Search Results for author:
Found 156 papers, 81 papers with code
Zero-Shot Learning Through Cross-Modal Transfer
This work introduces a model that can recognize objects in images even if no training data is available for the objects.
Robust Logistic Regression using Shift Parameters (Long Version)
Annotation errors can significantly hurt classifier performance, yet datasets are only growing noisier with the increased use of Amazon Mechanical Turk and techniques like distant supervision that automatically generate labels.
Cross-lingual Pseudo-Projected Expectation Regularization for Weakly Supervised Learning
We consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages.
Reasoning With Neural Tensor Networks for Knowledge Base Completion
We assess the model by considering the problem of predicting additional true relations between entities given a partial knowledge base.
Relaxations for inference in restricted Boltzmann machines
We propose a relaxation-based approximate inference algorithm that samples near-MAP configurations of a binary pairwise Markov random field.
Grounded Compositional Semantics for Finding and Describing Images with Sentences
Previous work on Recursive Neural Networks (RNNs) shows that these models can produce compositional feature vectors for accurately representing and classifying sentences or images.
Cross-lingual Projected Expectation Regularization for Weakly Supervised Learning
We consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages.
Universal Stanford dependencies: A cross-linguistic typology
Revisiting the now de facto standard Stanford dependency representation, we propose an improved taxonomy to capture grammatical relations across languages, including morphologically rich ones.
Recursive Neural Networks Can Learn Logical Semantics
Tree-structured recursive neural networks (TreeRNNs) for sentence meaning have been successful for many applications, but it remains an open question whether the fixed-length representations that they learn can support tasks as demanding as logical deduction.
Learning Distributed Word Representations for Natural Logic Reasoning
Natural logic offers a powerful relational conception of meaning that is a natural counterpart to distributed semantic representations, which have proven valuable in a wide range of sophisticated language tasks.
Learning Distributed Representations for Structured Output Prediction
In recent years, distributed representations of inputs have led to performance gains in many applications by allowing statistical information to be shared across inputs.
Simple MAP Inference via Low-Rank Relaxations
We focus on the problem of maximum a posteriori (MAP) inference in Markov random fields with binary variables and pairwise interactions.
Global Belief Recursive Neural Networks
Recursive Neural Networks have recently obtained state of the art performance on several natural language processing tasks.
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks.
Ranked #1 on
Semantic Similarity
on SICK
Text to 3D Scene Generation with Rich Lexical Grounding
The ability to map descriptions of scenes to 3D geometric representations has many applications in areas such as art, education, and robotics.
Tree-structured composition in neural networks without tree-structured architectures
We hypothesize that neural sequence models like LSTMs are in fact able to discover and implicitly use recursive compositional structure, at least for tasks with clear cues to that structure in the data.
Effective Approaches to Attention-based Neural Machine Translation
Our ensemble model using different attention architectures has established a new state-of-the-art result in the WMT'15 English to German translation task with 25. 9 BLEU points, an improvement of 1. 0 BLEU points over the existing best system backed by NMT and an n-gram reranker.
Ranked #1 on
Machine Translation
on 20NEWS
(Accuracy metric)
A large annotated corpus for learning natural language inference
Understanding entailment and contradiction is fundamental to understanding natural language, and inference about entailment and contradiction is a valuable testing ground for the development of semantic representations.
Ranked #91 on
Natural Language Inference
on SNLI
Stanford Neural Machine Translation Systems for Spoken Language Domains
Neural Machine Translation (NMT), though recently developed, has shown promising results for various language pairs.
Ranked #10 on
Machine Translation
on IWSLT2015 English-Vietnamese
Evaluating the word-expert approach for Named-Entity Disambiguation
Named Entity Disambiguation (NED) is the task of linking a named-entity mention to an instance in a knowledge-base, typically Wikipedia.
A Fast Unified Model for Parsing and Sentence Understanding
Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences.
Ranked #86 on
Natural Language Inference
on SNLI
Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models
We build hybrid systems that translate mostly at the word level and consult the character components for rare words.
A comparison of Named-Entity Disambiguation and Word Sense Disambiguation
Named Entity Disambiguation (NED) is the task of linking a named-entity mention to an instance in a knowledge-base, typically Wikipedia-derived resources like DBpedia.
Universal Dependencies v1: A Multilingual Treebank Collection
Cross-linguistically consistent annotation is necessary for sound comparative evaluation and cross-lingual learning experiments.
Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks
Many shallow natural language understanding tasks use dependency trees to extract relations between content words.
