Search Results for author:
Found 98 papers, 50 papers with code
Velocidapter: Task-oriented Dialogue Comprehension Modeling Pairing Synthetic Text Generation with Domain Adaptation
We introduce a synthetic dialogue generation framework, Velocidapter, which addresses the corpus availability problem for dialogue comprehension.
GL-CLeF: A Global–Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding
Specifically, we employ contrastive learning, leveraging bilingual dictionaries to construct multilingual views of the same utterance, then encourage their representations to be more similar than negative example pairs, which achieves to explicitly align representations of similar sentences across languages.
Re-examining the Role of Schema Linking in Text-to-SQL
By providing a schema linking corpus based on the Spider text-to-SQL dataset, we systematically study the role of schema linking.
Analyzing the Domain Robustness of Pretrained Language Models, Layer by Layer
The robustness of pretrained language models(PLMs) is generally measured using performance drops on two or more domains.
SciWING– A Software Toolkit for Scientific Document Processing
We introduce SciWING, an open-source soft-ware toolkit which provides access to state-of-the-art pre-trained models for scientific document processing (SDP) tasks, such as citation string parsing, logical structure recovery and citation intent classification.
Lightweight Contextual Logical Structure Recovery
Logical structure recovery in scientific articles associates text with a semantic section of the article.
ISQA: Informative Factuality Feedback for Scientific Summarization
We propose Iterative Facuality Refining on Informative Scientific Question-Answering (ISQA) feedback\footnote{Code is available at \url{https://github. com/lizekai-richard/isqa}}, a method following human learning theories that employs model-generated feedback consisting of both positive and negative information.
Discrete Semantic Tokenization for Deep CTR Prediction
Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios.
Beyond Memorization: The Challenge of Random Memory Access in Language Models
Through carefully-designed synthetic tasks, covering the scenarios of full recitation, selective recitation and grounded question answering, we reveal that LMs manage to sequentially access their memory while encountering challenges in randomly accessing memorized content.
NNOSE: Nearest Neighbor Occupational Skill Extraction
The labor market is changing rapidly, prompting increased interest in the automatic extraction of occupational skills from text.
Lightweight Modality Adaptation to Sequential Recommendation via Correlation Supervision
Specifically, we introduce a novel method that enhances the learning of embeddings in SR through the supervision of modality correlations.
ChOiRe: Characterizing and Predicting Human Opinions with Chain of Opinion Reasoning
Aligning language models (LMs) with human opinion is challenging yet vital to enhance their grasp of human values, preferences, and beliefs.
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
Annotated data plays a critical role in Natural Language Processing (NLP) in training models and evaluating their performance.
UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking
Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, ignoring unlabelled data in the target domain.
QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking
Fact-checking real-world claims often requires complex, multi-step reasoning due to the absence of direct evidence to support or refute them.
Automatic Feature Fairness in Recommendation via Adversaries
We leverage the Adaptive Adversarial perturbation based on the widely-applied Factorization Machine (AAFM) as our backbone model.
Investigating Zero- and Few-shot Generalization in Fact Verification
In this paper, we explore zero- and few-shot generalization for fact verification (FV), which aims to generalize the FV model trained on well-resourced domains (e. g., Wikipedia) to low-resourced domains that lack human annotations.
A Conversation is Worth A Thousand Recommendations: A Survey of Holistic Conversational Recommender Systems
However, not all CRS approaches use human conversations as their source of interaction data; the majority of prior CRS work simulates interactions by exchanging entity-level information.
FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generation
We introduce the task of real-world information-seeking follow-up question generation (FQG), which aims to generate follow-up questions seeking a more in-depth understanding of an initial question and answer.
Adaptive Multi-Modalities Fusion in Sequential Recommendation Systems
We propose a graph-based approach (named MMSR) to fuse modality features in an adaptive order, enabling each modality to prioritize either its inherent sequential nature or its interplay with other modalities.
Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization
However, existing work has focused on training models on centralized data, neglecting real-world scenarios where meeting data are infeasible to collect centrally, due to their sensitive nature.
Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models
Video question-answering is a fundamental task in the field of video understanding.
Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation
A challenge in the Dialogue State Tracking (DST) field is adapting models to new domains without using any supervised data, zero-shot domain adaptation.
Songs Across Borders: Singable and Controllable Neural Lyric Translation
The development of general-domain neural machine translation (NMT) methods has advanced significantly in recent years, but the lack of naturalness and musical constraints in the outputs makes them unable to produce singable lyric translations.
The ACL OCL Corpus: Advancing Open Science in Computational Linguistics
We present ACL OCL, a scholarly corpus derived from the ACL Anthology to assist Open scientific research in the Computational Linguistics domain.
ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning
We introduce ECHo (Event Causality Inference via Human-Centric Reasoning), a diagnostic dataset of event causality inference grounded in visio-linguistic social scenarios.
On the Risk of Misinformation Pollution with Large Language Models
In this paper, we comprehensively investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation and its subsequent impact on information-intensive applications, particularly Open-Domain Question Answering (ODQA) systems.
SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables
Current scientific fact-checking benchmarks exhibit several shortcomings, such as biases arising from crowd-sourced claims and an over-reliance on text-based evidence.
Fact-Checking Complex Claims with Program-Guided Reasoning
Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning.
Self-Evaluation Guided Beam Search for Reasoning
Stochastic beam search balances exploitation and exploration of the search space with temperature-controlled randomness.
Improving Recommendation Systems with User Personality Inferred from Product Reviews
Experiments on our two newly contributed personality datasets -- Amazon-beauty and Amazon-music -- validate our hypothesis, showing performance boosts of 3--28%. Our analysis uncovers that varying personality types contribute differently to recommendation performance: open and extroverted personalities are most helpful in music recommendation, while a conscientious personality is most helpful in beauty product recommendation.
UDApter -- Efficient Domain Adaptation Using Adapters
We even outperform unsupervised domain adaptation methods such as DANN and DSN in sentiment classification, and we are within 0. 85% F1 for natural language inference task, by fine-tuning only a fraction of the full model parameters.
Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge
In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables.
MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences
Existing multimodal tasks mostly target at the complete input modality setting, i. e., each modality is either complete or completely missing in both training and test sets.
CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations
Knowledge-grounded dialog systems need to incorporate smooth transitions among knowledge selected for generating responses, to ensure that dialog flows naturally.
Modeling and Leveraging Prerequisite Context in Recommendation
Prerequisites can play a crucial role in users' decision-making yet recommendation systems have not fully utilized such contextual background knowledge.
Comparative Snippet Generation
We model product reviews to generate comparative responses consisting of positive and negative experiences regarding the product.
So Different Yet So Alike! Constrained Unsupervised Text Style Transfer
Automatic transfer of text between domains has become popular in recent times.
GL-CLeF: A Global-Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding
We present Global--Local Contrastive Learning Framework (GL-CLeF) to address this shortcoming.
TraVLR: Now You See It, Now You Don't! A Bimodal Dataset for Evaluating Visio-Linguistic Reasoning
Furthermore, existing V+L benchmarks often report global accuracy scores on the entire dataset, making it difficult to pinpoint the specific reasoning tasks that models fail and succeed at.
Attacking Open-domain Question Answering by Injecting Misinformation
We curate both human-written and model-generated false documents that we inject into the evidence corpus of QA models and assess the impact on the performance of these systems.
Interpreting the Robustness of Neural NLP Models to Textual Perturbations
In this work, we test the hypothesis that the extent to which a model is affected by an unseen textual perturbation (robustness) can be explained by the learnability of the perturbation (defined as how well the model learns to identify the perturbation with a small amount of evidence).
Zero-shot Fact Verification by Claim Generation
However, for each new domain that requires fact verification, creating a dataset by manually writing claims and linking them to their supporting evidence is expensive.
Reliability Testing for Natural Language Processing Systems
Questions of fairness, robustness, and transparency are paramount to address before deploying NLP systems.
DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension
Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC.
Ranked #4 on
Question Answering
on Molweni
N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking
Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure.
Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework
We introduce a deep learning model to learn the set of enumerated job skills associated with a job description.
Exploring Question-Specific Rewards for Generating Deep Questions
Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing.
Domain Divergences: a Survey and Empirical Analysis
Domain divergence plays a significant role in estimating the performance of a model in new domains.
Unsupervised Multi-hop Question Answering by Question Generation
Obtaining training data for multi-hop question answering (QA) is time-consuming and resource-intensive.
Multi-modal Cooking Workflow Construction for Food Recipes
Understanding food recipe requires anticipating the implicit causal effects of cooking actions, such that the recipe can be converted into a graph describing the temporal workflow of the recipe.
FANG: Leveraging Social Context for Fake News Detection Using Graph Representation
In particular, FANG yields significant improvements for the task of fake news detection, and it is robust in the case of limited training data.
The MUIR Framework: Cross-Linking MOOC Resources to Enhance Discussion Forums
We demonstrate the feasibility of this approach to the automatic identification, linking and resolution -- a task known as Wikification -- of learning resources mentioned on MOOC discussion forums, from a harvested collection of 100K+ resources.
It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations
Training on only perfect Standard English corpora predisposes pre-trained neural networks to discriminate against minorities from non-standard linguistic backgrounds (e. g., African American Vernacular English, Colloquial Singapore English, etc.).
Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen
The curse of knowledge can impede communication between experts and laymen.
Mind Your Inflections! Improving NLP for Non-Standard Englishes with Base-Inflection Encoding
Inflectional variation is a common feature of World Englishes such as Colloquial Singapore English and African American Vernacular English.
Semantic Graphs for Generating Deep Questions
This paper proposes the problem of Deep Question Generation (DQG), which aims to generate complex questions that require reasoning over multiple pieces of information of the input passage.
Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure
Research into the area of multiparty dialog has grown considerably over recent years.
Ranked #7 on
Discourse Parsing
on Molweni
SciWING -- A Software Toolkit for Scientific Document Processing
We introduce SciWING, an open-source software toolkit which provides access to pre-trained models for scientific document processing tasks, inclusive of citation string parsing and logical structure recovery.
Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models.
A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages
We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process.
Sentiment Aware Neural Machine Translation
We conducted tests with both sentiment and non-sentiment bearing contexts to examine the effectiveness of our methods.
What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?
Based on our experiments on the 5 key MCRC datasets - RACE, MCTest, MCScript, MCScript2. 0, DREAM - we observe that 1) fine-tuned BERT mainly learns how keywords lead to correct prediction, instead of learning semantic understanding and reasoning; and 2) BERT does not need correct syntactic information to solve the task; 3) there exists artifacts in these datasets such that they can be solved even without the full context.
The CL-SciSumm Shared Task 2018: Results and Key Insights
This overview describes the official results of the CL-SciSumm Shared Task 2018 -- the first medium-scale shared task on scientific document summarization in the computational linguistics (CL) domain.
Overview and Results: CL-SciSumm Shared Task 2019
All papers are from the open access research papers in the CL domain.
Glocal: Incorporating Global Information in Local Convolution for Keyphrase Extraction
Graph Convolutional Networks (GCNs) are a class of spectral clustering techniques that leverage localized convolution filters to perform supervised classification directly on graphical structures.
Predicting Helpful Posts in Open-Ended Discussion Forums: A Neural Architecture
Users participate in online discussion forums to learn from others and share their knowledge with the community.
Dataset Mention Extraction and Classification
Datasets are integral artifacts of empirical scientific research.
When to reply? Context Sensitive Models to Predict Instructor Interventions in MOOC Forums
We propose novel attention based models to infer the amount of latent context necessary to predict instructor intervention.
Recent Advances in Neural Question Generation
Emerging research in Neural Question Generation (NQG) has started to integrate a larger variety of inputs, and generating questions requiring higher levels of cognition.
Resource Mention Extraction for MOOC Discussion Forums
We propose the novel problem of learning resource mention identification in MOOC forums.
Neural Multi-Task Learning for Citation Function and Provenance
Citation function and provenance are two cornerstone tasks in citation analysis.
Treatment Side Effect Prediction from Online User-generated Content
With Health 2. 0, patients and caregivers increasingly seek information regarding possible drug side effects during their medical treatments in online health communities.
Identifying Emergent Research Trends by Key Authors and Phrases
Identifying emergent research trends is a key issue for both primary researchers as well as secondary research managers.
Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures
Existing solutions to task-oriented dialogue systems follow pipeline designs which introduces architectural complexity and fragility.
Modeling Temporal Progression of Emotional Status in Mental Health Forum: A Recurrent Neural Net Approach
We study the problem of predicting a patient{'}s emotional status in the future from her past posts and we propose a Recurrent Neural Network (RNN) based architecture to address it.
Fast Matrix Factorization for Online Recommendation with Implicit Feedback
To address this, we specifically design a new learning algorithm based on the element-wise Alternating Least Squares (eALS) technique, for efficiently optimizing a MF model with variably-weighted missing data.
BiRank: Towards Ranking on Bipartite Graphs
In this paper, we study the problem of ranking vertices of a bipartite graph, based on the graph's link structure as well as prior information about vertices (which we term a query vector).
WING-NUS at SemEval-2017 Task 10: Keyphrase Extraction and Classification as Joint Sequence Labeling
We describe an end-to-end pipeline processing approach for SemEval 2017{'}s Task 10 to extract keyphrases and their relations from scientific publications.
Using Discourse Signals for Robust Instructor Intervention Prediction
We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs).
A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation
Thus we have also applied word embeddings to the novel task of cross-lingual WSD for Chinese and provide a public dataset for further benchmarking.
QANUS: An Open-source Question-Answering Platform
In this paper, we motivate the need for a publicly available, generic software framework for question-answering (QA) systems.
Linear Segmentation and Segment Significance
We present a new method for discovering a segmental discourse structure of a document while categorizing segment function.
