Papers by Eric Xing

27 papers
Efficient (Soft) Q-Learning for Text Generation with Limited Good Data (2022.findings-emnlp)

Copied to clipboard

Challenge: Maximum likelihood estimation (MLE) is the predominant method for training text generation models.
Approach: They propose a new RL formulation for text generation from the soft Q-learning perspective using path consistency learning to combine the best of on-/off-policy updates and learn effectively from sparse reward.
Outcome: The proposed approach outperforms MLE and previous RL methods in a wide range of tasks.
Self-Training for Jointly Learning to Ask and Answer Questions (N18-1)

Copied to clipboard

Challenge: Existing methods for question answering and question generation are hard to obtain in many domains.
Approach: They propose a method for jointly learning to ask and answer questions . they leverage unlabeled text along with labeled question answer pairs for learning .
Outcome: The proposed method improves on four benchmark datasets on question answering and question generation tasks.
Evaluating Step-by-Step Reasoning through Symbolic Verification (2024.findings-naacl)

Copied to clipboard

Challenge: Pre-trained language models (LMs) have shown remarkable reasoning performance using explanations or chain-of-thoughts (CoT)) for in-context learning.
Approach: They propose to use symbolic examples to iteratively reason over symbolic examples and to recover Prolog’s backward chaining algorithm to iterate over KBs.
Outcome: The proposed model performs better on length generalization benchmarks than CoT on explanations and chain-of-thoughts (CoT) tasks.
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Copied to clipboard

Challenge: Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach: They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome: Texar supports machine translation, summarization, dialog, content manipulation, and more.
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods to solve geometric problems are dependent on handcraft rules and limited on small-scale datasets.
Approach: They propose a Geometric Question Answering dataset with 5,010 geometric problems with corresponding annotated programs to illustrate the solving process.
Outcome: The proposed method is significantly lower than human performance on the proposed dataset than on a publicly available dataset.
Target-Guided Open-Domain Conversation (P19-1)

Copied to clipboard

Challenge: a new study aims to improve opendomain chat systems by integrating goals and strategy into the system.
Approach: They propose a structured approach that introduces coarse-grained keywords to control intended content of system responses and attains smooth conversation transition through turn-level supervised learning.
Outcome: The proposed system produces meaningful and effective conversations significantly better than other approaches.
Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-ray Reports (P19-1)

Copied to clipboard

Challenge: Existing studies do not consider the complex structure information between and within report sections.
Approach: They propose a framework which exploits the structure information between and within report sections for generating CXR imaging reports.
Outcome: The proposed framework achieves state-of-the-art performance on two CXR report datasets.
A Neural Architecture for Automated ICD Coding (P18-1)

Copied to clipboard

Challenge: Medical coding is time-consuming, expensive, and error prone.
Approach: They propose to use diagnosis descriptions (DDs) of a patient as inputs to select the most relevant ICD codes.
Outcome: The proposed algorithms perform on a clinical dataset with 59K patient visits.
Knowledge-Aware Meta-learning for Low-Resource Text Classification (2021.emnlp-main)

Copied to clipboard

Challenge: Existing meta-learning techniques may not be well-suited to testing tasks when they are not well-supported by training tasks.
Approach: They propose to use a meta-learning algorithm to add representations for each sentence learned from the extracted sentence-specific knowledge graph.
Outcome: The proposed model is able to represent each sentence learned from the extracted knowledge graph under supervised adaptation and unsupervised adaptation settings.
Standardized Tests as benchmarks for Artificial Intelligence (D18-3)

Copied to clipboard

Challenge: Standardized tests have been proposed as replacements to the Turing test as a driver for progress in AI.
Approach: et al. propose standardized tests as replacements to the Turing test as a driver for progress in AI.
Outcome: a series of standardized tests have been proposed as replacements to the Turing test . the tutorial categorizes open domain and closed domain tests into two categories . open domain tests require the system to have significant domain knowledge and reasoning capabilities.
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Empirical evaluations on eight recent LLMs reveal that DRPO significantly enhances alignment performance, enabling base models to outperform their SFT/RLHF-tuned counterparts.
Approach: They propose a tuning-free approach to self-alignment called Dynamic Rewarding with Prompt Optimization (DRPO) it leverages a dynamic rewarding mechanism to identify and rectify alignment weaknesses .
Outcome: The proposed approach outperforms existing methods and is highly adaptable to various alignment challenges.
Fast Matrix Multiplications for Lookup Table-Quantized LLMs (2024.findings-emnlp)

Copied to clipboard

Challenge: generative (tokenby-token) inference is memory-bound and requires a large amount of memory to perform.
Approach: They propose a lookup table engine for weight-quantized large language models that uses offline restructuring of the quantized weight matrix to minimize bit manipulations associated with unpacking.
Outcome: The proposed kernel can be 2-4x faster than existing GEMM kernels while achieving performance gains of 1.5 to 2 times.
Towards Visual Question Answering on Pathology Images (2021.acl-short)

