Search Results for author:
Found 77 papers, 28 papers with code
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.
Making PPO even better: Value-Guided Monte-Carlo Tree Search decoding
The key idea is not to throw out the value network, a byproduct of PPO training for evaluating partial output sequences, when decoding text out of the policy network.
Chain-of-Verification Reduces Hallucination in Large Language Models
Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models.
Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
It is also a general-purpose model that can do both text-to-image and image-to-text generation, allowing us to introduce self-contained contrastive decoding methods that produce high-quality outputs.
Ranked #2 on
Text-to-Image Generation
on COCO
Shepherd: A Critic for Language Model Generation
As large language models improve, there is increasing interest in techniques that leverage these models' capabilities to refine their own outputs.
RLCD: Reinforcement Learning from Contrast Distillation for Language Model Alignment
We propose Reinforcement Learning from Contrast Distillation (RLCD), a method for aligning language models to follow natural language principles without using human feedback.
Understanding In-Context Learning via Supportive Pretraining Data
We observe that a continued pretraining on this small subset significantly improves the model's ICL ability, by up to 18%.
Open-Domain Text Evaluation via Meta Distribution Modeling
We investigate MDM for open-domain text generation evaluation under two paradigms: 1) \emph{Generative} MDM, which leverages the Meta-Distribution Methods to generate in-domain negative samples for training discriminator-based metrics; 2) \emph{Discriminative} MDM, which directly uses distribution discrepancies between two language models for evaluation.
Gender Biases in Automatic Evaluation Metrics: A Case Study on Image Captioning
Pretrained model-based evaluation metrics have demonstrated strong performance with high correlations with human judgments in various natural language generation tasks such as image captioning.
Look-back Decoding for Open-Ended Text Generation
Given a prefix (context), open-ended generation aims to decode texts that are coherent, which don't abruptly drift from previous topics, and informative, which don't suffer from undesired repetitions.
OPT-R: Exploring the Role of Explanations in Finetuning and Prompting for Reasoning Skills of Large Language Models
Our study entails finetuning three different sizes of OPT on a carefully curated reasoning corpus, resulting in two sets of finetuned models: OPT-R, finetuned without explanations, and OPT-RE, finetuned with explanations.
RECKONING: Reasoning through Dynamic Knowledge Encoding
In the outer loop, the model learns to use the updated weights to reproduce and answer reasoning questions about the memorized knowledge.
Large Language Model Programs
In recent years, large pre-trained language models (LLMs) have demonstrated the ability to follow instructions and perform novel tasks from a few examples.
Augmented Language Models: a Survey
This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools.
STRUDEL: Structured Dialogue Summarization for Dialogue Comprehension
Abstractive dialogue summarization has long been viewed as an important standalone task in natural language processing, but no previous work has explored the possibility of whether abstractive dialogue summarization can also be used as a means to boost an NLP system's performance on other important dialogue comprehension tasks.
OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization
To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks.
Ranked #15 on
Natural Language Inference
on RTE
Improving Faithfulness of Abstractive Summarization by Controlling Confounding Effect of Irrelevant Sentences
Lack of factual correctness is an issue that still plagues state-of-the-art summarization systems despite their impressive progress on generating seemingly fluent summaries.
ALERT: Adapting Language Models to Reasoning Tasks
Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning.
MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation
We propose MURMUR, a neuro-symbolic modular approach to text generation from semi-structured data with multi-step reasoning.
ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
Large language models show improved downstream task performance when prompted to generate step-by-step reasoning to justify their final answers.
Complementary Explanations for Effective In-Context Learning
Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts, but there has been limited understanding of exactly how these explanations function or why they are effective.
ED-FAITH: Evaluating Dialogue Summarization on Faithfulness
Abstractive summarization models typically generate content unfaithful to the input, thus highlighting the significance of evaluating the faithfulness of generated summaries.
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Machine translation has seen rapid progress with the advent of Transformer-based models.
ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection
Hate speech detection is complex; it relies on commonsense reasoning, knowledge of stereotypes, and an understanding of social nuance that differs from one culture to the next.
Cultural Vocal Bursts Intensity Prediction
Few-Shot Learning
+1
A Review on Language Models as Knowledge Bases
Recently, there has been a surge of interest in the NLP community on the use of pretrained Language Models (LMs) as Knowledge Bases (KBs).
CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning
Using human evaluation and automatic faithfulness metrics, we show that our model significantly reduces all kinds of factual errors on the dialogue summarization, SAMSum corpus.
Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics
Recent works that revealed the vulnerability of dialogue state tracking (DST) models to distributional shifts have made holistic comparisons on robustness and qualitative analyses increasingly important for understanding their relative performance.
Ranked #4 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Dialogue State Tracking
Multi-domain Dialogue State Tracking
+1
Discourse-Aware Soft Prompting for Text Generation
We show that soft-prompt based conditional text generation can be improved with simple and efficient methods that simulate modeling the discourse structure of human written text.
Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs
In this paper, we discuss approaches to detecting when models have beliefs about the world, and we improve on methods for updating model beliefs to be more truthful, with a focus on methods based on learned optimizers or hypernetworks.
How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN
We apply these analyses to four neural language models (an LSTM, a Transformer, Transformer-XL, and GPT-2).
Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries
Current pre-trained models applied to summarization are prone to factual inconsistencies which either misrepresent the source text or introduce extraneous information.
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.
EmailSum: Abstractive Email Thread Summarization
Furthermore, we find that widely used automatic evaluation metrics (ROUGE, BERTScore) are weakly correlated with human judgments on this email thread summarization task.
Ranked #1 on
Email Thread Summarization
on EmailSum (short)
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
On several syntactic and semantic probing tasks, we demonstrate the emergent structural information in the role vectors and improved syntactic interpretability in the TPR layer outputs.
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.
Data Augmentation for Abstractive Query-Focused Multi-Document Summarization
The progress in Query-focused Multi-Document Summarization (QMDS) has been limited by the lack of sufficient largescale high-quality training datasets.
Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
In this paper, we propose a new model architecture for learning multi-modal neuro-symbolic representations for video captioning.
The Amazing World of Neural Language Generation
Neural Language Generation (NLG) {--} using neural network models to generate coherent text {--} is among the most promising methods for automated text creation.
RMM: A Recursive Mental Model for Dialogue Navigation
In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers.
GO FIGURE: A Meta Evaluation of Factuality in Summarization
While neural language models can generate text with remarkable fluency and coherence, controlling for factual correctness in generation remains an open research question.
Substance over Style: Document-Level Targeted Content Transfer
Existing language models excel at writing from scratch, but many real-world scenarios require rewriting an existing document to fit a set of constraints.
Evaluation of Text Generation: A Survey
The paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years.
Reparameterized Variational Divergence Minimization for Stable Imitation
While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from observation (ILO) setting, where trajectories \textit{only} contain expert observations, have not been met with the same success.
A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks
Learning to align these different instruction sets is challenging because: a) different recipes vary in their order of instructions and use of ingredients; and b) video instructions can be noisy and tend to contain far more information than text instructions.
Artemis: A Novel Annotation Methodology for Indicative Single Document Summarization
We describe the annotation process in detail and compare it with other similar evaluation systems.
RMM: A Recursive Mental Model for Dialog Navigation
In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers.
PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
We propose the task of outline-conditioned story generation: given an outline as a set of phrases that describe key characters and events to appear in a story, the task is to generate a coherent narrative that is consistent with the provided outline.
AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
Redundancy-aware extractive summarization systems score the redundancy of the sentences to be included in a summary either jointly with their salience information or separately as an additional sentence scoring step.
Working Memory Graphs
Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art results on supervised tasks involving text sequences.
Contrastive Multi-document Question Generation
In the SL stage, a single-document question generator is trained.
Robust Navigation with Language Pretraining and Stochastic Sampling
Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments.
Discourse Understanding and Factual Consistency in Abstractive Summarization
We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary.
Sentence Mover's Similarity: Automatic Evaluation for Multi-Sentence Texts
For evaluating machine-generated texts, automatic methods hold the promise of avoiding collection of human judgments, which can be expensive and time-consuming.
Learning Compressed Sentence Representations for On-Device Text Processing
Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems.
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017).
Efficient Adaptation of Pretrained Transformers for Abstractive Summarization
Large-scale learning of transformer language models has yielded improvements on a variety of natural language understanding tasks.
Abstractive Text Summarization
Natural Language Understanding
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks.
Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation with latent variables.
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments.
Ranked #2 on
Vision-Language Navigation
on Room2Room
Hierarchically-Structured Variational Autoencoders for Long Text Generation
Variational autoencoders (VAEs) have received much attention recently as an end-to-end architecture for text generation.
Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation
We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task.
Ranked #24 on
Visual Storytelling
on VIST
Discourse-Aware Neural Rewards for Coherent Text Generation
In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text.
Deep Communicating Agents for Abstractive Summarization
We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization.
Ranked #28 on
Abstractive Text Summarization
on CNN / Daily Mail
(using extra training data)
Learning and analyzing vector encoding of symbolic representations
We present a formal language with expressions denoting general symbol structures and queries which access information in those structures.
Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks.
Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems
Language understanding is a key component in a spoken dialogue system.
End-to-End Task-Completion Neural Dialogue Systems
One of the major drawbacks of modularized task-completion dialogue systems is that each module is trained individually, which presents several challenges.
Scaffolding Networks: Incremental Learning and Teaching Through Questioning
We introduce a new paradigm of learning for reasoning, understanding, and prediction, as well as the scaffolding network to implement this paradigm.
Associative Adversarial Networks
In this work, we use Restricted Boltzmann Machines (RBMs) as a higher-level associative memory and learn the probability distribution for the high-level features generated by D. The associative memory samples its underlying probability distribution and G learns how to map these samples to data space.
Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
Natural language understanding (NLU) is a core component of a spoken dialogue system.
