Search Results for author:
Found 43 papers, 14 papers with code
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations
Multiple-choice MRC is one of the most studied tasks in MRC due to the convenience of evaluation and the flexibility of answer format.
Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning
We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with constraint reasoning for solving pattern de-mixing problems, typically in an unsupervised or very-weakly-supervised setting.
Commit0: Library Generation from Scratch
As a benchmark, Commit0 is designed to move beyond static one-shot code generation towards agents that must process long-form natural language specifications, adapt to multi-stage feedback, and generate code with complex dependencies.
Are Triggers Needed for Document-Level Event Extraction?
Our research shows that trigger effectiveness varies based on the extraction task's characteristics and data quality, with basic, automatically-generated triggers serving as a viable alternative to human-annotated ones.
A Controlled Study on Long Context Extension and Generalization in LLMs
Broad textual understanding and in-context learning require language models that utilize full document contexts.
WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
The increasing availability of real-world conversation data offers exciting opportunities for researchers to study user-chatbot interactions.
Great Memory, Shallow Reasoning: Limits of $k$NN-LMs
$K$-nearest neighbor language models ($k$NN-LMs), which integrate retrieval with next-word prediction, have demonstrated strong performance in language modeling as well as downstream NLP benchmarks.
The Future of Open Human Feedback
In this work, we bring together interdisciplinary experts to assess the opportunities and challenges to realizing an open ecosystem of human feedback for AI.
WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries
While hallucinations of large language models (LLMs) prevail as a major challenge, existing evaluation benchmarks on factuality do not cover the diverse domains of knowledge that the real-world users of LLMs seek information about.
I Could've Asked That: Reformulating Unanswerable Questions
We curate CouldAsk, an evaluation benchmark composed of existing and new datasets for document-grounded question answering, specifically designed to study reformulating unanswerable questions.
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
This study focuses on the topic of LLMs assist NLP Researchers, particularly examining the effectiveness of LLM in assisting paper (meta-)reviewing and its recognizability.
WildChat: 1M ChatGPT Interaction Logs in the Wild
In addition to timestamped chat transcripts, we enrich the dataset with demographic data, including state, country, and hashed IP addresses, alongside request headers.
kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning
Task-Oriented Parsing (TOP) enables conversational assistants to interpret user commands expressed in natural language, transforming them into structured outputs that combine elements of both natural language and intent/slot tags.
Language Model Inversion
We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of information about the preceding text.
UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations
To instead investigate the ability to model unusual, unexpected, and unlikely situations, we explore the task of uncommonsense abductive reasoning.
In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search
To effectively use large language models (LLMs) for real-world queries, it is imperative that they generalize to the long-tail distribution, i. e. rare examples where models exhibit low confidence.
JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction
Furthermore, the copy mechanism in value generator and the value attention module in value classifier help our model address the data discrepancy issue by only focusing on the relevant part of input text and ignoring other information which causes the discrepancy issue such as sentence structure in the text.
Aspect-based Meeting Transcript Summarization: A Two-Stage Approach with Weak Supervision on Sentence Classification
Then we merge the sentences selected for a specific aspect as the input for the summarizer to produce the aspect-based summary.
DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
Moreover, a significant gap in the current landscape is the absence of a realistic benchmark for evaluating the effectiveness of grounding LLMs on heterogeneous knowledge sources (e. g., knowledge base and text).
Symbolic Planning and Code Generation for Grounded Dialogue
Large language models (LLMs) excel at processing and generating both text and code.
Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach
In this paper, we propose to incorporate the label dependencies among entity types into a multi-task learning framework for better MRC-based NER.
Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables
Furthermore, TAG-QA outperforms the end-to-end model T5 by 16% and 12% on BLEU-4 and PARENT F-score, respectively.
Self-Calibrated Cross Attention Network for Few-Shot Segmentation
Moreover, when calculating SCCA, we design a scaled-cosine mechanism to better utilize the support features for similarity calculation.
Ranked #9 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Click-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce
Position bias, the phenomenon whereby users tend to focus on higher-ranked items of the search result list regardless of the actual relevance to queries, is prevailing in many ranking systems.
Structure-Sensitive Graph Dictionary Embedding for Graph Classification
Instead of a plain use of a base graph dictionary, we propose the variational graph dictionary adaptation (VGDA) to generate a personalized dictionary (named adapted graph dictionary) for catering to each input graph.
Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations
Instead of using direct supervision, this work proposes an approach for abductive commonsense reasoning that exploits the fact that only a subset of explanations is correct for a given context.
HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision
Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers.
Serenity: Library Based Python Code Analysis for Code Completion and Automated Machine Learning
We demonstrate the efficiency and usefulness of Serenity's analysis in two applications: code completion and automated machine learning.
Compositional Task-Oriented Parsing as Abstractive Question Answering
Task-oriented parsing (TOP) aims to convert natural language into machine-readable representations of specific tasks, such as setting an alarm.
Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots
Few-shot table-to-text generation is a task of composing fluent and faithful sentences to convey table content using limited data.
Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors
Through further analysis of the ASR outputs, we find that in some cases the sentiment words, the key sentiment elements in the textual modality, are recognized as other words, which makes the sentiment of the text change and hurts the performance of multimodal sentiment models directly.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning
DRNets compensate for the limited data by exploiting and magnifying the rich prior knowledge about the thermodynamic rules governing the mixtures of crystals with constraint reasoning seamlessly integrated into neural network optimization.
Enriching Non-Autoregressive Transformer with Syntactic and Semantic Structures for Neural Machine Translation
In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance.
HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders
This in turn leads to a challenging and long-standing problem in the field of computer science - how to perform ac-curate multi-label classification with hundreds of labels?
Evaluating Multi-label Classifiers with Noisy Labels
In the real world, it is more common to deal with noisy datasets than clean datasets, given how modern datasets are labeled by a large group of annotators on crowdsourcing platforms, but little attention has been given to evaluating multi-label classifiers with noisy labels.
Zero Training Overhead Portfolios for Learning to Solve Combinatorial Problems
There has been an increasing interest in harnessing deep learning to tackle combinatorial optimization (CO) problems in recent years.
Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation
In this paper, we claim that the syntactic and semantic structures among natural language are critical for non-autoregressive machine translation and can further improve the performance.
Graph Deformer Network
In this paper, we propose a simple yet effective graph deformer network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images.
Co-Saliency Detection with Co-Attention Fully Convolutional Network
Co-saliency detection aims to detect common salient objects from a group of relevant images.
Dual-Attention Graph Convolutional Network
Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification.
Deep Reasoning Networks: Thinking Fast and Slow, for Pattern De-mixing
We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving pattern de-mixing problems, typically in an unsupervised or weakly-supervised setting.
Deep Reasoning Networks: Thinking Fast and Slow
At a high level, DRNets encode a structured latent space of the input data, which is constrained to adhere to prior knowledge by a reasoning module.
When Work Matters: Transforming Classical Network Structures to Graph CNN
In this paper, we aim to give a comprehensive analysis of when work matters by transforming different classical network structures to graph CNN, particularly in the basic graph recognition problem.
Ranked #3 on
Graph Classification
on IMDb-B