Copied to clipboard

Challenge: Pathology imaging is used for identifying the causes and effects of diseases or injuries.
Approach: They propose a pathological visual question answering framework to analyze pathology images and answer medical questions related to these images.
Outcome: The proposed framework performs self-supervised pretraining and finetuning end-to-end to learn powerful visual and textual representations jointly and automatically identifies and excludes noisy self-controlled examples from pretraining.
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Radiology report generation aims at generating descriptive text from radiology images automatically.
Approach: They propose a weakly supervised contrastive loss method that generates descriptive text from radiology images automatically.
Outcome: The proposed method outperforms previous work on correctness and text generation metrics for two public benchmarks.
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for finding the optimal prompt for a task are difficult to optimize.
Approach: They propose an efficient discrete prompt optimization approach with reinforcement learning that generates the optimal discrete stimulus after training with reward.
Outcome: The proposed approach is based on a parameter-efficient policy network that generates the optimal discrete prompt after training with reward.
On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)

Copied to clipboard

Challenge: under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors.
Approach: They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients .
Outcome: The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets.
On the Automatic Generation of Medical Imaging Reports (P18-1)

Copied to clipboard

Challenge: a complete medical imaging report contains multiple heterogeneous forms of information, including findings and tags . abnormal regions in medical images are difficult to identify and the reports are typically long, containing multiple sentences.
Approach: They propose a multi-task learning framework which predicts tags and generates paragraphs for abnormal regions in medical images.
Outcome: The proposed framework can generate long paragraphs on two publicly available datasets.
BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to construct knowledge graphs are limited to a small set of relations due to manual cost or restrictions in text corpus.
Approach: They propose to automatically construct knowledge graphs (KGs) of diverse new relations from pretrained language models that accept knowledge queries with prompts.
Outcome: The proposed framework extracts knowledge of over 400 new relations from pretrained language models, including RoBERTaNet, with minimal input of a relation definition and a few shot of example entity pairs.
Data-to-Text Generation with Style Imitation (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles.
Approach: They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach .
Outcome: The proposed approach achieves stronger performance than a range of comparison methods.
A Data-Centric Framework for Composable NLP Workflows (2020.emnlp-demos)

Copied to clipboard

Challenge: Empirical natural language processing (NLP) systems involve interoperation among multiple components . a wealth of NLP toolkits exist ( 4), such as spaCy, DKPro, CoreNLP.
Approach: They propose a unified open-source framework that supports fast development of NLP workflows . framework includes processors for NLP tasks, visualization, and annotation .
Outcome: The framework offers processors for NLP tasks, visualization, and annotation, and is extensible . it is delivered through two modularized yet integratable open-source projects, Forte and Stave .
RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs (2024.naacl-demo)

Copied to clipboard

Challenge: Recent advances in machine learning (ML) are attributed to large language models (LLMs), but their escalating memory requirements require developers to partition a large model to distribute it across multiple GPUs or TPUs.
Approach: They propose a lightweight and user-friendly tool to automate distributed training and inference for LLMs and to simplify ML pipeline development.
Outcome: The proposed tool automates distributed training and inference for LLMs, and simplifies ML pipeline development.
Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming (2023.findings-acl)

Copied to clipboard

Challenge: Pre-trained large language models struggle to perform logical reasoning reliably despite advances in scale and compositionality.
Approach: They propose a Differentiable Symbolic Reasoning framework that uses symbolic programming to improve LMs' logical reasoning abilities.
Outcome: The proposed framework outperforms competitive baselines when faced with systematic changes in sequence length.
Progressive Generation of Long Text with Pretrained Language Models (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for "long" text generation are limited to outputs of 50-200 tokens . however, our proposed ProGen generates coherent long passages of text in a progressive manner .
Approach: They propose a method for generating coherent long passages of text in a progressive manner . they first produce domain-specific content keywords and then refine them into complete passages . human evaluation validates that their proposed generation is more coherent .
Outcome: The proposed method produces domain-specific content keywords and refines them into complete passages in multiple stages.
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Natural language generation (NLG) tasks have complex nature and require manual evaluation.
Approach: They propose a unifying perspective based on the nature of information change in NLG tasks . they propose 'information alignment' metrics that can be used to evaluate different aspects of NLG .
Outcome: The proposed metrics achieve stronger or comparable correlations with human judgement compared to state-of-the-art metrics in diverse tasks.
ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to data-to-text generation require limited training examples . a data-based approach is based on a set of pre-trained language models with optional finetuning.
Approach: They propose a data-to-text generation task that makes use of any given (or no) examples.
Outcome: The proposed approach improves on baselines on a dataset with zero/few/full-shot settings.
A Study on the Calibration of In-context Learning (2024.naacl-long)

Copied to clipboard

Challenge: Prior research has demonstrated improvements in the calibration of language models (LMs) in-context learning is a popular method for adapting static LMs to safety-critical domains.
Approach: They use in-context learning to adapt static language models through tailored prompts to a wide range of tasks and find that miscalibration occurs in low-shot settings.
Outcome: The proposed calibrations show that models exhibit increased miscalibration before achieving better calibration in low-shot settings.
Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies on aspect-based abstractive summarization assume a small set of aspects and do not consider other diverse aspects.
Approach: They propose a weak supervision construction method and an aspect modeling scheme to solve this problem.
Outcome: The proposed method significantly expands the application of the task in practice.

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