morphologically complex language.
A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents
Distantly supervised datasets for relation extraction mostly focus on sentence-level extraction, and they cover very few relations.
A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection
One of the major challenges is that a dialogue system may generate an undesired utterance leading to a dialogue breakdown, which degrades the overall interaction quality.
Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model
Experimental results show that our proposed method achieves significant performance improvements over the state-of-the-art pretrained cross-lingual language model in the CLCD setting.
A Survey of Unsupervised Dependency Parsing
Syntactic dependency parsing is an important task in natural language processing.
Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training
To improve the robustness of self-training, in this paper we present class-aware feature self-distillation (CFd) to learn discriminative features from PrLMs, in which PrLM features are self-distilled into a feature adaptation module and the features from the same class are more tightly clustered.
Learning to Identify Follow-Up Questions in Conversational Question Answering
Despite recent progress in conversational question answering, most prior work does not focus on follow-up questions.
Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?
Multi-hop question answering (QA) requires a model to retrieve and integrate information from different parts of a long text to answer a question.
Effective Attention Modeling for Neural Relation Extraction
Relation extraction is the task of determining the relation between two entities in a sentence.
Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction
A relation tuple consists of two entities and the relation between them, and often such tuples are found in unstructured text.
Ranked #1 on
Relation Extraction
on NYT24
Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations
Contextualized word representations are able to give different representations for the same word in different contexts, and they have been shown to be effective in downstream natural language processing tasks, such as question answering, named entity recognition, and sentiment analysis.
Ranked #14 on
Word Sense Disambiguation
on Supervised:
Learning from the Experience of Doctors: Automated Diagnosis of Appendicitis Based on Clinical Notes
The objective of this work is to develop an automated diagnosis system that is able to predict the probability of appendicitis given a free-text emergency department (ED) note and additional structured information (e. g., lab test results).
Cross-Sentence Grammatical Error Correction
Automatic grammatical error correction (GEC) research has made remarkable progress in the past decade.
Improving the Robustness of Question Answering Systems to Question Paraphrasing
Despite the advancement of question answering (QA) systems and rapid improvements on held-out test sets, their generalizability is a topic of concern.
An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a natural language sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
Neural Quality Estimation of Grammatical Error Correction
We also show that a state-of-the-art GEC system can be improved when quality scores are used as features for re-ranking the N-best candidates.
Ranked #2 on
Grammatical Error Correction
on Restricted
A Nil-Aware Answer Extraction Framework for Question Answering
However, current approaches suffer from an impractical assumption that every question has a valid answer in the associated passage.
Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification
We consider the cross-domain sentiment classification problem, where a sentiment classifier is to be learned from a source domain and to be generalized to a target domain.
A Reassessment of Reference-Based Grammatical Error Correction Metrics
Previous studies of the correlation of these metrics with human quality judgments were inconclusive, due to the lack of appropriate significance tests, discrepancies in the methods, and choice of datasets used.
Effective Attention Modeling for Aspect-Level Sentiment Classification
First, we propose a method for target representation that better captures the semantic meaning of the opinion target.
Exploiting Document Knowledge for Aspect-level Sentiment Classification
Attention-based long short-term memory (LSTM) networks have proven to be useful in aspect-level sentiment classification.
Upping the Ante: Towards a Better Benchmark for Chinese-to-English Machine Translation
Our goal in this paper is to propose a benchmark in evaluation setup for Chinese-to-English machine translation, such that the effectiveness of a new proposed MT approach can be directly compared to previous approaches.
A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction
We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network.
Ranked #1 on
Grammatical Error Correction
on Restricted
A Question-Focused Multi-Factor Attention Network for Question Answering
Neural network models recently proposed for question answering (QA) primarily focus on capturing the passage-question relation.
Ranked #4 on
Question Answering
on NewsQA
Connecting the Dots: Towards Human-Level Grammatical Error Correction
We build a grammatical error correction (GEC) system primarily based on the state-of-the-art statistical machine translation (SMT) approach, using task-specific features and tuning, and further enhance it with the modeling power of neural network joint models.
An Unsupervised Neural Attention Model for Aspect Extraction
Unlike topic models which typically assume independently generated words, word embedding models encourage words that appear in similar contexts to be located close to each other in the embedding space.
A Dependency-Based Neural Reordering Model for Statistical Machine Translation
In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge.
Automated Anonymization as Spelling Variant Detection
Personal health information (PHI) (such as name and identification number) needs to be removed so that patients cannot be identified.
To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation
Reordering poses a major challenge in machine translation (MT) between two languages with significant differences in word order.
Neural Network Translation Models for Grammatical Error Correction
Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy.
Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction
Grammatical error correction (GEC) is the task of detecting and correcting grammatical errors in texts written by second language learners.
Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages
We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones.