Improving Coreference Resolution by Learning Entity-Level Distributed Representations
A long-standing challenge in coreference resolution has been the incorporation of entity-level information - features defined over clusters of mentions instead of mention pairs.
Ranked #24 on
Coreference Resolution
on OntoNotes
Learning Language Games through Interaction
We introduce a new language learning setting relevant to building adaptive natural language interfaces.
A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
Enabling a computer to understand a document so that it can answer comprehension questions is a central, yet unsolved goal of NLP.
Ranked #3 on
Question Answering
on CNN / Daily Mail
Compression of Neural Machine Translation Models via Pruning
Neural Machine Translation (NMT), like many other deep learning domains, typically suffers from over-parameterization, resulting in large storage sizes.
Deep Reinforcement Learning for Mention-Ranking Coreference Models
Coreference resolution systems are typically trained with heuristic loss functions that require careful tuning.
Ranked #23 on
Coreference Resolution
on OntoNotes
Deep Biaffine Attention for Neural Dependency Parsing
This paper builds off recent work from Kiperwasser & Goldberg (2016) using neural attention in a simple graph-based dependency parser.
Ranked #2 on
Dependency Parsing
on CoNLL-2009
A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue
Task-oriented dialogue focuses on conversational agents that participate in user-initiated dialogues on domain-specific topics.
SceneSeer: 3D Scene Design with Natural Language
We present SceneSeer: an interactive text to 3D scene generation system that allows a user to design 3D scenes using natural language.
Get To The Point: Summarization with Pointer-Generator Networks
Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text).
Ranked #12 on
Extractive Text Summarization
on CNN / Daily Mail
Arc-swift: A Novel Transition System for Dependency Parsing
Transition-based dependency parsers often need sequences of local shift and reduce operations to produce certain attachments.
Key-Value Retrieval Networks for Task-Oriented Dialogue
Neural task-oriented dialogue systems often struggle to smoothly interface with a knowledge base.
Ranked #8 on
Task-Oriented Dialogue Systems
on KVRET
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
The Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets.
Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task
This paper describes the neural dependency parser submitted by Stanford to the CoNLL 2017 Shared Task on parsing Universal Dependencies.
Position-aware Attention and Supervised Data Improve Slot Filling
The combination of better supervised data and a more appropriate high-capacity model enables much better relation extraction performance.
Ranked #7 on
Relation Extraction
on Re-TACRED
Importance sampling for unbiased on-demand evaluation of knowledge base population
Our first contribution is a new importance-sampling based evaluation which corrects for this bias by annotating a new system{'}s predictions on-demand via crowdsourcing.
Compositional Attention Networks for Machine Reasoning
We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning.
Ranked #2 on
Visual Question Answering (VQA)
on CLEVR-Humans
Referring Expression Comprehension
Visual Question Answering (VQA)
+1
Sentences with Gapping: Parsing and Reconstructing Elided Predicates
Sentences with gapping, such as Paul likes coffee and Mary tea, lack an overt predicate to indicate the relation between two or more arguments.
Simpler but More Accurate Semantic Dependency Parsing
While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture between-word relationships that are more closely related to the meaning of a sentence, using graph-structured representations.
Ranked #4 on
Semantic Dependency Parsing
on DM
CoQA: A Conversational Question Answering Challenge
Humans gather information by engaging in conversations involving a series of interconnected questions and answers.
Ranked #3 on
Generative Question Answering
on CoQA
Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts
To understand a sentence like "whereas only 10% of White Americans live at or below the poverty line, 28% of African Americans do" it is important not only to identify individual facts, e. g., poverty rates of distinct demographic groups, but also the higher-order relations between them, e. g., the disparity between them.
Learning to Summarize Radiology Findings
The Impression section of a radiology report summarizes crucial radiology findings in natural language and plays a central role in communicating these findings to physicians.
Semi-Supervised Sequence Modeling with Cross-View Training
We therefore propose Cross-View Training (CVT), a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data.
Ranked #3 on
CCG Supertagging
on CCGbank
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers.
Ranked #34 on
Question Answering
on HotpotQA
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
Dependency trees help relation extraction models capture long-range relations between words.
Ranked #5 on
Relation Classification
on TACRED
Universal Dependency Parsing from Scratch
This paper describes Stanford's system at the CoNLL 2018 UD Shared Task.
Ranked #4 on
Dependency Parsing
on Universal Dependencies
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering
We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets.
Ranked #6 on
Visual Question Answering (VQA)
on GQA test-std
A Structural Probe for Finding Syntax in Word Representations
Recent work has improved our ability to detect linguistic knowledge in word representations.
