Search Results for author:
Found 59 papers, 24 papers with code
Say ‘YES’ to Positivity: Detecting Toxic Language in Workplace Communications
Specifically, the lack of corpus, sparsity of toxicity in enterprise emails, and well-defined criteria for annotating toxic conversations have prevented researchers from addressing the problem at scale.
An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e. g., edge) devices, tend to lag behind in terms of response quality.
Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation
Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions, just out of the box, but they are often trained with a single task in mind.
Automatic Pair Construction for Contrastive Post-training
Remarkably, our automatic contrastive post-training further improves the performance of Orca, already a state-of-the-art instruction learning model tuned with GPT-4 outputs, to outperform ChatGPT.
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks.
FedJETs: Efficient Just-In-Time Personalization with Federated Mixture of Experts
Our gating function harnesses the knowledge of a pretrained model common expert to enhance its routing decisions on-the-fly.
GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
Generalization to unseen tasks is an important ability for few-shot learners to achieve better zero-/few-shot performance on diverse tasks.
Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback
We explore multiple types of help players can give to the AI to guide it and analyze the impact of this help in AI behavior, resulting in performance improvements.
An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models
Large-scale Pre-Trained Language Models (PTLMs) capture knowledge from massive human-written data which contains latent societal biases and toxic contents.
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models.
Boosting Natural Language Generation from Instructions with Meta-Learning
Recent work has shown that language models (LMs) trained with multi-task \textit{instructional learning} (MTIL) can solve diverse NLP tasks in zero- and few-shot settings with improved performance compared to prompt tuning.
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
Furthermore, existing MoE works do not consider computational constraints (e. g., FLOPs, latency) to guide their design.
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models.
PREME: Preference-based Meeting Exploration through an Interactive Questionnaire
The recent increase in the volume of online meetings necessitates automated tools for managing and organizing the material, especially when an attendee has missed the discussion and needs assistance in quickly exploring it.
Pathologies of Pre-trained Language Models in Few-shot Fine-tuning
Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from.
Knowledge Infused Decoding
Hence, they tend to suffer from counterfactual or hallucinatory generation when used in knowledge-intensive natural language generation (NLG) tasks.
Ranked #2 on
Question Answering
on KILT: ELI5
AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models
Our framework AutoDistil addresses above challenges with the following steps: (a) Incorporates inductive bias and heuristics to partition Transformer search space into K compact sub-spaces (K=3 for typical student sizes of base, small and tiny); (b) Trains one SuperLM for each sub-space using task-agnostic objective (e. g., self-attention distillation) with weight-sharing of students; (c) Lightweight search for the optimal student without re-training.
Compositional Generalization for Natural Language Interfaces to Web APIs
We define new compositional generalization tasks for NL2API which explore the models' ability to extrapolate from simple API calls in the training set to new and more complex API calls in the inference phase.
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
In this paper, we present Adversarial GLUE (AdvGLUE), a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks.
Ranked #1 on
Adversarial Robustness
on AdvGLUE
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
We demonstrate that while recent models reach human performance when they have access to large amounts of labeled data, there is a huge gap in performance in the few-shot setting for most tasks.
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights.
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding
Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks.
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners
The first is the use of self-training to leverage large amounts of unlabeled data for prompt-based FN in few-shot settings.
A Conditional Generative Matching Model for Multi-lingual Reply Suggestion
We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously.
An Exploratory Study on Long Dialogue Summarization: What Works and What's Next
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
MetaXT: Meta Cross-Task Transfer between Disparate Label Spaces
In this paper, we aim to the address of the problem of few shot task learning by exploiting and transferring from a different task which admits a related but disparate label space.
SummerTime: Text Summarization Toolkit for Non-experts
We also provide explanations for models and evaluation metrics to help users understand the model behaviors and select models that best suit their needs.
WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language Understanding
In this paper, we propose such a benchmark, named WALNUT (semi-WeAkly supervised Learning for Natural language Understanding Testbed), to advocate and facilitate research on weak supervision for NLU.
Fairness via Representation Neutralization
This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness sensitive information has been removed from the encoder.
XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation
While deep and large pre-trained models are the state-of-the-art for various natural language processing tasks, their huge size poses significant challenges for practical uses in resource constrained settings.