What Does BERT Look At? An Analysis of BERT's Attention
Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data.
Learning by Abstraction: The Neural State Machine
We introduce the Neural State Machine, seeking to bridge the gap between the neural and symbolic views of AI and integrate their complementary strengths for the task of visual reasoning.
Ranked #2 on
Visual Question Answering (VQA)
on GQA test-std
BAM! Born-Again Multi-Task Networks for Natural Language Understanding
It can be challenging to train multi-task neural networks that outperform or even match their single-task counterparts.
Do Massively Pretrained Language Models Make Better Storytellers?
Large neural language models trained on massive amounts of text have emerged as a formidable strategy for Natural Language Understanding tasks.
Answering Complex Open-domain Questions Through Iterative Query Generation
It is challenging for current one-step retrieve-and-read question answering (QA) systems to answer questions like "Which novel by the author of 'Armada' will be adapted as a feature film by Steven Spielberg?"
Ranked #47 on
Question Answering
on HotpotQA
Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports
Neural abstractive summarization models are able to generate summaries which have high overlap with human references.
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages.
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not.
Ranked #7 on
Question Answering
on Quora Question Pairs
Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation
Question Generation (QG) is fundamentally a simple syntactic transformation; however, many aspects of semantics influence what questions are good to form.
Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection
Universal Dependencies is an open community effort to create cross-linguistically consistent treebank annotation for many languages within a dependency-based lexicalist framework.
Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations
We investigate the problem of generating informative questions in information-asymmetric conversations.
Finding Universal Grammatical Relations in Multilingual BERT
Recent work has found evidence that Multilingual BERT (mBERT), a transformer-based multilingual masked language model, is capable of zero-shot cross-lingual transfer, suggesting that some aspects of its representations are shared cross-lingually.
Biomedical and Clinical English Model Packages in the Stanza Python NLP Library
We introduce biomedical and clinical English model packages for the Stanza Python NLP library.
Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations
At the end of the competition, Chirpy Cardinal progressed to the finals with an average rating of 3. 6/5. 0, a median conversation duration of 2 minutes 16 seconds, and a 90th percentile duration of over 12 minutes.
Contrastive Learning of Medical Visual Representations from Paired Images and Text
Existing work commonly relies on fine-tuning weights transferred from ImageNet pretraining, which is suboptimal due to drastically different image characteristics, or rule-based label extraction from the textual report data paired with medical images, which is inaccurate and hard to generalize.
The EOS Decision and Length Extrapolation
Extrapolation to unseen sequence lengths is a challenge for neural generative models of language.
RNNs can generate bounded hierarchical languages with optimal memory
Recurrent neural networks empirically generate natural language with high syntactic fidelity.
Answering Open-Domain Questions of Varying Reasoning Steps from Text
We develop a unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps.
Ranked #9 on
Question Answering
on HotpotQA
SLM: Learning a Discourse Language Representation with Sentence Unshuffling
We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner.
Pre-Training Transformers as Energy-Based Cloze Models
We introduce Electric, an energy-based cloze model for representation learning over text.
Human-like informative conversations: Better acknowledgements using conditional mutual information
This is because models trained with two contexts - new factual content and conversational history - generate responses that are non-specific w. r. t.
Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser
While many NLP pipelines assume raw, clean texts, many texts we encounter in the wild, including a vast majority of legal documents, are not so clean, with many of them being visually structured documents (VSDs) such as PDFs.
Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
Active learning promises to alleviate the massive data needs of supervised machine learning: it has successfully improved sample efficiency by an order of magnitude on traditional tasks like topic classification and object recognition.
Neural Abstructions: Abstractions that Support Construction for Grounded Language Learning
Although virtual agents are increasingly situated in environments where natural language is the most effective mode of interaction with humans, these exchanges are rarely used as an opportunity for learning.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
Conditional probing: measuring usable information beyond a baseline
Probing experiments investigate the extent to which neural representations make properties -- like part-of-speech -- predictable.
ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts
Reviewing contracts is a time-consuming procedure that incurs large expenses to companies and social inequality to those who cannot afford it.
Hindsight: Posterior-guided training of retrievers for improved open-ended generation
Many text generation systems benefit from using a retriever to retrieve passages from a textual knowledge corpus (e. g., Wikipedia) which are then provided as additional context to the generator.
Fast Model Editing at Scale
To enable easy post-hoc editing at scale, we propose Model Editor Networks using Gradient Decomposition (MEND), a collection of small auxiliary editing networks that use a single desired input-output pair to make fast, local edits to a pre-trained model's behavior.
You Only Need One Model for Open-domain Question Answering
Recent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another reader model.
GreaseLM: Graph REASoning Enhanced Language Models for Question Answering
Answering complex questions about textual narratives requires reasoning over both stated context and the world knowledge that underlies it.
Synthetic Disinformation Attacks on Automated Fact Verification Systems
Automated fact-checking is a needed technology to curtail the spread of online misinformation.
Detecting Label Errors by using Pre-Trained Language Models
We show that large pre-trained language models are inherently highly capable of identifying label errors in natural language datasets: simply examining out-of-sample data points in descending order of fine-tuned task loss significantly outperforms more complex error-detection mechanisms proposed in previous work.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Memory-Based Model Editing at Scale
We find that only SERAC achieves high performance on all three problems, consistently outperforming existing approaches to model editing by a significant margin.
Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset
One concern with the rise of large language models lies with their potential for significant harm, particularly from pretraining on biased, obscene, copyrighted, and private information.
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
We present Chirpy Cardinal, an open-domain social chatbot.
When can I Speak? Predicting initiation points for spoken dialogue agents
Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilted conversational flow.
Truncation Sampling as Language Model Desmoothing
In this light, truncation algorithms aim to perform desmoothing, estimating a subset of the support of the true distribution.
Characterizing Intrinsic Compositionality in Transformers with Tree Projections
To evaluate this possibility, we describe an unsupervised and parameter-free method to \emph{functionally project} the behavior of any transformer into the space of tree-structured networks.
Fixing Model Bugs with Natural Language Patches
Current approaches for fixing systematic problems in NLP models (e. g. regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts.
On Measuring the Intrinsic Few-Shot Hardness of Datasets
While advances in pre-training have led to dramatic improvements in few-shot learning of NLP tasks, there is limited understanding of what drives successful few-shot adaptation in datasets.
Holistic Evaluation of Language Models
We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models.
Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference
While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs.
Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models
A growing ecosystem of large, open-source foundation models has reduced the labeled data and technical expertise necessary to apply machine learning to many new problems.
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
In this paper, we identify a property of the structure of an LLM's probability function that is useful for such detection.
ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation
We argue that this concern is realized for the COGS benchmark.
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
A trustworthy real-world prediction system should produce well-calibrated confidence scores; that is, its confidence in an answer should be indicative of the likelihood that the answer is correct, enabling deferral to an expert in cases of low-confidence predictions.
Meta-Learning Online Adaptation of Language Models
We meta-train a small, autoregressive model to reweight the language modeling loss for each token during online fine-tuning, with the objective of maximizing the out-of-date base question-answering model's ability to answer questions about a document after a single weighted gradient step.
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
The information stored in large language models (LLMs) falls out of date quickly, and retraining from scratch is often not an option.
Backpack Language Models
We can interpret a sense vector by inspecting its (non-contextual, linear) projection onto the output space, and intervene on these interpretable hooks to change the model's behavior in predictable ways.
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Existing methods for gaining such steerability collect human labels of the relative quality of model generations and fine-tune the unsupervised LM to align with these preferences, often with reinforcement learning from human feedback (RLHF).
Grokking of Hierarchical Structure in Vanilla Transformers
When analyzing the relationship between model-internal properties and grokking, we find that optimal depth for grokking can be identified using the tree-structuredness metric of \citet{murty2023projections}.
An Emulator for Fine-Tuning Large Language Models using Small Language Models
To aid in doing so, we introduce a novel technique for decoupling the knowledge and skills gained in these two stages, enabling a direct answer to the question, "What would happen if we combined the knowledge learned by a large model during pre-training with the knowledge learned by a small model during fine-tuning (or vice versa)?"
Pushdown Layers: Encoding Recursive Structure in Transformer Language Models
Recursion is a prominent feature of human language, and fundamentally challenging for self-attention due to the lack of an explicit recursive-state tracking mechanism.
Fine-tuning Language Models for Factuality
The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines.
Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching
While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language model rescoring.
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge.
Ranked #3 on
Question Answering
on QuALITY
Model Editing with Canonical Examples
The Backpack defines a large bank of sense vectors--a decomposition of the different uses of each word--which are weighted and summed to form the output logits of the model.
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability.
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text
Models such as GPT-4 and Med-PaLM 2 have demonstrated impressive performance on a wide variety of biomedical NLP tasks.
ReFT: Representation Finetuning for Language Models
LoReFT is a drop-in replacement for existing PEFTs and learns interventions that are 10x-50x more parameter-efficient than prior state-of-the-art PEFTs.