A Dataset and Baselines for Multilingual Reply Suggestion
Reply suggestion models help users process emails and chats faster.
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Extensive experiments on real-world low-resource languages - without access to large-scale monolingual corpora or large amounts of labeled data - for tasks like cross-lingual sentiment analysis and named entity recognition show the effectiveness of our approach.
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed.
Self-Training with Weak Supervision
In this work, we develop a weak supervision framework (ASTRA) that leverages all the available data for a given task.
NL-EDIT: Correcting semantic parse errors through natural language interaction
We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to generate a sequence of edits that can be applied to the initial parse to correct its errors.
SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing
Conversational Semantic Parsing (CSP) is the task of converting a sequence of natural language queries to formal language (e. g., SQL, SPARQL) that can be executed against a structured ontology (e. g. databases, knowledge bases).
Ranked #3 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Adaptive Self-training for Neural Sequence Labeling with Few Labels
Neural sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing.
Leveraging Structured Metadata for Improving Question Answering on the Web
We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking.
Structure-Grounded Pretraining for Text-to-SQL
Additionally, to evaluate different methods under more realistic text-table alignment settings, we create a new evaluation set Spider-Realistic based on Spider dev set with explicit mentions of column names removed, and adopt eight existing text-to-SQL datasets for cross-database evaluation.
Adaptive Self-training for Few-shot Neural Sequence Labeling
While self-training serves as an effective mechanism to learn from large amounts of unlabeled data -- meta-learning helps in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels.
Smart To-Do: Automatic Generation of To-Do Items from Emails
Intelligent features in email service applications aim to increase productivity by helping people organize their folders, compose their emails and respond to pending tasks.
Uncertainty-aware Self-training for Text Classification with Few Labels
Standard self-training mechanism randomly samples instances from the unlabeled pool to pseudo-label and augment labeled data.
An Empirical Study of Software Exceptions in the Field using Search Logs
Using the machine learning model, we extracted exceptions from raw queries and performed popularity, effort, success, query characteristic and web domain analysis.
Learning with Weak Supervision for Email Intent Detection
In this paper, we propose to leverage user actions as a source of weak supervision, in addition to a limited set of annotated examples, to detect intents in emails.
Smart To-Do : Automatic Generation of To-Do Items from Emails
Intelligent features in email service applications aim to increase productivity by helping people organize their folders, compose their emails and respond to pending tasks.
Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback
We study the task of semantic parse correction with natural language feedback.
Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer
In this paper, we study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications.
Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News
Social media has greatly enabled people to participate in online activities at an unprecedented rate.
Analyzing Web Search Behavior for Software Engineering Tasks
Subsequently, we propose a taxonomy of intents to identify the various contexts in which web search is used in software engineering.
Meta Label Correction for Noisy Label Learning
We view the label correction procedure as a meta-process and propose a new meta-learning based framework termed MLC (Meta Label Correction) for learning with noisy labels.
Ranked #9 on
Image Classification
on Clothing1M (using clean data)
(using extra training data)
Detecting Fake News with Weak Social Supervision
This is especially the case for many real-world tasks where large scale annotated examples are either too expensive to acquire or unavailable due to privacy or data access constraints.
Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data
We show that our student models can compress the huge teacher by up to 26x while still matching or even marginally exceeding the teacher performance in low-resource settings with small amount of labeled data.
On Domain Transfer When Predicting Intent in Text
In many domains, especially enterprise text analysis, there is an abundance of data which can be used for the development of new AI-powered intelligent experiences to improve people's productivity.
Multi-Source Cross-Lingual Model Transfer: Learning What to Share
In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance.
Ranked #10 on
Cross-Lingual NER
on CoNLL Dutch
Zero-Resource Multilingual Model Transfer: Learning What to Share
In this work, we propose a zero-resource multilingual transfer learning model that can utilize training data in multiple source languages, while not requiring target language training data nor cross-lingual supervision.
Actionable Email Intent Modeling with Reparametrized RNNs
Emails in the workplace are often intentional calls to action for its recipients.
Characterizing and Predicting Enterprise Email Reply Behavior
Email is still among the most popular online activities.
